Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.
Add SEO meta descriptions to all doc pages (#757)
Louis Choquelfd6e9d9d4716
diff --git a/.github/workflows/doc-check.yml b/.github/workflows/doc-check.ymlindex 90fbff650..45a58e877 100644--- a/.github/workflows/doc-check.yml+++ b/.github/workflows/doc-check.yml@@ -34,7 +34,7 @@ jobs:- name: Install mkdocsrun: |python -m pip install --upgrade pip- pip install mkdocs==1.6.1 mkdocs-material==9.6.14 mkdocs-glightbox==0.4.0 mkdocs-meta-manager==1.1.0+ pip install mkdocs==1.6.1 mkdocs-material==9.6.14 mkdocs-glightbox==0.4.0 mkdocs-meta-manager==1.1.0 mkdocs-redirects==1.2.2- name: Check documentation buildrun: mkdocs build --strictdiff --git a/.pipelex/inference/backends/pipelex_gateway.toml b/.pipelex/inference/backends/pipelex_gateway.tomlindex bca075b7c..5b02901ee 100644--- a/.pipelex/inference/backends/pipelex_gateway.toml+++ b/.pipelex/inference/backends/pipelex_gateway.toml@@ -30,7 +30,7 @@# with direct provider backends (openai, anthropic, etc.) instead.## Documentation:-# https://docs.pipelex.com/home/7-configuration/config-technical/inference-backend-config/+# https://docs.pipelex.com/latest/configuration/config-technical/inference-backend-config/# Support: https://go.pipelex.com/discord#################################################################################diff --git a/.pipelex/inference/backends/pipelex_gateway_models.md b/.pipelex/inference/backends/pipelex_gateway_models.mdindex eeab8851d..be0c6ff78 100644--- a/.pipelex/inference/backends/pipelex_gateway_models.md+++ b/.pipelex/inference/backends/pipelex_gateway_models.md@@ -1,6 +1,6 @@# Pipelex Gateway — Available ModelsThis file lists the LLMs, document extraction models, and image generation models currently available through Pipelex Gateway.-For configuration details, see the [documentation](https://docs.pipelex.com/latest/home/5-setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-for-getting-started).+For configuration details, see the [documentation](https://docs.pipelex.com/latest/setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-and-most-powerful-for-getting-started).## Language Models (LLM)@@ -515,6 +515,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late> **AUTO-GENERATED FILE** - Do not edit manually.-> Last updated: 2026-03-10T06:49:52Z+> Last updated: 2026-03-14T15:45:06Z>> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.\ No newline at end of filediff --git a/.pipelex/inference/backends/pipelex_gateway_models_plain.md b/.pipelex/inference/backends/pipelex_gateway_models_plain.mdindex cd75c6723..a69794b49 100644--- a/.pipelex/inference/backends/pipelex_gateway_models_plain.md+++ b/.pipelex/inference/backends/pipelex_gateway_models_plain.md@@ -1,7 +1,7 @@# Pipelex Gateway — Available Models (Plain Text)This file lists the LLMs, document extraction models, and image generation models currently available through Pipelex Gateway.-For configuration details, see the [documentation](https://docs.pipelex.com/latest/home/5-setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-for-getting-started).+For configuration details, see the [documentation](https://docs.pipelex.com/latest/setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-and-most-powerful-for-getting-started).**Note:** This is the plain-text readable version. See `pipelex_gateway_models.md` for the HTML-styled version.@@ -193,6 +193,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late> **AUTO-GENERATED FILE** - Do not edit manually.-> Last updated: 2026-03-10T06:49:52Z+> Last updated: 2026-03-14T15:45:06Z>> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.\ No newline at end of filediff --git a/CHANGELOG.md b/CHANGELOG.mdindex cb0c2d55c..931eb69ee 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -186,7 +186,7 @@**`pipelex build runner`** — Now automatically generates both the Python runner file AND the required Pydantic structures. When you run this command, it creates a complete, ready-to-execute Python script that imports the generated structures, so you can immediately use typed objects in your pipeline code.- See the [Build Commands documentation](https://docs.pipelex.com/home/9-tools/cli/#build-commands) for usage examples.+ See the [Build Commands documentation](https://docs.pipelex.com/latest/tools/cli/build/) for usage examples.- **New Backends & Models**:- **Hugging Face Inference** — Support for Hugging Face Inference API, including `qwen-image` text-to-image model.@@ -209,7 +209,7 @@- **LLM Reasoning Controls**: Unified support for "Thinking" models (Chain of Thought) with `reasoning_effort`, `reasoning_budget`, and `thinking_mode` parameters. Supports Anthropic Extended Thinking, Google Gemini Thinking, OpenAI Reasoning (`o1`/`o3`), and Mistral/Magistral models. Includes new presets: `$deep-analysis` and `$quick-reasoning`.- **Image-to-Image Generation**: `PipeImgGen` now supports input images via `input_images` field, with `InputImagesTaxonomy` for provider-specific handling and variable reference detection (`{{ var }}`, `$var`, `@var`) in prompts.- **PipeCompose "Construct" Mode**: New `construct` mode for building structured objects (dictionaries/Pydantic models) directly from variables.-- **Nested concepts in inline structures**: You can now define nested structures for your concepts in your `.plx` files. Learn more here: [Nested Concepts in Inline Structures](https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/inline-structures).+- **Nested concepts in inline structures**: You can now define nested structures for your concepts in your `.plx` files. Learn more here: [Nested Concepts in Inline Structures](https://docs.pipelex.com/latest/building-methods/concepts/inline-structures).### Breaking Changes@@ -456,7 +456,7 @@- **LLM Reasoning Controls**: Unified support for "Thinking" models (Chain of Thought) with `reasoning_effort`, `reasoning_budget`, and `thinking_mode` parameters. Supports Anthropic Extended Thinking, Google Gemini Thinking, OpenAI Reasoning (`o1`/`o3`), and Mistral/Magistral models. Includes new presets: `$deep-analysis` and `$quick-reasoning`.- **Image-to-Image Generation**: `PipeImgGen` now supports input images via `input_images` field, with `InputImagesTaxonomy` for provider-specific handling and variable reference detection (`{{ var }}`, `$var`, `@var`) in prompts.- **PipeCompose "Construct" Mode**: New `construct` mode for building structured objects (dictionaries/Pydantic models) directly from variables.- - **Nested concepts in inline structures**: You can now define nested structures for your concepts in your `.plx` files. Learn more here: [Nested Concepts in Inline Structures](https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/inline-structures).+ - **Nested concepts in inline structures**: You can now define nested structures for your concepts in your `.plx` files. Learn more here: [Nested Concepts in Inline Structures](https://docs.pipelex.com/latest/building-methods/concepts/inline-structures).### Added- **Builder Auto-Repair**: Self-healing capabilities including auto-generation of undeclared concepts, multiplicity mismatch fixes, and pruning of unreachable pipes/unused concepts.@@ -558,7 +558,7 @@**`pipelex build runner`** — Now automatically generates both the Python runner file AND the required Pydantic structures. When you run this command, it creates a complete, ready-to-execute Python script that imports the generated structures, so you can immediately use typed objects in your pipeline code.- See the [Build Commands documentation](https://docs.pipelex.com/home/9-tools/cli/#build-commands) for usage examples.+ See the [Build Commands documentation](https://docs.pipelex.com/latest/tools/cli/build/) for usage examples.- **New Backends & Models**:- **Hugging Face Inference** — Support for Hugging Face Inference API, including `qwen-image` text-to-image model.@@ -1237,13 +1237,13 @@ This is all in the spirit of making Pipelex a declarative language, where you exWe've completely redesigned how LLMs are configured and accessed in Pipelex, making it more flexible and easier to get started:-- **Get started in seconds** with [Pipelex Inference](home/7-configuration/config-technical/inference-backend-config.md): Use a single API key to access all major LLM providers (OpenAI, Anthropic, Google, Mistral, and more)+- **Get started in seconds** with [Pipelex Inference](configuration/config-technical/inference-backend-config.md): Use a single API key to access all major LLM providers (OpenAI, Anthropic, Google, Mistral, and more)- **Flexible backend configuration**: Configure multiple inference backends (Azure OpenAI, Amazon Bedrock, Vertex AI, etc.) through simple TOML files in `.pipelex/inference/`-- **Smart model routing**: Automatically route models to the right backend using [routing profiles](home/7-configuration/config-technical/inference-backend-config.md#routing-profiles) with pattern matching+- **Smart model routing**: Automatically route models to the right backend using [routing profiles](configuration/config-technical/inference-backend-config.md#routing-profiles) with pattern matching- **User-friendly aliases**: Define shortcuts like `best-claude` → `claude-4.1-opus` with optional fallback chains- **Cost-aware model specs**: Each model includes detailed pricing, capabilities, and constraints for better cost management-For complete details, see the [Inference Backend Configuration](home/7-configuration/config-technical/inference-backend-config.md) documentation.+For complete details, see the [Inference Backend Configuration](configuration/config-technical/inference-backend-config.md) documentation.### Addeddiff --git a/Makefile b/Makefileindex a98f10331..81b8e5232 100644--- a/Makefile+++ b/Makefile@@ -802,6 +802,9 @@ check-TODOs: envDOCS_VERSION := $(shell grep -m1 '^version = ' pyproject.toml | sed -E 's/version = "(.*)"/\1/')SITE_DOMAIN := $(shell cat docs/CNAME 2>/dev/null | tr -d '[:space:]')+# Authoritative robots.txt for the domain root (docs.pipelex.com/robots.txt).+# Deployed by docs-deploy-root. Note: docs/robots.txt is a no-op — it only+# lands at /latest/robots.txt, which crawlers ignore per RFC 9309.define ROOT_ROBOTS_TXTUser-agent: *Allow: /latest/@@ -818,9 +821,22 @@ define ROOT_INDEX_HTML<title>Redirecting to latest documentation...</title><meta http-equiv="refresh" content="0;url=/latest/"><link rel="canonical" href="https://$(SITE_DOMAIN)/latest/">+ <style>+ body {+ margin: 0;+ min-height: 100vh;+ display: flex;+ align-items: center;+ justify-content: center;+ background: #2e303e;+ color: #ccc;+ font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;+ }+ a { color: #45BF9F; text-decoration: none; }+ </style></head><body>- <p>Redirecting to <a href="/latest/">latest documentation</a>...</p>+ <p>Redirecting to <a href="/latest/">latest documentation</a>…</p></body></html>endefdiff --git a/README.md b/README.mdindex 3c8ef1f7a..0a7923b76 100644--- a/README.md+++ b/README.md@@ -111,11 +111,11 @@ Get **free credits** with a single API key for LLMs, document extraction, and im### Option B: Bring Your Own Keys-Use your existing API keys from OpenAI, Anthropic, Google, Mistral, etc. See [Configure AI Providers](https://docs.pipelex.com/home/5-setup/configure-ai-providers/).+Use your existing API keys from OpenAI, Anthropic, Google, Mistral, etc. See [Configure AI Providers](https://docs.pipelex.com/latest/setup/configure-ai-providers/).### Option C: Local AI-Run models locally with Ollama, vLLM, LM Studio, or llama.cpp — no API keys required. See [Configure AI Providers](https://docs.pipelex.com/home/5-setup/configure-ai-providers/).+Run models locally with Ollama, vLLM, LM Studio, or llama.cpp — no API keys required. See [Configure AI Providers](https://docs.pipelex.com/latest/setup/configure-ai-providers/).# Example: CV Batch Screening@@ -535,12 +535,12 @@ pip install "pipelex[anthropic,google,google-genai,mistralai,bedrock,fal,linkup,Pipelex supports two independent telemetry streams:-- **Gateway Telemetry**: When using Pipelex Gateway, telemetry must be enabled (tied to your hashed API key) to monitor service quality and enforce fair usage. [Learn more](https://docs.pipelex.com/home/5-setup/telemetry/#gateway-telemetry-pipelex-controlled)-- **Custom Telemetry**: User-controlled via `.pipelex/telemetry.toml` for your own observability systems (Langfuse, PostHog, OTLP). [Learn more](https://docs.pipelex.com/home/5-setup/telemetry/#custom-telemetry-user-controlled)+- **Gateway Telemetry**: When using Pipelex Gateway, telemetry must be enabled (tied to your hashed API key) to monitor service quality and enforce fair usage. [Learn more](https://docs.pipelex.com/latest/setup/telemetry/#gateway-telemetry-pipelex-controlled)+- **Custom Telemetry**: User-controlled via `.pipelex/telemetry.toml` for your own observability systems (Langfuse, PostHog, OTLP). [Learn more](https://docs.pipelex.com/latest/setup/telemetry/#custom-telemetry-user-controlled)**We only collect technical data** (model names, token counts, latency, error rates) — never your prompts, completions, or business data. Set `DO_NOT_TRACK=1` to disable all telemetry (note: Gateway requires telemetry to function).-For more details, see the [Telemetry Documentation](https://docs.pipelex.com/home/5-setup/telemetry/) or read our [Privacy Policy](https://go.pipelex.com/privacy-policy).+For more details, see the [Telemetry Documentation](https://docs.pipelex.com/latest/setup/telemetry/) or read our [Privacy Policy](https://go.pipelex.com/privacy-policy).## Contributingdiff --git a/docs/.meta.yml b/docs/.meta.ymlindex e3cf63b09..b8bb8184f 100644--- a/docs/.meta.yml+++ b/docs/.meta.yml@@ -1,3 +1,3 @@image: https://d2cinlfp2qnig1.cloudfront.net/docs/pipelex_banner_1200x630.png?v=1-description: Docs for Pipelex, open-source language for repeatable AI workflows.-keywords: [pipelex, ai, llm, workflows, knowledge pipelines, pipelines, deterministic, repeatable, framework, language]+description: "Pipelex documentation — build executable AI methods with structured validation, pipeline orchestration, and 60+ model support."+keywords: [pipelex, ai, llm, methods, executable methods, pipelines, deterministic, structured outputs, declarative, workflows]diff --git a/docs/404.html b/docs/404.htmlindex 01c7ef06e..59abafc98 100644--- a/docs/404.html+++ b/docs/404.html@@ -2,7 +2,83 @@<html><head><meta charset="utf-8">- <title>Redirecting...</title>+ <meta name="viewport" content="width=device-width, initial-scale=1">+ <meta name="robots" content="noindex, nofollow">+ <link rel="canonical" href="https://docs.pipelex.com/latest/">+ <title>Page not found | Pipelex Documentation</title>+ <style>+ :root {+ color-scheme: dark;+ --bg: #2e303e;+ --panel: #393b4d;+ --text: #f1f3f8;+ --muted: #b6bdd1;+ --accent: #45bf9f;+ --accent-hover: #62d4b7;+ }++ * {+ box-sizing: border-box;+ }++ body {+ margin: 0;+ min-height: 100vh;+ display: grid;+ place-items: center;+ padding: 24px;+ background: radial-gradient(circle at top, #3a3d52 0%, var(--bg) 55%);+ color: var(--text);+ font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;+ }++ main {+ max-width: 720px;+ padding: 32px;+ border-radius: 18px;+ background: rgba(57, 59, 77, 0.92);+ box-shadow: 0 24px 80px rgba(0, 0, 0, 0.35);+ }++ h1 {+ margin: 0 0 12px;+ font-size: clamp(2rem, 4vw, 2.8rem);+ line-height: 1.1;+ }++ p {+ margin: 0 0 12px;+ color: var(--muted);+ line-height: 1.6;+ }++ a {+ color: var(--accent);+ text-decoration: none;+ }++ a:hover {+ color: var(--accent-hover);+ }++ .actions {+ margin-top: 20px;+ }++ .button {+ display: inline-block;+ padding: 12px 18px;+ border-radius: 999px;+ background: var(--accent);+ color: #102019;+ font-weight: 600;+ }++ .button:hover {+ color: #102019;+ background: var(--accent-hover);+ }+ </style><script>const path = window.location.pathname;// Get path segments (e.g., "/latest/foo/bar" → ["latest", "foo", "bar"])@@ -15,28 +91,57 @@// Check if we're on a version's root 404 page (exactly /{version}/404.html)const isVersionRoot404 = segments.length === 2 && segments[1] === '404.html';+ // Rewrite old URL prefixes to new clean paths+ const pathRewrites = {+ 'home/1-features/': 'features/',+ 'home/2-get-started/': 'get-started/',+ 'home/3-understand-pipelex/': 'viewpoint/',+ 'home/4-cookbook-examples/': 'cookbook/',+ 'home/5-setup/': 'setup/',+ 'home/6-build-reliable-ai-workflows/': 'building-methods/',+ 'home/7-configuration/': 'configuration/',+ 'home/8-analytics/': 'analytics/',+ 'home/9-tools/': 'tools/',+ 'home/10-advanced-customizations/': 'advanced/',+ };++ function rewritePath(p) {+ for (const [oldPrefix, newPrefix] of Object.entries(pathRewrites)) {+ if (p.includes(oldPrefix)) {+ return p.replace(oldPrefix, newPrefix);+ }+ }+ return p;+ }+if (!hasVersion) {- // No version in URL, redirect to /latest/...- const newUrl = '/latest' + path + window.location.search + window.location.hash;+ // No version in URL, rewrite old paths then redirect to /latest/...+ const rewritten = rewritePath(path);+ const newUrl = '/latest' + rewritten + window.location.search + window.location.hash;window.location.replace(newUrl);} else if (isVersionRoot404 && firstSegment !== 'latest') {// We tried a version's 404.html but it doesn't exist (invalid version)// Fall back to /latest/404.htmlwindow.location.replace('/latest/404.html');} else if (!isVersionRoot404) {- // Has version but not on 404 page, redirect to that version's styled 404 page- const version404Url = '/' + firstSegment + '/404.html';+ // Has version but not on 404 page, rewrite old paths then redirect to that version's styled 404 page+ const remainingPath = '/' + segments.slice(1).join('/');+ const rewrittenPath = rewritePath(remainingPath);+ const version404Url = rewrittenPath !== remainingPath+ ? '/' + firstSegment + rewrittenPath + window.location.search + window.location.hash+ : '/' + firstSegment + '/404.html';window.location.replace(version404Url);- } else {- // We're on /latest/404.html and it still 404'd - show basic error- document.write('<h1>Page not found</h1><p>The page you requested does not exist. <a href="/latest/">Go to documentation</a>.</p>');}</script></head><body>- <noscript>+ <main><h1>Page not found</h1>- <p>Enable JavaScript for automatic redirects, or go to <a href="/latest/">the documentation</a>.</p>- </noscript>+ <p>The page you requested does not exist in this documentation version.</p>+ <p>If you followed an old link, the redirect rules may already have sent you to the closest matching page under <code>/latest/</code>.</p>+ <div class="actions">+ <a class="button" href="/latest/">Go to the latest docs</a>+ </div>+ </main></body></html>diff --git a/docs/404.md b/docs/404.mddeleted file mode 100644index 3e244a7f9..000000000--- a/docs/404.md+++ /dev/null@@ -1,10 +0,0 @@-----template: main.html-title: Page not found------# Page not found--The page you requested does not exist.--[Return to the documentation homepage](index.md){ .md-button .md-button--primary }diff --git a/docs/CLAUDE.md b/docs/CLAUDE.mdnew file mode 100644index 000000000..b23ce0e8f--- /dev/null+++ b/docs/CLAUDE.md@@ -0,0 +1,64 @@+# Documentation Site Architecture++This file documents non-obvious architectural decisions for the docs site (`docs.pipelex.com`). Read this before modifying anything under `docs/`.++## Site Architecture Overview++- MkDocs Material with `mike` versioning, published at `docs.pipelex.com`+- `site_url` is `https://docs.pipelex.com/latest/` — all canonical URLs include `/latest/`+- Custom domain via `docs/CNAME` (value: `docs.pipelex.com`)+- Theme overrides live in `docs/overrides/`++## URL Structure & Redirects++Legacy URL paths (e.g. `home/1-features/`) are redirected to current clean paths (e.g. `features/`) via two mechanisms:++- The `mkdocs-redirects` plugin maps old→new paths (see `redirect_maps` in `mkdocs.yml`)+- `docs/404.html` contains client-side JS rewrite rules for the same prefixes, covering URLs that bypass MkDocs routing++Both must stay in sync. `mkdocs-redirects` must be installed in CI (`doc-check.yml`).++## The Two 404 Pages (critical — do not conflate)++There are two distinct 404 pages serving different purposes:++1. **`docs/404.html`** — Standalone root-level fallback for GitHub Pages. Copied to `/404.html` on `gh-pages` by `docs-deploy-root`. Contains JS redirect logic for legacy URLs. **NOT** part of the MkDocs build.++2. **`docs/overrides/404.html`** — MkDocs Material template override. Controls the versioned `site/404.html` rendered by MkDocs. Extends `main.html`. Must include both SEO tags (`noindex`, canonical) AND visible user-facing content (heading + link back to `/latest/`).++There must be **NO** `docs/404.md` — a Markdown 404 would be treated as content, appear in the sitemap, and create an indexable `/latest/404/` URL.++## SEO Architecture++- **`docs/overrides/main.html`** — Owns OG tags, Twitter cards, JSON-LD for all pages. Uses null-safe `page.meta` access (`page.meta and page.meta.description`). Does NOT special-case 404 behavior.+- **`docs/overrides/404.html`** — Extends `main.html`, adds `noindex/nofollow` + canonical back to `/latest/`. Must also render visible content.+- **`docs/.meta.yml`** — Default frontmatter for all pages via `meta-manager` plugin (image, description, keywords).+- Per-page `description` frontmatter in individual `.md` files overrides the default.++## robots.txt: Two Files, Different Purposes++- **`docs/robots.txt`** — Lands at `/latest/robots.txt` inside the versioned site. Crawlers ignore it (RFC 9309: only domain-root robots.txt is authoritative). Exists as a courtesy/fallback.+- **`Makefile` `ROOT_ROBOTS_TXT`** — The authoritative robots.txt deployed to domain root by `docs-deploy-root`. Allows only `/latest/`, disallows everything else, points sitemap to `/latest/sitemap.xml`.++## Deployment (`docs-deploy-root`)++The `docs-deploy-root` Makefile target deploys root assets (`404.html`, `robots.txt`, `index.html`) directly to the `gh-pages` branch via a temporary git worktree.++- Called automatically after `docs-deploy-stable` and `docs-deploy-specific-version-pre-release`+- The root `index.html` is a meta-refresh redirect to `/latest/`++## MkDocs Plugins++- `search` — site search with custom separator+- `redirects` — legacy→current URL path mapping+- `meta-manager` — applies `docs/.meta.yml` defaults to all pages+- `glightbox` — image lightbox++## Common Mistakes to Avoid++- Do NOT create `docs/404.md` — it poisons the sitemap with an indexable `/latest/404/` URL+- Do NOT delete `docs/overrides/404.html` — it controls the versioned 404 page+- Do NOT put 404-specific SEO tags in `main.html` — that's `overrides/404.html`'s job+- Do NOT treat `docs/robots.txt` as the production robots policy — the authoritative one is `ROOT_ROBOTS_TXT` in the Makefile+- When changing URL paths, update BOTH `mkdocs.yml` `redirect_maps` AND `docs/404.html` JS rewrite rules+- Always add `mkdocs-redirects` to CI pip install when `redirect_maps` existdiff --git a/docs/CODE_OF_CONDUCT.md b/docs/CODE_OF_CONDUCT.mdindex 7e3ea63d8..c23868222 100644--- a/docs/CODE_OF_CONDUCT.md+++ b/docs/CODE_OF_CONDUCT.md@@ -1,5 +1,6 @@---title: Code of Conduct+description: "Code of conduct for the Pipelex open-source community — guidelines for respectful collaboration and contribution."-----8<-- "CODE_OF_CONDUCT.md"\ No newline at end of filediff --git a/docs/advanced/content-generator-injection.md b/docs/advanced/content-generator-injection.mdnew file mode 100644index 000000000..e0c412047--- /dev/null+++ b/docs/advanced/content-generator-injection.md@@ -0,0 +1,8 @@+---+description: "Replace the default content generator to control how Pipelex produces artefacts from pipe outputs — plug in your own logic without touching core code."+---++# Content Generator Injection++!!! warning "Under Construction"+ This section is currently under development.diff --git a/docs/home/10-advanced-customizations/index.md b/docs/advanced/index.mdsimilarity index 93%rename from docs/home/10-advanced-customizations/index.mdrename to docs/advanced/index.mdindex d7124d99e..56e33ecaf 100644--- a/docs/home/10-advanced-customizations/index.md+++ b/docs/advanced/index.md@@ -1,3 +1,7 @@+---+description: "Extend Pipelex through dependency injection — swap in custom secrets providers, storage backends, observers, and reporting delegates."+---+# Dependency Injection## Overviewdiff --git a/docs/home/10-advanced-customizations/observer-provider-injection.md b/docs/advanced/observer-provider-injection.mdsimilarity index 97%rename from docs/home/10-advanced-customizations/observer-provider-injection.mdrename to docs/advanced/observer-provider-injection.mdindex eaeb4b21b..f0b8c8597 100644--- a/docs/home/10-advanced-customizations/observer-provider-injection.md+++ b/docs/advanced/observer-provider-injection.md@@ -1,3 +1,7 @@+---+description: "Build a custom observer to monitor pipe executions — collect inputs, outputs, errors, and performance metrics at every stage."+---+# Observer Provider InjectionThe Observer system in Pipelex allows you to monitor and collect data about pipe executions. This guide explains how to implement your own observer by following the dependency injection pattern and the ObserverProtocol.diff --git a/docs/advanced/pipe-router-injection.md b/docs/advanced/pipe-router-injection.mdnew file mode 100644index 000000000..6e1b719ec--- /dev/null+++ b/docs/advanced/pipe-router-injection.md@@ -0,0 +1,8 @@+---+description: "Override pipe routing to control how Pipelex resolves and dispatches pipe codes to their concrete implementations at runtime."+---++# Pipe Router Injection++!!! warning "Under Construction"+ This section is currently under development.diff --git a/docs/advanced/reporting-delegate-injection.md b/docs/advanced/reporting-delegate-injection.mdnew file mode 100644index 000000000..15d83190d--- /dev/null+++ b/docs/advanced/reporting-delegate-injection.md@@ -0,0 +1,8 @@+---+description: "Customize cost reporting by swapping in your own reporting delegate — control how Pipelex generates and routes reports for LLM and OCR operations."+---++# Reporting Delegate Injection++!!! warning "Under Construction"+ This section is currently under development.diff --git a/docs/advanced/secrets-provider-injection.md b/docs/advanced/secrets-provider-injection.mdnew file mode 100644index 000000000..f2eb992e2--- /dev/null+++ b/docs/advanced/secrets-provider-injection.md@@ -0,0 +1,8 @@+---+description: "Supply API keys and credentials from your preferred vault or secrets manager by plugging a custom secrets provider into Pipelex."+---++# Secrets Provider Injection++!!! warning "Under Construction"+ This section is currently under development.diff --git a/docs/advanced/storage-provider-injection.md b/docs/advanced/storage-provider-injection.mdnew file mode 100644index 000000000..26e812d27--- /dev/null+++ b/docs/advanced/storage-provider-injection.md@@ -0,0 +1,8 @@+---+description: "Route artefact reads and writes to S3, GCS, or your own backend by plugging a custom storage provider into the Pipelex runtime."+---++# Storage Provider Injection++!!! warning "Under Construction"+ This section is currently under development.diff --git a/docs/home/8-analytics/data-extraction.md b/docs/analytics/data-extraction.mdsimilarity index 88%rename from docs/home/8-analytics/data-extraction.mdrename to docs/analytics/data-extraction.mdindex 8d65a9187..6ce6fae5c 100644--- a/docs/home/8-analytics/data-extraction.md+++ b/docs/analytics/data-extraction.md@@ -1,3 +1,7 @@+---+description: "Extract execution data from Pipelex pipes — collect performance metrics, usage patterns, and debugging information automatically."+---+# Observer Data ExtractionThe Observer system in Pipelex automatically collects execution data from your pipes for later analysis. This data extraction feature is currently a work in progress but provides valuable insights into pipeline performance, usage patterns, and debugging information.@@ -45,4 +49,4 @@ You can implement custom data extraction to:## Current Status: Work in Progress-See [Observer Provider Injection](../../home/10-advanced-customizations/observer-provider-injection.md) for implementation details.\ No newline at end of file+See [Observer Provider Injection](../advanced/observer-provider-injection.md) for implementation details.\ No newline at end of filediff --git a/docs/home/6-build-reliable-ai-workflows/adapt-to-llm-prompting-style-openai-anthropic-mistral.md b/docs/building-methods/adapt-to-llm-prompting-style-openai-anthropic-mistral.mdsimilarity index 74%rename from docs/home/6-build-reliable-ai-workflows/adapt-to-llm-prompting-style-openai-anthropic-mistral.mdrename to docs/building-methods/adapt-to-llm-prompting-style-openai-anthropic-mistral.mdindex 2d17890c5..3d9da6310 100644--- a/docs/home/6-build-reliable-ai-workflows/adapt-to-llm-prompting-style-openai-anthropic-mistral.md+++ b/docs/building-methods/adapt-to-llm-prompting-style-openai-anthropic-mistral.md@@ -1,4 +1,9 @@-# Prompting Configuration+---+title: "LLM Prompting Style Configuration"+description: "Adapt prompting styles for OpenAI, Anthropic, Mistral, and other LLM providers to get the best results from your Pipelex methods."+---++# LLM Prompting Style ConfigurationThe `PromptingConfig` class controls how Pipelex handles prompting styles for different LLM targets.@@ -55,3 +60,9 @@ This allows for:- Configure specific styles for LLMs with unique requirements- Test prompting styles with each LLM target- Document any special formatting requirements++## Related Documentation++- [LLM Structured Generation Configuration](./llm-structured-generation-config.md) - Control text-then-structure behavior+- [PipeLLM](./pipes/pipe-operators/PipeLLM.md) - Pipe-level prompting and output controls+- [LLM Integration](../features/llm-integration.md) - High-level LLM capability overviewdiff --git a/docs/home/6-build-reliable-ai-workflows/concepts/define_your_concepts.md b/docs/building-methods/concepts/define_your_concepts.mdsimilarity index 89%rename from docs/home/6-build-reliable-ai-workflows/concepts/define_your_concepts.mdrename to docs/building-methods/concepts/define_your_concepts.mdindex c1fc9447f..821c6b09f 100644--- a/docs/home/6-build-reliable-ai-workflows/concepts/define_your_concepts.md+++ b/docs/building-methods/concepts/define_your_concepts.md@@ -1,5 +1,12 @@+---+description: "Define typed concepts in .mthds files to give your AI methods clear data boundaries, validation rules, and structured outputs."+---+# Defining Your Concepts+!!! tip "MTHDS Standard Reference"+ Concepts are part of the MTHDS open standard. For the authoritative language specification, see [Concepts](https://mthds.ai/latest/language/concepts/) on mthds.ai. This page documents Pipelex-specific behavior and usage.+Concepts are the foundation of reliable AI methods. They define what flows through your pipes—not just as data types, but as meaningful pieces of knowledge with clear boundaries and validation rules.## Writing Concept Definitions@@ -126,12 +133,12 @@ For advanced features like custom validation, computed properties, or reusable b## Refining Concepts-You can create more specific versions of existing concepts through refinement. For example, an `Invoice` is a specific kind of `PDF`:+You can create more specific versions of existing concepts through refinement. For example, an `Invoice` is a specific kind of `Document`:```toml[concept.Invoice]description = "A commercial document issued by a seller to a buyer"-refines = "PDF"+refines = "Document"```The refined concept inherits the structure of the base concept while adding semantic specificity.@@ -140,7 +147,7 @@ The refined concept inherits the structure of the base concept while adding sema## Native Concepts-Pipelex includes several built-in native concepts that cover common data types: `Text`, `Image`, `PDF`, `TextAndImages`, `Number`, `Page`, `Dynamic`, and `Anything`.+Pipelex includes 12 built-in native concepts: `Text`, `Image`, `Document`, `Html`, `TextAndImages`, `Number`, `ImgGenPrompt`, `Page`, `Dynamic`, `JSON`, `SearchResult`, and `Anything`.These concepts are automatically available in all pipelines—no setup required. You can use them directly in your pipes or refine them to create more specific concepts.diff --git a/docs/home/6-build-reliable-ai-workflows/concepts/inline-structures.md b/docs/building-methods/concepts/inline-structures.mdsimilarity index 97%rename from docs/home/6-build-reliable-ai-workflows/concepts/inline-structures.mdrename to docs/building-methods/concepts/inline-structures.mdindex 160ceb8a7..0b3337a3f 100644--- a/docs/home/6-build-reliable-ai-workflows/concepts/inline-structures.md+++ b/docs/building-methods/concepts/inline-structures.md@@ -1,3 +1,7 @@+---+description: "Declare typed schemas directly in .mthds files with inline structures. Build structured AI workflows without Python boilerplate."+---+# Inline Structure DefinitionDefine structured concepts directly in your `.mthds` files using pipelex syntax. This is the **recommended approach** for most use cases, offering rapid development without Python boilerplate.@@ -306,5 +310,5 @@ See [Python StructuredContent Classes](python-classes.md) for advanced features.- [Define Your Concepts](define_your_concepts.md) - Learn about concept semantics and naming- [Python StructuredContent Classes](python-classes.md) - Advanced features with Python-- [Writing Methods Tutorial](../../2-get-started/write-methods-manually.md) - Get started with structured outputs+- [Writing Methods Tutorial](../../get-started/write-methods-manually.md) - Get started with structured outputsdiff --git a/docs/home/6-build-reliable-ai-workflows/concepts/native-concepts.md b/docs/building-methods/concepts/native-concepts.mdsimilarity index 89%rename from docs/home/6-build-reliable-ai-workflows/concepts/native-concepts.mdrename to docs/building-methods/concepts/native-concepts.mdindex e591db861..e444b273f 100644--- a/docs/home/6-build-reliable-ai-workflows/concepts/native-concepts.md+++ b/docs/building-methods/concepts/native-concepts.md@@ -1,3 +1,7 @@+---+description: "Pipelex ships with built-in native concepts for text, images, documents, and numbers. Use them as ready-made building blocks in any pipeline."+---+# Native ConceptsPipelex includes several built-in native concepts that cover common data types in AI methods. These concepts come with predefined structures and are automatically available in all pipelines—no setup required.@@ -29,6 +33,8 @@ Here are all the native concepts you can use out of the box:| `Page` | A document page with text, images, and optional page view | `PageContent` || `Dynamic` | A dynamic concept that adapts to context | `DynamicContent` || `JSON` | A JSON object | `JSONContent` |+| `Html` | HTML content with inner HTML and CSS class | `HtmlContent` |+| `ImgGenPrompt` | A prompt for image generation | *No specific implementation* || `SearchResult` | A web search result with answer and sources | `SearchResultContent` || `Anything` | Any type of content | *No specific implementation* |@@ -152,6 +158,29 @@ class JSONContent(StuffContent):json_obj: dict[str, Any]```+### HtmlContent++Represents HTML content with styling:++```python+class HtmlContent(StuffContent):+ inner_html: str+ css_class: str+```++**Fields:**++- `inner_html`: The inner HTML of the content+- `css_class`: The CSS class applied to the wrapping element++**Use for:** Rendered HTML fragments, styled content blocks, HTML-based reports.++### ImgGenPrompt++A prompt for image generation. This concept is used as an intermediate representation in image generation pipelines (e.g., with `PipeImgGen`). It does not have a dedicated content class.++**Use for:** Storing and passing image generation prompts between pipes.+### SearchResultContentRepresents the result of a web search query. Produced by `PipeSearch`:@@ -326,5 +355,5 @@ prompt = "What is $topic?"- [Define Your Concepts](define_your_concepts.md) - Learn about concept semantics- [Inline Structures](inline-structures.md) - Add structure to refined concepts- [Python StructuredContent Classes](python-classes.md) - Advanced customization-- [Writing Methods Tutorial](../../2-get-started/write-methods-manually.md) - Use native concepts in pipelines+- [Writing Methods Tutorial](../../get-started/write-methods-manually.md) - Use native concepts in pipelinesdiff --git a/docs/home/6-build-reliable-ai-workflows/concepts/python-classes.md b/docs/building-methods/concepts/python-classes.mdsimilarity index 96%rename from docs/home/6-build-reliable-ai-workflows/concepts/python-classes.mdrename to docs/building-methods/concepts/python-classes.mdindex b8e3b9b77..e55843a21 100644--- a/docs/home/6-build-reliable-ai-workflows/concepts/python-classes.md+++ b/docs/building-methods/concepts/python-classes.md@@ -1,3 +1,7 @@+---+description: "Extend concepts with Python StructuredContent classes for custom validation, computed properties, and advanced business logic in Pipelex."+---+# Python StructuredContent ClassesFor advanced features beyond inline structures, create explicit Python classes that inherit from `StructuredContent`. This approach gives you full Pydantic power with custom validation, computed properties, and reusable business logic.@@ -255,6 +259,6 @@ Product = "A product in the catalog"- [Inline Structures](inline-structures.md) - Fast prototyping with TOML- [Define Your Concepts](define_your_concepts.md) - Learn about concept semantics and naming-<!-- path verified: resolves to docs/home/2-get-started/write-methods-manually.md -->-- [Writing Methods Tutorial](../../2-get-started/write-methods-manually.md) - Get started with structured outputs+<!-- path verified: resolves to docs/get-started/write-methods-manually.md -->+- [Writing Methods Tutorial](../../get-started/write-methods-manually.md) - Get started with structured outputsdiff --git a/docs/home/6-build-reliable-ai-workflows/concepts/refining-concepts.md b/docs/building-methods/concepts/refining-concepts.mdsimilarity index 98%rename from docs/home/6-build-reliable-ai-workflows/concepts/refining-concepts.mdrename to docs/building-methods/concepts/refining-concepts.mdindex 036b7ebfc..6f4224107 100644--- a/docs/home/6-build-reliable-ai-workflows/concepts/refining-concepts.md+++ b/docs/building-methods/concepts/refining-concepts.md@@ -1,3 +1,7 @@+---+description: "Refine concepts to create specialized subtypes that inherit structure while adding semantic specificity to your declarative AI workflows."+---+# Refining ConceptsConcept refinement allows you to create more specific versions of existing concepts while inheriting their structure. This provides semantic clarity and type safety for domain-specific methods.@@ -20,7 +24,7 @@ Refined concepts make your pipeline's intent explicit:```toml# ❌ Less clear[pipe.process_invoice]-inputs = { invoice = "PDF" }+inputs = { invoice = "Document" }# ✅ More clear[pipe.process_invoice]diff --git a/docs/home/6-build-reliable-ai-workflows/configure-ai-llm-to-optimize-methods.md b/docs/building-methods/configure-ai-llm-to-optimize-methods.mdsimilarity index 92%rename from docs/home/6-build-reliable-ai-workflows/configure-ai-llm-to-optimize-methods.mdrename to docs/building-methods/configure-ai-llm-to-optimize-methods.mdindex eab1ad60b..719a9936d 100644--- a/docs/home/6-build-reliable-ai-workflows/configure-ai-llm-to-optimize-methods.md+++ b/docs/building-methods/configure-ai-llm-to-optimize-methods.md@@ -1,3 +1,7 @@+---+description: "Configure LLM handles, presets, and model decks in Pipelex to optimize cost, latency, and quality across your executable AI methods."+---+# LLM Settings Guide## Overview@@ -10,7 +14,7 @@ The system provides three main concepts for LLM configuration:- LLM Presets- Model Deck-For complete details about the inference backend configuration system, see the [Inference Backend Configuration](../../home/7-configuration/config-technical/inference-backend-config.md) documentation.+For complete details about the inference backend configuration system, see the [Inference Backend Configuration](../configuration/config-technical/inference-backend-config.md) documentation.## LLM Handles (Aliases)@@ -66,7 +70,7 @@ deep-analysis = { model = "@default-premium", temperature = 0.1, reasoning_efforquick-reasoning = { model = "@default-premium", temperature = 0.3, reasoning_effort = "low", description = "Quick reasoning for simple tasks" }```-`reasoning_effort` accepts values from `"none"` to `"max"`. For an explicit token budget, use `reasoning_budget` instead (mutually exclusive with `reasoning_effort`). For provider-specific behavior and model examples, see [Reasoning Controls](../../under-the-hood/reasoning-controls.md).+`reasoning_effort` accepts values from `"none"` to `"max"`. For an explicit token budget, use `reasoning_budget` instead (mutually exclusive with `reasoning_effort`). For provider-specific behavior and model examples, see [Reasoning Controls](../under-the-hood/reasoning-controls.md).### Using LLM Settings in Pipelinesdiff --git a/docs/home/6-build-reliable-ai-workflows/domain.md b/docs/building-methods/domain.mdsimilarity index 93%rename from docs/home/6-build-reliable-ai-workflows/domain.mdrename to docs/building-methods/domain.mdindex 8482bd477..3d587b4bd 100644--- a/docs/home/6-build-reliable-ai-workflows/domain.md+++ b/docs/building-methods/domain.md@@ -1,5 +1,12 @@+---+description: "Domains organize concepts and pipes into semantic namespaces within .mthds files. Learn how to structure declarative AI workflows in Pipelex."+---+# Understanding Domains+!!! tip "MTHDS Standard Reference"+ Domains are part of the MTHDS open standard. For the authoritative language specification, see [Domains](https://mthds.ai/latest/language/domains/) on mthds.ai. This page documents Pipelex-specific behavior and usage.+A domain in Pipelex is a **semantic namespace** that organizes related concepts and pipes. It's declared at the top of every `.mthds` file and serves as an identifier for grouping related functionality.## What is a Domain?diff --git a/docs/home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md b/docs/building-methods/kick-off-a-methods-project.mdsimilarity index 96%rename from docs/home/6-build-reliable-ai-workflows/kick-off-a-methods-project.mdrename to docs/building-methods/kick-off-a-methods-project.mdindex 2c0e8c32a..c3203804c 100644--- a/docs/home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md+++ b/docs/building-methods/kick-off-a-methods-project.md@@ -1,3 +1,7 @@+---+description: "Set up your first Pipelex project with .mthds files, define concepts and pipes, and build executable AI methods from scratch."+---+# Kicking off a Pipelex Method Project## Creating Your First Pipelinediff --git a/docs/home/6-build-reliable-ai-workflows/libraries.md b/docs/building-methods/libraries.mdsimilarity index 97%rename from docs/home/6-build-reliable-ai-workflows/libraries.mdrename to docs/building-methods/libraries.mdindex 794d30d26..62d3348a3 100644--- a/docs/home/6-build-reliable-ai-workflows/libraries.md+++ b/docs/building-methods/libraries.md@@ -1,3 +1,7 @@+---+description: "Libraries collect domains, concepts, and pipes into a unified runtime context. Understand how Pipelex loads and resolves your Methods."+---+# LibrariesA **Library** in Pipelex is a complete collection of domains, concepts, and pipes that can be loaded and used together. It represents the full set of Pipelex definitions available for execution within a specific context, typically for a single pipeline run.diff --git a/docs/home/6-build-reliable-ai-workflows/llm-structured-generation-config.md b/docs/building-methods/llm-structured-generation-config.mdsimilarity index 78%rename from docs/home/6-build-reliable-ai-workflows/llm-structured-generation-config.mdrename to docs/building-methods/llm-structured-generation-config.mdindex feaabbaaa..1d59ba42c 100644--- a/docs/home/6-build-reliable-ai-workflows/llm-structured-generation-config.md+++ b/docs/building-methods/llm-structured-generation-config.md@@ -1,4 +1,9 @@-# Structure Configuration+---+title: "LLM Structured Generation Configuration"+description: "Control how Pipelex generates structured outputs from LLMs, including the two-step text-then-structure approach for typed JSON schemas."+---++# LLM Structured Generation ConfigurationThe `StructureConfig` class controls how Pipelex handles structural processing of content, particularly in LLM-based pipes.@@ -73,9 +78,8 @@ The two-step process uses:1. The pipe's configured prompts for initial text generation2. A specialized structure extraction prompt that can be customized in the `pipelex.toml` config in the `[cogt.llm_config.generic_templates]` section:-- - `structure_from_preliminary_text_system`: The system prompt for the second LLM call- - `structure_from_preliminary_text_user`: The user prompt for the second LLM call+ - `structure_from_preliminary_text_system`: The system prompt for the second LLM call+ - `structure_from_preliminary_text_user`: The user prompt for the second LLM call## Example Flow@@ -91,3 +95,9 @@ graph TDB -->|false| G[Direct Structure Generation]G --> H```++## Related Documentation++- [PipeLLM](./pipes/pipe-operators/PipeLLM.md) - Structured output behavior at the pipe level+- [LLM Prompting Style Configuration](./adapt-to-llm-prompting-style-openai-anthropic-mistral.md) - Prompt formatting by target model+- [LLM Integration](../features/llm-integration.md) - High-level LLM capability overviewdiff --git a/docs/building-methods/packages.md b/docs/building-methods/packages.mdnew file mode 100644index 000000000..6b3030e73--- /dev/null+++ b/docs/building-methods/packages.md@@ -0,0 +1,172 @@+---+title: "Packages"+description: "Use `METHODS.toml` to give a method package an identity and define which pipes it exports. Learn the current public `mthds package` workflow."+---++# Packages++A **package** is a collection of `.mthds` bundles with a `METHODS.toml` manifest at the project root. The manifest gives the package an identity and defines which pipes are exported to the outside world.++!!! info "Opt-in packaging"+ If your project has no `METHODS.toml`, Pipelex still loads your local bundles. Packaging is optional.++## What the Manifest Does++`METHODS.toml` currently serves two main purposes:++- **Identity**: give the package an address, version, and description+- **Visibility**: declare which pipes are exported through `[exports]`++## The Package Manifest: `METHODS.toml`++Here is a representative manifest:++```toml+[package]+address = "github.com/acme/legal-tools"+version = "1.0.0"+description = "Legal document analysis and contract review methods."+authors = ["Acme Corp"]+license = "MIT"+mthds_version = ">=0.8.0"++[exports.legal.contracts]+pipes = ["extract_clause", "analyze_contract"]++[exports.scoring]+pipes = ["compute_weighted_score"]+```++### Field Reference++| Field | Required | Description |+|-------|----------|-------------|+| `address` | Yes | Package address following a hostname/path pattern such as `github.com/org/repo` |+| `version` | Yes | Semantic version such as `1.0.0` or `2.1.3-beta.1` |+| `description` | Yes | Human-readable package description |+| `name` | No | Optional short method name |+| `display_name` | No | Optional display label |+| `authors` | No | List of author names |+| `license` | No | License string such as `MIT` |+| `main_pipe` | No | Optional main pipe code |+| `mthds_version` | No | Required MTHDS version constraint |++## Exports and Visibility++The `[exports]` section controls which pipes are visible outside the package.++### Default Behavior++- **Without `METHODS.toml`**: local bundles are still available to your project+- **With `METHODS.toml`**: pipes are private by default — only pipes listed in `[exports]` (and each bundle's `main_pipe`) are visible from outside++### Declaring Exports++Exports are grouped by domain path:++```toml+[exports.legal.contracts]+pipes = ["extract_clause", "analyze_contract"]++[exports.scoring]+pipes = ["compute_weighted_score"]+```++This manifest exports two pipes from `legal.contracts` and one pipe from `scoring`.++## Cross-Package References++Pipelex can resolve cross-package references when the required packages are available to the runtime. The reference form is:++```text+alias->domain.code+```++Example:++```toml+[pipe.analyze_item]+type = "PipeSequence"+description = "Analyze an item using another package"+steps = [+ { pipe = "scoring_lib->scoring.compute_weighted_score" },+]+```++This runtime-level capability exists separately from the current public `mthds package` CLI workflow documented on this page. If you rely on cross-package references, validate them against the specific runtime setup you are using.++### Example Layout++```text+your-project/+├── METHODS.toml+├── my_project/+│ ├── finance/+│ │ ├── invoices.mthds+│ │ └── invoices_struct.py+│ └── legal/+│ ├── contracts.mthds+│ └── contracts_struct.py+├── .pipelex/+│ └── pipelex.toml+└── requirements.txt+```++The `METHODS.toml` file sits at the project root. Pipelex discovers it by walking up from bundle locations until it finds the manifest.++## Current Public CLI Workflow++The public package-management commands documented in this repo are provided by the lowercase `mthds` CLI:++```bash+mthds package init+mthds package list+mthds package validate+```++### Initialize a Manifest++```bash+mthds package init+```++This command creates `METHODS.toml` interactively. It asks for package metadata and writes a manifest with an empty `[exports]` section.++### Inspect a Manifest++```bash+mthds package list+```++This command reads the manifest from the target package directory and prints the parsed package metadata and exports.++### Validate a Manifest++```bash+mthds package validate+```++This command validates the manifest syntax and package fields.++### Target a Different Directory++All three commands accept `-C, --package-dir <path>`:++```bash+mthds package init -C ./my-package+mthds package list -C ./my-package+mthds package validate -C ./my-package+```++## Important Compatibility Note++The current public `mthds package validate` command focuses on package identity and exports. It does **not** document a public dependency-management workflow here, and it rejects a `[dependencies]` section in the current JS CLI validation path.++For this reason, this documentation only describes the stable public package-manifest workflow exposed by the current `mthds` CLI.++## Related Documentation++- [Domain](./domain.md) — How domains organize concepts and pipes+- [Libraries](./libraries.md) — How libraries load and validate bundles+- [Pipelex Bundle Specification](./pipelex-bundle-specification.md) — The `.mthds` file format+- [Package Commands](../tools/cli/pkg.md) — `mthds package` command referencediff --git a/docs/home/6-build-reliable-ai-workflows/pipelex-bundle-specification.md b/docs/building-methods/pipelex-bundle-specification.mdsimilarity index 94%rename from docs/home/6-build-reliable-ai-workflows/pipelex-bundle-specification.mdrename to docs/building-methods/pipelex-bundle-specification.mdindex f36b33d15..5ef020fec 100644--- a/docs/home/6-build-reliable-ai-workflows/pipelex-bundle-specification.md+++ b/docs/building-methods/pipelex-bundle-specification.md@@ -1,5 +1,12 @@+---+description: "The .mthds bundle is the fundamental unit of Pipelex. Learn the TOML-based format for declaring concepts, pipes, and domain metadata."+---+# Pipelex Bundle Specification+!!! tip "MTHDS Standard Reference"+ The `.mthds` bundle format is defined by the MTHDS open standard. For the authoritative language specification, see [Bundles](https://mthds.ai/latest/language/bundles/) on mthds.ai. This page documents Pipelex-specific behavior and usage.+A **Pipelex bundle** is the fundamental unit of organization in Pipelex. It's a single `.mthds` file that defines a cohesive set of concepts and pipes for a specific domain of work.## What is a Pipelex Bundle?@@ -50,7 +57,6 @@ Every bundle **must** declare a domain. Only the `domain` field is mandatory; al```tomldomain = "invoice_processing"description = "Tools for extracting and validating invoice data"-source = "path/to/invoice_processing.mthds"system_prompt = "You are an expert in financial document processing."main_pipe = "extract_and_validate_invoice"```@@ -59,7 +65,6 @@ main_pipe = "extract_and_validate_invoice"- **`domain`** (required) - The unique identifier for this bundle's namespace- **`description`** (Optional) - A human-readable description of what this bundle does-- **`source`** (Optional) - The file path of the bundle (usually set automatically)- **`system_prompt`** (Optional) - A system prompt that applies to all `PipeLLM` operators in this bundle- **`main_pipe`** (Optional) - The default pipe to execute when no specific pipe is requested when running the bundle (covered in section 2)@@ -141,7 +146,7 @@ Pipes are the processing units that transform data. Like concepts, they're optio[pipe.extract_invoice]type = "PipeExtract"description = "Extract text and images from an invoice PDF"-inputs = { document = "PDF" }+inputs = { document = "Document" }output = "Page"```See more about designing pipes in [Designing Pipelines](./pipes/index.md).@@ -213,7 +218,7 @@ domain = "accounts_payable"[pipe.process_vendor_invoice]type = "PipeSequence"description = "Process a vendor invoice end-to-end"-inputs = { pdf_document = "PDF" }+inputs = { pdf_document = "Document" }output = "PaymentSchedule"steps = [# Call pipe from invoice_processing domaindiff --git a/docs/home/6-build-reliable-ai-workflows/pipes/executing-pipelines.md b/docs/building-methods/pipes/executing-pipelines.mdsimilarity index 88%rename from docs/home/6-build-reliable-ai-workflows/pipes/executing-pipelines.mdrename to docs/building-methods/pipes/executing-pipelines.mdindex faf8005ef..5e2b1c23d 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/executing-pipelines.md+++ b/docs/building-methods/pipes/executing-pipelines.md@@ -1,3 +1,7 @@+---+description: "Run Pipelex pipelines from the CLI, Python API, or Pipelex Client. Execute .mthds bundles and retrieve structured outputs programmatically."+---+# Executing PipelinesOnce your pipes are defined in `.mthds` files, you can execute them in multiple ways.@@ -93,7 +97,7 @@ When using `PipelexRunner`, you can control library behavior with these parameteFor a comprehensive understanding of libraries, including their structure, uniqueness rules, lifecycle, and best practices, see [Libraries](../libraries.md).!!! tip "Library Directory Configuration"- For complete configuration options including the `PIPELEXPATH` environment variable, CLI options, and priority resolution, see [Configuring Library Directories](../../7-configuration/config-technical/library-config.md#configuring-library-directories).+ For complete configuration options including the `PIPELEXPATH` environment variable, CLI options, and priority resolution, see [Configuring Library Directories](../../configuration/config-technical/library-config.md#configuring-library-directories).### Running Pipes by Code@@ -162,7 +166,7 @@ pipe_output = response.pipe_output```!!! tip "Listing available pipes"- Use the `pipelex show pipes` command to list all the pipes available in your project.+ Use `pipelex show pipe --all` to list the pipes available in your project.### Using MTHDS Content Directly@@ -223,31 +227,8 @@ Pipelex has a REST API for executing pipelines. See more about it [here](https:/----## Background Execution with `start_pipeline`+## Background Execution-For more complex scenarios where you need asynchronous control, use `start_pipeline`. This function immediately returns a `pipeline_run_id` and an `asyncio.Task`, allowing you to run pipelines in the background.--```python-from pipelex.pipelex import Pipelex-from pipelex.pipeline.start import start_pipeline--Pipelex.make()--# Start the pipeline without waiting-pipeline_run_id, task = await start_pipeline(- bundle_uri="path/to/my_bundle.mthds",- inputs={- "description": {- "concept": "ProductDescription",- "content": "...",- },- },-)--print(f"Pipeline started with ID: {pipeline_run_id}")--# Do other work while the pipeline runs...--# Wait for completion when ready-pipe_output = await task-```+<!-- start_pipeline exists on PipelexRunner as a protocol stub (raises NotImplementedError).+ The public entry point is execute_pipeline(). Keep this note so reviewers don't flag the stub as contradictory. -->+The public Python entry point is `PipelexRunner.execute_pipeline()`. The older standalone `start_pipeline` function is no longer a documented entry point.diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/index.md b/docs/building-methods/pipes/index.mdsimilarity index 97%rename from docs/home/6-build-reliable-ai-workflows/pipes/index.mdrename to docs/building-methods/pipes/index.mdindex 7e3ad761d..1a3e781bb 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/index.md+++ b/docs/building-methods/pipes/index.md@@ -1,3 +1,7 @@+---+description: "Design composable pipelines by combining pipe operators and controllers. Break complex AI tasks into testable, deterministic units."+---+# Designing PipelinesIn Pipelex, a pipeline is not just a rigid sequence of steps; it's a dynamic and intelligent method built by composing individual, reusable components called **pipes**. This approach allows you to break down complex AI tasks into manageable, testable, and reliable units.diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeBatch.md b/docs/building-methods/pipes/pipe-controllers/PipeBatch.mdsimilarity index 93%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeBatch.mdrename to docs/building-methods/pipes/pipe-controllers/PipeBatch.mdindex 05c979cf9..ca8d284ff 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeBatch.md+++ b/docs/building-methods/pipes/pipe-controllers/PipeBatch.md@@ -1,3 +1,7 @@+---+description: "PipeBatch maps a single pipe over a list of items in parallel. Process collections of documents or records efficiently in Pipelex pipelines."+---+# PipeBatchThe `PipeBatch` controller provides a powerful "map" operation for your pipelines. It takes a list of items as input and runs the same pipe on each item in the list, executing them all in parallel for maximum efficiency.@@ -66,4 +70,8 @@ How this works:3. In branch #1, it takes the first article from `ArticleList`, puts it into the branch's isolated working memory, and gives it the name `ArticleText` (as specified by `input_item_name`).4. The `summarize_one_article` pipe is then executed in branch #1. It looks for an input named `ArticleText`, finds the injected article, and produces a summary.5. Steps 3 and 4 happen simultaneously for all 10 articles in their respective branches.-6. Once all `summarize_one_article` pipes are done, `PipeBatch` collects the 10 `ArticleSummary` outputs and bundles them into a single `SummaryList`. This list is the final result.\ No newline at end of file+6. Once all `summarize_one_article` pipes are done, `PipeBatch` collects the 10 `ArticleSummary` outputs and bundles them into a single `SummaryList`. This list is the final result.++## Related Documentation++- [Understanding Multiplicity](../understanding-multiplicity.md) - How Pipelex handles lists and batch processing\ No newline at end of filediff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeCondition.md b/docs/building-methods/pipes/pipe-controllers/PipeCondition.mdsimilarity index 94%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeCondition.mdrename to docs/building-methods/pipes/pipe-controllers/PipeCondition.mdindex d459e9827..78d2232b6 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeCondition.md+++ b/docs/building-methods/pipes/pipe-controllers/PipeCondition.md@@ -1,3 +1,7 @@+---+description: "Add if/else branching logic to your pipelines with PipeCondition. Route execution dynamically based on Jinja2 expressions and pipe maps."+---+# PipeConditionThe `PipeCondition` controller adds branching logic to your pipelines. It evaluates an expression and, based on the string result, chooses which subsequent pipe to execute from a map of possibilities.@@ -171,3 +175,8 @@ add_alias_from_expression_to = "category_type"- Creates an alias from the expression result- Makes the result available in working memory- Requires the target to exist in working memory beforehand++## Related Documentation++- [Pipeline Orchestration](../../../features/pipeline-orchestration.md) - Overview of pipeline orchestration capabilities+- [Provide Inputs](../provide-inputs.md) - Passing inputs to pipes and pipelinesdiff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeParallel.md b/docs/building-methods/pipes/pipe-controllers/PipeParallel.mdsimilarity index 94%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeParallel.mdrename to docs/building-methods/pipes/pipe-controllers/PipeParallel.mdindex 9c58bd5b3..9bd2a7dc6 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeParallel.md+++ b/docs/building-methods/pipes/pipe-controllers/PipeParallel.md@@ -1,3 +1,7 @@+---+description: "Execute multiple pipes concurrently with PipeParallel. Speed up independent tasks while keeping each branch isolated in its own memory."+---+# PipeParallelThe `PipeParallel` controller executes multiple pipes simultaneously. This is highly effective for running pipes concurrently in isolated branches.@@ -79,4 +83,8 @@ How this works:3. The `extract_features` pipe runs in one branch, and the `analyze_sentiment` pipe runs in the other, simultaneously.4. After both complete, `PipeParallel` collects the results. The output from `extract_features` is named `features`, and the output from `analyze_sentiment` is named `sentiment`.5. Because `combined_output` is set to `ProductAnalysis`, a new structured object of type `ProductAnalysis` is created. This object is populated with the results, like `{"features": ..., "sentiment": ...}`.-6. This single `ProductAnalysis` object becomes the final output of the `analyze_product_in_parallel` pipe.\ No newline at end of file+6. This single `ProductAnalysis` object becomes the final output of the `analyze_product_in_parallel` pipe.++## Related Documentation++- [Pipeline Orchestration](../../../features/pipeline-orchestration.md) - Overview of pipeline orchestration capabilities\ No newline at end of filediff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeSequence.md b/docs/building-methods/pipes/pipe-controllers/PipeSequence.mdsimilarity index 85%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeSequence.mdrename to docs/building-methods/pipes/pipe-controllers/PipeSequence.mdindex 8249dd9d8..664063fed 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeSequence.md+++ b/docs/building-methods/pipes/pipe-controllers/PipeSequence.md@@ -1,3 +1,7 @@+---+description: "PipeSequence runs pipes one after another, passing outputs forward through working memory. The core building block for linear AI methods."+---+# PipeSequenceThe `PipeSequence` controller is used to execute a series of pipes one after another. It is the fundamental building block for creating linear methods where the output of one step becomes the input for the next.@@ -70,4 +74,11 @@ steps = [{ pipe = "summarize_text", result = "english_summary" },{ pipe = "translate_to_french", result = "french_summary" },]-```\ No newline at end of file+```++## Related Documentation++- [Invoice Extractor Example](../../../cookbook/invoice-extractor.md) - Complete invoice processing pipeline using PipeSequence+- [Write Tweet Example](../../../cookbook/write-tweet.md) - Multi-step tweet generation workflow+- [Table Extraction Example](../../../cookbook/extract-table.md) - Extract and correct tables from images+- [Gantt Extraction Example](../../../cookbook/extract-gantt.md) - Extract Gantt chart data from documents\ No newline at end of filediff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/index.md b/docs/building-methods/pipes/pipe-controllers/index.mdsimilarity index 79%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/index.mdrename to docs/building-methods/pipes/pipe-controllers/index.mdindex 0cb7e229a..da5d3663d 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-controllers/index.md+++ b/docs/building-methods/pipes/pipe-controllers/index.md@@ -1,5 +1,12 @@+---+description: "Pipe controllers orchestrate execution flow in Pipelex. Sequence, parallelize, batch, or branch your pipes for structured AI workflows."+---+# Pipe Controllers+!!! tip "MTHDS Standard Reference"+ Pipe controllers are part of the MTHDS open standard. For the authoritative language specification, see [Pipes & Controllers](https://mthds.ai/latest/language/pipes-controllers/) on mthds.ai. This page documents Pipelex-specific behavior and usage.+Pipe controllers are the orchestrators of a Pipelex pipeline. While [Pipe Operators](../pipe-operators/index.md) perform the work, pipe controllers define the method and manage the execution logic. They allow you to run other pipes in sequence, in parallel, or conditionally.## Core Controllersdiff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeCompose.md b/docs/building-methods/pipes/pipe-operators/PipeCompose.mdsimilarity index 82%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeCompose.mdrename to docs/building-methods/pipes/pipe-operators/PipeCompose.mdindex 2f9085841..65b84de83 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeCompose.md+++ b/docs/building-methods/pipes/pipe-operators/PipeCompose.md@@ -1,8 +1,12 @@+---+description: "PipeCompose renders Jinja2 templates or constructs structured objects from working memory. Combine pipeline data into new outputs deterministically."+---+# PipeComposeThe `PipeCompose` operator composes data from your pipeline's working memory into new outputs. It supports two modes:-1. **Template mode**: Render Jinja2 templates to produce `Text` or `Html` output+1. **Template mode**: Render templates to produce `Text`-like output2. **Construct mode**: Build structured objects by mapping fields from inputs## Template Mode@@ -13,10 +17,10 @@ Template mode uses [Jinja2 templates](https://jinja.palletsprojects.com/) to dyn`PipeCompose` takes all the data currently in the `WorkingMemory` and uses it as the context for rendering a Jinja2 template. The resulting text is then saved back to the working memory as a new `Text` or `Html` output.-The template can be provided as:--- **Inline string**: A template string directly in the pipe definition-- **Template section**: A `[pipe.name.template]` section with additional configuration+<!-- target_format is a pipelex convenience field (PipeComposeSpec in pipe_compose_spec.py),+ transformed to TemplateBlueprint at build time. The MTHDS standard uses category ++ templating_style.text_format, but pipelex exposes target_format as a simpler authoring form. -->+The public authoring form uses a top-level `template` field plus a required `target_format`.### Template Context@@ -29,10 +33,11 @@ The Jinja2 template has access to all the "stuffs" currently in the working memo| `type` | string | The type of the pipe: `PipeCompose` | Yes || `description` | string | A description of the operation | Yes || `inputs` | table | Input variables needed for the template | Yes |-| `output` | string | The concept for the output (typically `Text` or `Html`) | No |+| `output` | string | The concept for the output | No || `template` | string | An inline Jinja2 template string | Yes* |+| `target_format` | string | Output rendering target, such as `plain`, `markdown`, `html`, `json`, or `mermaid` | Yes* |-*Either `template` (inline) or a `[pipe.name.template]` section must be provided.+*Template mode requires both `template` and `target_format`.### Template Mode Examples@@ -44,10 +49,11 @@ type = "PipeCompose"description = "Compose a greeting message"inputs = { user = "User" }output = "Text"+target_format = "plain"template = "Hello $user.name, welcome to our platform!"```-**HTML template with section:**+**HTML template:**```toml[pipe.format_html_report]@@ -55,9 +61,7 @@ type = "PipeCompose"description = "Format data as HTML"inputs = { summary = "Text", items = "Item[]" }output = "Html"--[pipe.format_html_report.template]-category = "html"+target_format = "html"template = """<h1>Report</h1><p>{{ summary }}</p>@@ -137,3 +141,8 @@ In this example:| Assemble structured data from multiple sources | Construct || Combine fields from different inputs into one object | Construct || Need to map/rename fields | Construct |++## Related Documentation++- [Working Memory](../working-memory.md) - How pipes access and share data+- [Provide Inputs](../provide-inputs.md) - Passing inputs to pipes and pipelinesdiff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md b/docs/building-methods/pipes/pipe-operators/PipeExtract.mdsimilarity index 71%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.mdrename to docs/building-methods/pipes/pipe-operators/PipeExtract.mdindex 77e9cd8f2..c62ae6142 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md+++ b/docs/building-methods/pipes/pipe-operators/PipeExtract.md@@ -1,12 +1,16 @@+---+description: "PipeExtract performs OCR on images and PDFs to extract text and embedded visuals. Turn documents into structured data for your AI methods."+---+# PipeExtractThe `PipeExtract` operator performs Optical Character Recognition (OCR) on images and PDF documents. It extracts text, embedded images, and provides full-page renderings.## How it works-`PipeExtract` takes a single input, which must be either an `Image` or a `Pdf`. It processes the document page by page and produces a list of `PageContent` objects. Each `PageContent` object encapsulates all the information extracted from a single page.+`PipeExtract` takes a single input, which must be a `Document` or an `Image` (or a concept that refines one of them). It processes the input and produces a list of `PageContent` objects. Each `PageContent` object encapsulates all the information extracted from one page.-The output is always a list, even if the input is a single image (in which case the list will contain just one item).+The output is always a list. If the input is a single image, the output still contains one `Page` item.### The `PageContent` Structure@@ -43,8 +47,8 @@ OCR presets are defined in your model deck configuration and can include paramet| --------------------------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------- | -------- || `type` | string | The type of the pipe: `PipeExtract` | Yes || `description` | string | A description of the OCR operation. | Yes |-| `inputs` | Fixed | The value is either of concept `Image` or `Pdf`. | Yes |-| `output` | string | The output concept produced by the OCR operation. | Yes |+| `inputs` | Fixed | The value must be of concept `Document` or `Image` (or a concept that refines one of them). | Yes |+| `output` | string | The output concept produced by the OCR operation. Use `Page[]`. | Yes || `max_page_images` | integer or null | Maximum number of images to extract from pages: `null` (or omit) for unlimited, `0` for no images, or a positive integer to limit. Defaults to the value in your Extract model preset. | No || `page_views` | boolean | If `true`, a high-fidelity image of each page will be included in the `page_view` field. Defaults to `false`. | No || `page_views_dpi` | integer | The resolution (in Dots Per Inch) for the generated page views when processing a PDF. Defaults to `150`. | No |@@ -67,11 +71,18 @@ refines = "Page"type = "PipeExtract"description = "Extract text from a scanned document"inputs = { document = "ScannedDocument" }-output = "Page"+output = "Page[]"page_views = truepage_views_dpi = 200```-The output of the PipeExtract must be exactly the native `Page` concept.+The output of `PipeExtract` must be `Page[]`.++To use this pipe, first load a PDF into the `ScannedDocument` concept. After the pipe runs, the output contains a list of `PageContent` objects, where each object has the extracted text and a 200 DPI image of the corresponding page.++## Related Documentation-To use this pipe, you would first need to load a PDF into the `ScannedDocument` concept. After the pipe runs, the `ExtractedPages` concept will contain a list of `PageContent` objects, where each object has the extracted text and a 200 DPI image of the corresponding page.+- [Simple OCR Example](../../../cookbook/simple-ocr.md) - Basic OCR pipeline using PipeExtract+- [Generic Extraction Example](../../../cookbook/extract-generic.md) - Multi-modal document extraction+- [Invoice Extractor Example](../../../cookbook/invoice-extractor.md) - Complete invoice processing pipeline+- [Document Extraction Feature](../../../features/document-extraction.md) - Overview of document extraction capabilitiesdiff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeFunc.md b/docs/building-methods/pipes/pipe-operators/PipeFunc.mdsimilarity index 93%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeFunc.mdrename to docs/building-methods/pipes/pipe-operators/PipeFunc.mdindex 2d72f6d74..8b27e99cb 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeFunc.md+++ b/docs/building-methods/pipes/pipe-operators/PipeFunc.md@@ -1,3 +1,7 @@+---+description: "Run custom Python functions inside Pipelex pipelines with PipeFunc. Integrate business logic, external APIs, and data transformations."+---+# PipeFuncThe `PipeFunc` operator provides an essential escape hatch, allowing you to execute arbitrary Python code from within a pipeline. This is useful for custom data manipulation, complex logic, or integrating with external services not supported by other operators.@@ -107,3 +111,8 @@ description = "Combine two text inputs using a custom Python function"function_name = "concatenate_texts"output = "ConcatenatedText"```++## Related Documentation++- [Advanced Customizations](../../../advanced/index.md) - Extend Pipelex with custom logic+- [Working Memory](../working-memory.md) - How pipes access and share datadiff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeImgGen.md b/docs/building-methods/pipes/pipe-operators/PipeImgGen.mdsimilarity index 80%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeImgGen.mdrename to docs/building-methods/pipes/pipe-operators/PipeImgGen.mdindex 8c1e54b92..99b19a387 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeImgGen.md+++ b/docs/building-methods/pipes/pipe-operators/PipeImgGen.md@@ -1,3 +1,7 @@+---+description: "Generate images from text prompts within your Pipelex pipelines using PipeImgGen. Configure models, sizes, and output formats declaratively."+---+# PipeImgGenThe `PipeImgGen` operator is used to generate images from a text prompt using a specified image generation model.@@ -65,8 +69,12 @@ Image generation presets are defined in your model deck configuration and can in| `output` | string | The output concept produced by the image generation operation. Use bracket notation for multiple images: `"Image[3]"` generates exactly 3 images. | Yes || `model` | string | The choice of image generation model name, setting, or preset to use (e.g., `"gpt-image-1"`). Defaults to the model specified in the global config. | No || `prompt` | string | The image generation prompt. Can be a static string or reference input variables using `$` prefix (e.g., `"$description"` or `"A sketch of: $subject"`). | Yes |-| `aspect_ratio` | string | The desired aspect ratio of the image (e.g., `"16:9"`, `"1:1"`). | No |+| `negative_prompt` | string | Optional negative prompt when supported by the selected model or provider. | No |+| `aspect_ratio` | string | The desired aspect ratio of the image. Valid values: `"square"`, `"landscape_4_3"`, `"landscape_3_2"`, `"landscape_16_9"`, `"landscape_21_9"`, `"portrait_3_4"`, `"portrait_2_3"`, `"portrait_9_16"`, `"portrait_9_21"`. | No || `seed` | integer or "auto" | A seed for the random number generator to ensure reproducibility. `"auto"` uses a random seed. | No |+| `background` | string | Optional background setting when supported by the selected provider. | No |+| `output_format` | string | Optional output image format when supported by the selected provider. | No |+| `is_raw` | boolean | Request a raw generation mode when supported by the selected provider. | No |### Example: Generating a single image from a static prompt@@ -79,8 +87,7 @@ description = "Generate a futuristic car image"output = "Image"prompt = "A sleek, futuristic sports car driving on a neon-lit highway at night."model = "$gen-image"-aspect_ratio = "16:9"-quality = "hd"+aspect_ratio = "landscape_16_9"```### Example: Generating an image from a dynamic prompt@@ -123,10 +130,15 @@ inputs = { img_prompt = "ImgGenPrompt" }output = "Image[3]"prompt = "$img_prompt"model = "$gen-image"-aspect_ratio = "1:1"+aspect_ratio = "square"```The output of the PipeImgGen has to be a concept compatible with the native `Image` concept. A concept is compatible with the `Image` concept if it refines the `Image` concept.To use this pipe, you would first load a text prompt (e.g., "A minimalist logo for a coffee shop, featuring a stylized mountain and a coffee bean") into the input stuff (`ImgGenPrompt` concept). After running, the output will be a list containing three generated `ImageContent` objects.+## Related Documentation++- [Image Generation Feature](../../../features/image-generation.md) - Overview of image generation capabilities+- [Cloud Storage](../../../features/cloud-storage.md) - Store generated images in cloud storage+diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md b/docs/building-methods/pipes/pipe-operators/PipeLLM.mdsimilarity index 93%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.mdrename to docs/building-methods/pipes/pipe-operators/PipeLLM.mdindex 987d083b6..0e423e4d9 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md+++ b/docs/building-methods/pipes/pipe-operators/PipeLLM.md@@ -1,3 +1,8 @@+---+title: "PipeLLM Operator"+description: "PipeLLM is Pipelex's core operator for calling LLMs — supports text generation, summarization, classification, structured outputs, vision models, and document processing."+---+# PipeLLM`PipeLLM` is the core operator in Pipelex for leveraging Large Language Models (LLMs). It can be used for a wide range of tasks, including text generation, summarization, classification, and structured data extraction.@@ -234,7 +239,7 @@ When `model` is specified as a table (inline LLM setting), it accepts the follow| `description` | string | Human-readable description (for presets) |!!! tip "More on Reasoning"- For provider-specific behavior and model-specific examples, see [Reasoning Controls](../../../../under-the-hood/reasoning-controls.md).+ For provider-specific behavior and model-specific examples, see [Reasoning Controls](../../../under-the-hood/reasoning-controls.md).### Output Multiplicity@@ -370,4 +375,12 @@ Analyze the following topic in depth, considering multiple perspectives:@topic"""-```\ No newline at end of file+```++## Related Documentation++- [Hello World Example](../../../cookbook/hello-world.md) - Simple introductory example using PipeLLM+- [Invoice Extractor Example](../../../cookbook/invoice-extractor.md) - Complete invoice processing pipeline+- [Write Tweet Example](../../../cookbook/write-tweet.md) - Multi-step tweet generation workflow+- [Table Extraction Example](../../../cookbook/extract-table.md) - Extract and correct tables from images+- [Gantt Extraction Example](../../../cookbook/extract-gantt.md) - Extract Gantt chart data from documents\ No newline at end of filediff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md b/docs/building-methods/pipes/pipe-operators/PipeSearch.mdsimilarity index 88%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.mdrename to docs/building-methods/pipes/pipe-operators/PipeSearch.mdindex 97eeb6470..f0a85758a 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md+++ b/docs/building-methods/pipes/pipe-operators/PipeSearch.md@@ -1,3 +1,7 @@+---+description: "PipeSearch queries the web and returns structured results with citations. Add real-time knowledge retrieval to your executable AI methods."+---+# PipeSearchThe `PipeSearch` operator searches the web using a configurable search provider and returns structured results with an answer and source citations.@@ -35,7 +39,7 @@ Common search presets:| `type` | string | The type of the pipe: `PipeSearch` | Yes || `description` | string | A description of the search operation. | Yes || `inputs` | dictionary | The input concept(s) for the search query, as a dictionary mapping input names to concept codes. Required when the prompt references variables. | No |-| `output` | string | The output concept produced by the search. Must be `SearchResult` or a concept that refines `SearchResult`. | Yes |+| `output` | string | The output concept produced by the search. `SearchResult` is the default shape, but PipeSearch can also target a structured output concept. | Yes || `model` | string | The search model preset to use (e.g., `"$standard"`, `"$deep"`). Defaults to the model specified in the global config. | No || `prompt` | string | The search query. Can be a static string or reference input variables using `$` prefix (e.g., `"What is $topic?"`). | Yes || `include_images` | boolean | Whether to include images in search results. Overrides the preset setting. | No |@@ -102,4 +106,8 @@ from_date = "2026-01-01"include_domains = ["reuters.com", "apnews.com", "bbc.com"]```-The output of PipeSearch must be `SearchResult` or a concept that refines `SearchResult`. After execution, the output contains the synthesized `answer` and a list of `sources` with their names, URLs, and snippets.+When the output concept is compatible with `SearchResult`, the output contains the synthesized `answer` and a list of `sources` with their names, URLs, and snippets. PipeSearch can also feed a structured output concept when your method needs a more specialized downstream shape.++## Related Documentation++- [Web Search Feature](../../../features/web-search.md) - Overview of web search capabilitiesdiff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/index.md b/docs/building-methods/pipes/pipe-operators/index.mdsimilarity index 87%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/index.mdrename to docs/building-methods/pipes/pipe-operators/index.mdindex 28c17c495..0934598a6 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/index.md+++ b/docs/building-methods/pipes/pipe-operators/index.md@@ -1,5 +1,12 @@+---+description: "Pipe operators are the action units of Pipelex pipelines. Explore operators for LLM integration, document extraction, search, and more."+---+# Pipe Operators+!!! tip "MTHDS Standard Reference"+ Pipe operators are part of the MTHDS open standard. For the authoritative language specification, see [Pipes & Operators](https://mthds.ai/latest/language/pipes-operators/) on mthds.ai. This page documents Pipelex-specific behavior and usage.+Pipe operators are the fundamental building blocks in Pipelex, representing a single, focused task. They are the "verbs" of your pipeline that perform the actual work.Each operator specializes in a specific kind of action, from interacting with Large Language Models to executing custom Python code. You combine these operators using [Pipe Controllers](../pipe-controllers/index.md) to create complex methods.diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-output.md b/docs/building-methods/pipes/pipe-output.mdsimilarity index 97%rename from docs/home/6-build-reliable-ai-workflows/pipes/pipe-output.mdrename to docs/building-methods/pipes/pipe-output.mdindex a8857dde9..84e08b930 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-output.md+++ b/docs/building-methods/pipes/pipe-output.md@@ -1,3 +1,7 @@+---+description: "Every pipe produces a Stuff object stored in working memory. Learn how to access, inspect, and use pipeline outputs in Pipelex."+---+# Pipe OutputWhen you execute a pipeline, each pipe produces a `Stuff` that is automatically stored in the [Working Memory](working-memory.md). The final output of the pipeline execution is accessible through a `PipeOutput` object.diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/provide-inputs.md b/docs/building-methods/pipes/provide-inputs.mdsimilarity index 98%rename from docs/home/6-build-reliable-ai-workflows/pipes/provide-inputs.mdrename to docs/building-methods/pipes/provide-inputs.mdindex 773349184..6b6f554d8 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/provide-inputs.md+++ b/docs/building-methods/pipes/provide-inputs.md@@ -1,3 +1,7 @@+---+description: "Prepare and format pipeline inputs for Pipelex using the CLI, Python API, or Client. Generate input templates and pass data to your methods."+---+# Providing Inputs to PipelinesWhen running Pipelex pipelines, you need to provide input data that matches what your pipeline expects. This guide explains how to prepare and format inputs, whether you're using the CLI, Python API, or Pipelex Client.@@ -16,7 +20,7 @@ This creates a `results/inputs.json` file with the structure needed for your pippipelex run bundle path/to/my_pipe.mthds --inputs results/inputs.json```-See more about the options of the CLI [here](../../9-tools/cli/index.md).+See more about the options of the CLI [here](../../tools/cli/index.md).!!! tip "Starting Point for Input Structure"Use `pipelex build inputs` to quickly understand what inputs your pipeline expects and generate a template to fill in.diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/understanding-multiplicity.md b/docs/building-methods/pipes/understanding-multiplicity.mdsimilarity index 96%rename from docs/home/6-build-reliable-ai-workflows/pipes/understanding-multiplicity.mdrename to docs/building-methods/pipes/understanding-multiplicity.mdindex 6e92581fd..aea679112 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/understanding-multiplicity.md+++ b/docs/building-methods/pipes/understanding-multiplicity.md@@ -1,5 +1,12 @@+---+description: "Multiplicity defines whether a pipe handles single items or collections. Build flexible Methods that scale from one document to thousands."+---+# Understanding Multiplicity+!!! tip "MTHDS Standard Reference"+ Multiplicity is part of the MTHDS open standard. For the authoritative language specification, see [Multiplicity](https://mthds.ai/latest/language/multiplicity/) on mthds.ai. This page documents Pipelex-specific behavior and usage.+Multiplicity in Pipelex defines how many items a particular stuff can comprise in a particular context. This applies to any of the pipe input variables and also to the output of the pipe. This idea is fundamental to building flexible AI methods that can handle both single items and collections.This guide explains the philosophy behind multiplicity in Pipelex and how to use it effectively in your pipelines.diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/working-memory.md b/docs/building-methods/pipes/working-memory.mdsimilarity index 84%rename from docs/home/6-build-reliable-ai-workflows/pipes/working-memory.mdrename to docs/building-methods/pipes/working-memory.mdindex 334deab9d..7353eecc6 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/working-memory.md+++ b/docs/building-methods/pipes/working-memory.md@@ -1,5 +1,12 @@+---+description: "Working memory enables data flow between pipes during pipeline execution. Learn how Pipelex stores and passes typed data across steps."+---+# Working Memory+!!! tip "MTHDS Standard Reference"+ Working memory is part of the MTHDS open standard. For the authoritative language specification, see [Working Memory](https://mthds.ai/latest/language/working-memory/) on mthds.ai. This page documents Pipelex-specific behavior and usage.+The **Working Memory** is the mechanism that enables data flow between pipes in your pipeline. It acts as a **temporary** storage space that exists for the duration of a single pipeline run.## How Data Flows Between Pipesdiff --git a/docs/changelog.md b/docs/changelog.mdindex ece2e41b0..7c76563f0 100644--- a/docs/changelog.md+++ b/docs/changelog.md@@ -1,5 +1,6 @@---title: Changelog+description: "Pipelex changelog — release history, new features, bug fixes, and breaking changes for the Pipelex runtime and CLI."-----8<-- "CHANGELOG.md"\ No newline at end of filediff --git a/docs/home/7-configuration/config-advanced/feature-config.md b/docs/configuration/config-advanced/feature-config.mdsimilarity index 71%rename from docs/home/7-configuration/config-advanced/feature-config.mdrename to docs/configuration/config-advanced/feature-config.mdindex d36f27045..5f790cce7 100644--- a/docs/home/7-configuration/config-advanced/feature-config.md+++ b/docs/configuration/config-advanced/feature-config.md@@ -1,3 +1,7 @@+---+description: "Toggle Pipelex feature flags — enable or disable the reporting system and other optional capabilities through TOML configuration."+---+# Feature ConfigurationThe `FeatureConfig` class controls which features are enabled in Pipelex.@@ -40,3 +44,8 @@ is_reporting_enabled = true# Enable reporting for cost monitoringis_reporting_enabled = true```++## Related Documentation++- [Cost Tracking](../../features/cost-tracking.md) - Track and monitor AI usage costs+- [Reporting Config](../config-practical/reporting-config.md) - Detailed reporting configuration optionsdiff --git a/docs/home/7-configuration/config-pipeline-validation/dry-run-config.md b/docs/configuration/config-pipeline-validation/dry-run-config.mdsimilarity index 85%rename from docs/home/7-configuration/config-pipeline-validation/dry-run-config.mdrename to docs/configuration/config-pipeline-validation/dry-run-config.mdindex 4871f862f..8d4625263 100644--- a/docs/home/7-configuration/config-pipeline-validation/dry-run-config.md+++ b/docs/configuration/config-pipeline-validation/dry-run-config.md@@ -1,3 +1,7 @@+---+description: "Configure dry-run behavior in Pipelex — set mock generation rules, truncation limits, image URLs, and allowed-to-fail pipes via TOML."+---+# Dry Run ConfigurationThe `DryRunConfig` class controls how Pipelex behaves during dry runs.@@ -80,3 +84,8 @@ The `text_gen_truncate_length` controls:- Set appropriate truncation lengths- Enable template validation when testing templates- Review dry run logs for potential issues++## Related Documentation++- [Validation & Dry Run](../../features/validation-dry-run.md) - Overview of validation and dry run capabilities+- [CLI validate](../../tools/cli/validate.md) - Using the CLI to validate methodsdiff --git a/docs/home/7-configuration/config-practical/logging-config.md b/docs/configuration/config-practical/logging-config.mdsimilarity index 94%rename from docs/home/7-configuration/config-practical/logging-config.mdrename to docs/configuration/config-practical/logging-config.mdindex a7636fe5f..4fbce4db9 100644--- a/docs/home/7-configuration/config-practical/logging-config.md+++ b/docs/configuration/config-practical/logging-config.md@@ -1,3 +1,7 @@+---+description: "Fine-tune Pipelex logging levels, Rich console output, and message formatting through TOML configuration settings in pipelex.toml."+---+# Logging ConfigurationConfiguration section: `[pipelex.log_config]`@@ -191,3 +195,7 @@ keywords_to_hilight = ["error", "warning", "failed"]- Set noisy third-party packages to WARNING- Keep pipelex at INFO for important updates- Use VERBOSE only when debugging specific issues++## Related Documentation++- [Logging Tool](../../tools/logging.md) - Using Pipelex logging in your codediff --git a/docs/home/7-configuration/config-practical/pipe-run-config.md b/docs/configuration/config-practical/pipe-run-config.mdsimilarity index 64%rename from docs/home/7-configuration/config-practical/pipe-run-config.mdrename to docs/configuration/config-practical/pipe-run-config.mdindex 1cc9a7226..46f7fef01 100644--- a/docs/home/7-configuration/config-practical/pipe-run-config.md+++ b/docs/configuration/config-practical/pipe-run-config.md@@ -1,3 +1,7 @@+---+description: "Set execution parameters for pipes, including stack depth limits and runtime behavior for nested pipe calls in your Pipelex project."+---+# Pipe Run ConfigurationThe `PipeRunConfig` class controls execution parameters for pipes in Pipelex.@@ -32,3 +36,8 @@ The `pipe_stack_limit` prevents infinite recursion in pipe execution by:- Set a reasonable stack limit based on your pipeline complexity- Monitor stack usage in complex pipelines++## Related Documentation++- [Executing Pipelines](../../building-methods/pipes/executing-pipelines.md) - How to run pipes and pipelines+- [Pipeline Orchestration](../../features/pipeline-orchestration.md) - Orchestrating complex multi-step pipelinesdiff --git a/docs/home/7-configuration/config-practical/reporting-config.md b/docs/configuration/config-practical/reporting-config.mdsimilarity index 84%rename from docs/home/7-configuration/config-practical/reporting-config.mdrename to docs/configuration/config-practical/reporting-config.mdindex 544095a9b..df1b76372 100644--- a/docs/home/7-configuration/config-practical/reporting-config.md+++ b/docs/configuration/config-practical/reporting-config.md@@ -1,3 +1,7 @@+---+description: "Manage cost reporting for LLM usage, OCR processing, and other operations — configure console output and report file destinations."+---+# Reporting ConfigurationConfiguration section: `[pipelex.reporting_config]`@@ -88,3 +92,8 @@ cost_report_unit_scale = 1000.0!!! warning "Under Construction"This section is currently under development.++## Related Documentation++- [Cost Tracking](../../features/cost-tracking.md) - Track and monitor AI usage costs+- [Reporting Delegate Injection](../../advanced/reporting-delegate-injection.md) - Customize reporting behavior with dependency injectiondiff --git a/docs/home/7-configuration/config-practical/telemetry-config.md b/docs/configuration/config-practical/telemetry-config.mdsimilarity index 95%rename from docs/home/7-configuration/config-practical/telemetry-config.mdrename to docs/configuration/config-practical/telemetry-config.mdindex 5e59f83d5..b433c6ab1 100644--- a/docs/home/7-configuration/config-practical/telemetry-config.md+++ b/docs/configuration/config-practical/telemetry-config.md@@ -1,3 +1,7 @@+---+description: "Set up custom telemetry destinations for observability data — send execution metrics to your own analytics and monitoring backends."+---+# Telemetry Configuration## Overview@@ -10,7 +14,7 @@ Telemetry configuration is stored in `.pipelex/telemetry.toml`. This file contro1. **Gateway Telemetry** (Pipelex-controlled): Automatic when using Pipelex Gateway, tied to your API key2. **Custom Telemetry** (User-controlled): Configured in this file, sent to your own backends- For an overview, see [Telemetry Setup](../../5-setup/telemetry.md).+ For an overview, see [Telemetry Setup](../../setup/telemetry.md).## Configuration File Location@@ -249,3 +253,8 @@ pipelex init telemetry- The `DO_NOT_TRACK` environment variable provides a global kill switchFor more information about our data practices, see our [Privacy Policy](https://go.pipelex.com/privacy-policy).++## Related Documentation++- [Telemetry Feature](../../features/telemetry.md) - Overview of telemetry capabilities+- [Telemetry Setup](../../setup/telemetry.md) - Step-by-step telemetry configuration guidediff --git a/docs/home/7-configuration/config-technical/aws-config.md b/docs/configuration/config-technical/aws-config.mdsimilarity index 77%rename from docs/home/7-configuration/config-technical/aws-config.mdrename to docs/configuration/config-technical/aws-config.mdindex ce960ae16..294549380 100644--- a/docs/home/7-configuration/config-technical/aws-config.md+++ b/docs/configuration/config-technical/aws-config.md@@ -1,3 +1,7 @@+---+description: "Configure AWS authentication for Pipelex — choose between environment variables or a custom secret provider for AWS service access."+---+# AWS ConfigurationConfiguration section: `[pipelex.aws_config]`@@ -42,7 +46,7 @@ When using `api_key_method = "secret_provider"`, Pipelex will:!!! warning "Secret Provider Requirements"To use the secret provider method, you must:-1. Configure a secret provider in your project using the `SecretsProviderAbstract`: See more in the [Secrets](../../../home/10-advanced-customizations/secrets-provider-injection.md) documentation.+1. Configure a secret provider in your project using the `SecretsProviderAbstract`: See more in the [Secrets](../../advanced/secrets-provider-injection.md) documentation.2. Store your AWS credentials in your secret provider3. Ensure your secret provider is properly authenticated@@ -54,9 +58,14 @@ Pipelex uses dependency injection to manage AWS clients and credentials. You can- Override default credential providers- Mock AWS services for testing-For detailed information about dependency injection, including examples and best practices, see the [Dependency Injection](../../../home/10-advanced-customizations/index.md) documentation.+For detailed information about dependency injection, including examples and best practices, see the [Dependency Injection](../../advanced/index.md) documentation.## Best Practices!!! warning "Under Construction"This section is currently under development.++## Related Documentation++- [Cloud Storage](../../features/cloud-storage.md) - Using cloud storage with Pipelex+- [Storage Provider Injection](../../advanced/storage-provider-injection.md) - Customize storage providers with dependency injectiondiff --git a/docs/home/7-configuration/config-technical/cogt-config.md b/docs/configuration/config-technical/cogt-config.mdsimilarity index 89%rename from docs/home/7-configuration/config-technical/cogt-config.mdrename to docs/configuration/config-technical/cogt-config.mdindex 8b57566df..e3f345e01 100644--- a/docs/home/7-configuration/config-technical/cogt-config.md+++ b/docs/configuration/config-technical/cogt-config.md@@ -1,3 +1,7 @@+---+description: "Configure cognitive tools in Pipelex — LLM inference, image generation, and OCR extraction settings through TOML configuration."+---+# Cognitive Tools (Cogt) ConfigurationThe Cogt configuration manages all cognitive tools in Pipelex, including LLM (Language Models), Image Generation, and OCR (Optical Character Recognition) capabilities.@@ -190,3 +194,10 @@ seed = "auto"[cogt.extract_config]default_page_views_dpi = 72```++## Related Documentation++- [PipeExtract Operator](../../building-methods/pipes/pipe-operators/PipeExtract.md) - Extract text and images from documents+- [PipeImgGen Operator](../../building-methods/pipes/pipe-operators/PipeImgGen.md) - Generate images with AI models+- [Document Extraction](../../features/document-extraction.md) - Overview of document extraction capabilities+- [Image Generation](../../features/image-generation.md) - Overview of image generation capabilitiesdiff --git a/docs/home/7-configuration/config-technical/inference-backend-config.md b/docs/configuration/config-technical/inference-backend-config.mdsimilarity index 97%rename from docs/home/7-configuration/config-technical/inference-backend-config.mdrename to docs/configuration/config-technical/inference-backend-config.mdindex 36673771a..6c4882de8 100644--- a/docs/home/7-configuration/config-technical/inference-backend-config.md+++ b/docs/configuration/config-technical/inference-backend-config.md@@ -1,3 +1,7 @@+---+description: "Set up AI model providers, routing profiles, and inference backends — use Pipelex Gateway, direct API keys, or custom configurations."+---+# Inference Backend ConfigurationThe Inference Backend Configuration System manages how Pipelex handles AI model providers, model routing, and inference settings across LLMs, OCR, and image generation. This unified system provides a flexible and scalable way to configure multiple inference backends and route different types of AI models to the appropriate providers.@@ -649,3 +653,9 @@ Common error types:- Keep base configurations unchanged to make upgrades easier- Version control your custom configurations- Share routing profiles and presets across your team++## Related Documentation++- [LLM Integration](../../features/llm-integration.md) - Overview of LLM provider support and capabilities+- [PipeLLM Operator](../../building-methods/pipes/pipe-operators/PipeLLM.md) - The pipe operator that uses inference backends+- [Configure AI Providers](../../setup/configure-ai-providers.md) - Setup guide for connecting AI providersdiff --git a/docs/home/7-configuration/config-technical/library-config.md b/docs/configuration/config-technical/library-config.mdsimilarity index 96%rename from docs/home/7-configuration/config-technical/library-config.mdrename to docs/configuration/config-technical/library-config.mdindex 2fa996bac..9936a8fdd 100644--- a/docs/home/7-configuration/config-technical/library-config.md+++ b/docs/configuration/config-technical/library-config.md@@ -1,4 +1,9 @@-# Pipeline Discovery and Loading+---+title: "Library Directories and Bundle Loading"+description: "Tell Pipelex where to find your `.mthds` bundle files. Point to a bundle directly or configure library directories for automatic discovery."+---++# Library Directories and Bundle LoadingWhen running pipelines, Pipelex needs to find your `.mthds` bundle files. There are two approaches:@@ -131,7 +136,7 @@ pipelex run bundle my_bundle.mthds --inputs data.json -L /path/to/pipelines# Available on multiple commandspipelex validate --all -L /path/to/pipelines/dir-pipelex show pipes -L /path/to/pipelines/dir+pipelex show pipe --all -L /path/to/pipelines/dirpipelex which my_pipe -L /path/to/pipelines/dir```@@ -401,7 +406,7 @@ Pipelex loads your pipelines in a specific order to ensure dependencies are reso### 2. Concept Loading-- Loads native concepts (Text, Image, PDF, etc.)+- Loads native concepts (Text, Image, Document, etc.)- Loads custom concepts from `.mthds` files- Validates concept definitions and relationships- Links concepts to Python structure classes by name@@ -462,7 +467,7 @@ pipelex validate --allpipelex validate YOUR_PIPE_CODE# Show all available pipes-pipelex show pipes+pipelex show pipe --all# Show details of a specific pipepipelex show pipe YOUR_PIPE_CODE@@ -512,7 +517,7 @@ pipelex show pipe YOUR_PIPE_CODE1. Ensure files have the `.mthds` extension2. Check that files are not in excluded directories3. Verify file permissions allow reading-4. Run `pipelex show pipes` to see what was discovered+4. Run `pipelex show pipe --all` to see what was discovered### Structure Classes Not Registered@@ -546,3 +551,8 @@ pipelex show pipe YOUR_PIPE_CODE2. Check concept references are spelled correctly3. Verify pipe configurations match expected format4. Ensure all required fields are present++## Related Documentation++- [Libraries](../../building-methods/libraries.md) - Understanding method libraries+- [Packages](../../building-methods/packages.md) - Organizing methods into packagesdiff --git a/docs/home/7-configuration/index.md b/docs/configuration/index.mdsimilarity index 94%rename from docs/home/7-configuration/index.mdrename to docs/configuration/index.mdindex c33b9cad5..8ed133983 100644--- a/docs/home/7-configuration/index.md+++ b/docs/configuration/index.md@@ -1,3 +1,7 @@+---+description: "Configure Pipelex with its layered TOML configuration system — shipped defaults plus project-level overrides for executable AI methods."+---+# Configuration## Overview@@ -37,7 +41,7 @@ In addition to `.pipelex/pipelex.toml`, Pipelex can apply override files at the4. `pipelex_override.toml` (recommended to gitignore)!!! info "Contributor details"- For the full “where defaults live” and “how config is merged” explanation, see [Configuration Internals](../../contribute/configuration-defaults-and-overrides.md).+ For the full “where defaults live” and “how config is merged” explanation, see [Configuration Internals](../contribute/configuration-defaults-and-overrides.md).## Configuration Structurediff --git a/docs/contribute/configuration-defaults-and-overrides.md b/docs/contribute/configuration-defaults-and-overrides.mdindex 574831446..c7cade005 100644--- a/docs/contribute/configuration-defaults-and-overrides.md+++ b/docs/contribute/configuration-defaults-and-overrides.md@@ -1,8 +1,12 @@+---+description: "For contributors: how Pipelex merges configuration layers at runtime — shipped defaults, project overrides, and root override files."+---+# Configuration Internals (defaults and overrides)This page is for **contributors**: it explains where Pipelex defaults live, how configuration is merged at runtime, and where to change the behavior in code.-For the user-facing configuration guide, see [Configuration Overview](../home/7-configuration/index.md).+For the user-facing configuration guide, see [Configuration Overview](../configuration/index.md).## Mental model (for contributors)diff --git a/docs/contributing.md b/docs/contributing.mdindex ec207150d..f4d1e3437 100644--- a/docs/contributing.md+++ b/docs/contributing.md@@ -1,5 +1,6 @@---title: Contributing to Pipelex+description: "Contribute to Pipelex — guidelines for reporting issues, submitting pull requests, and developing the open-source AI methods runtime."-----8<-- "CONTRIBUTING.md"diff --git a/docs/home/4-cookbook-examples/extract-dpe.md b/docs/cookbook/extract-dpe.mdsimilarity index 89%rename from docs/home/4-cookbook-examples/extract-dpe.mdrename to docs/cookbook/extract-dpe.mdindex b7dd9feac..5f96ef099 100644--- a/docs/home/4-cookbook-examples/extract-dpe.md+++ b/docs/cookbook/extract-dpe.md@@ -1,3 +1,7 @@+---+description: "Extract structured data from French energy performance diagnostics (DPE) using Pipelex declarative AI workflows and typed schemas."+---+# Example: DPE ExtractionThis example demonstrates how to extract information from a French "Diagnostic de Performance Énergétique" (DPE) document. This is a specialized document, and the pipeline is tailored to its specific structure.@@ -81,4 +85,9 @@ To help you do so, you are given the text extracted from the page by an OCR mode- You can use tables if it is relevant."""```-This is a great example of how to create a highly specialized extraction pipeline by combining a custom data model with a detailed, guiding prompt.\ No newline at end of file+This is a great example of how to create a highly specialized extraction pipeline by combining a custom data model with a detailed, guiding prompt.++## Related Documentation++- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [Document Extraction](../features/document-extraction.md) - Overview of document extraction capabilities\ No newline at end of filediff --git a/docs/home/4-cookbook-examples/extract-gantt.md b/docs/cookbook/extract-gantt.mdsimilarity index 95%rename from docs/home/4-cookbook-examples/extract-gantt.mdrename to docs/cookbook/extract-gantt.mdindex 4edb63928..dccb5905f 100644--- a/docs/home/4-cookbook-examples/extract-gantt.md+++ b/docs/cookbook/extract-gantt.md@@ -1,3 +1,7 @@+---+description: "Extract tasks, dates, and dependencies from Gantt chart images using executable AI methods — a step-by-step Pipelex cookbook example."+---+# Example: Gantt Chart ExtractionThis example showcases the ability of Pipelex to extract structured information from images. In this case, it processes an image of a Gantt chart and extracts the tasks, dates, and dependencies.@@ -208,4 +212,9 @@ class extract_details_of_task sub_b;R2oLH-branch-11 -- "Extract details of task" ----> QFEdmVvYVHdL6DsCRtwqHq-branch-11QFEdmVvYVHdL6DsCRtwqHq-branch-11 -...- nCmpxnCmpx -- "Gather in a gantt chart" ----> NuMVc-```\ No newline at end of file+```++## Related Documentation++- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [PipeSequence Controller](../building-methods/pipes/pipe-controllers/PipeSequence.md) - Chain pipes into sequential workflows\ No newline at end of filediff --git a/docs/home/4-cookbook-examples/extract-generic.md b/docs/cookbook/extract-generic.mdsimilarity index 78%rename from docs/home/4-cookbook-examples/extract-generic.mdrename to docs/cookbook/extract-generic.mdindex 9a7a7f6a5..260e4de1d 100644--- a/docs/home/4-cookbook-examples/extract-generic.md+++ b/docs/cookbook/extract-generic.md@@ -1,3 +1,8 @@+---+title: "Generic Document Extraction Example"+description: "Extract content from complex PDF documents containing text and images. This Pipelex pipeline merges extracted content into a single coherent output."+---+# Example: Generic Document ExtractionThis example demonstrates a powerful and generic pipeline for extracting content from complex PDF documents. It can handle documents that contain both text and images, and it merges the extracted content into a single, coherent output.@@ -49,4 +54,10 @@ def merge_markdown_and_images(working_memory: WorkingMemory) -> TextAndImagesCon)```-This example shows the flexibility of Pipelex in handling complex, multi-modal documents and allowing for custom logic.\ No newline at end of file+This example shows the flexibility of Pipelex in handling complex, multi-modal documents and allowing for custom logic.++## Related Documentation++- [PipeExtract Operator](../building-methods/pipes/pipe-operators/PipeExtract.md) - Extract text and images from documents+- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [Document Extraction](../features/document-extraction.md) - Overview of document extraction capabilities\ No newline at end of filediff --git a/docs/home/4-cookbook-examples/extract-proof-of-purchase.md b/docs/cookbook/extract-proof-of-purchase.mdsimilarity index 88%rename from docs/home/4-cookbook-examples/extract-proof-of-purchase.mdrename to docs/cookbook/extract-proof-of-purchase.mdindex c857ce69b..b0690538f 100644--- a/docs/home/4-cookbook-examples/extract-proof-of-purchase.md+++ b/docs/cookbook/extract-proof-of-purchase.md@@ -1,3 +1,7 @@+---+description: "Build a pipeline that extracts structured data from receipts and invoices using declarative AI workflows and .mthds files."+---+# Example: Proof of Purchase ExtractionThis example demonstrates a pipeline designed to extract structured data from a proof of purchase, such as a receipt or an invoice.@@ -75,4 +79,9 @@ To help you do so, you are given the text extracted from the page by an OCR mode- You can use tables if it is relevant."""```-The combination of a detailed prompt, the OCR text, and the document image allows the LLM to accurately extract the required information and structure it as a `ProofOfPurchase` object.+The combination of a detailed prompt, the OCR text, and the document image allows the LLM to accurately extract the required information and structure it as a `ProofOfPurchase` object.++## Related Documentation++- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [Document Extraction](../features/document-extraction.md) - Overview of document extraction capabilitiesdiff --git a/docs/home/4-cookbook-examples/extract-table.md b/docs/cookbook/extract-table.mdsimilarity index 88%rename from docs/home/4-cookbook-examples/extract-table.mdrename to docs/cookbook/extract-table.mdindex a7c596846..7eb8a0ddc 100644--- a/docs/home/4-cookbook-examples/extract-table.md+++ b/docs/cookbook/extract-table.md@@ -1,3 +1,7 @@+---+description: "Turn table images into structured HTML with Pipelex executable AI methods — ideal for processing scanned documents and reports."+---+# Example: Table Extraction from ImageThis example shows how to extract a table from an image and convert it into a structured HTML format. This is a common requirement when dealing with scanned documents or reports where data is presented in tabular form.@@ -87,4 +91,9 @@ Rewrite the entire html table with your potential corrections.Make sure you do not forget any text."""```-This self-correction pattern is a key technique for building robust and reliable AI methods with Pipelex.\ No newline at end of file+This self-correction pattern is a key technique for building robust and reliable AI methods with Pipelex.++## Related Documentation++- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [PipeSequence Controller](../building-methods/pipes/pipe-controllers/PipeSequence.md) - Chain pipes into sequential workflows\ No newline at end of filediff --git a/docs/home/4-cookbook-examples/hello-world.md b/docs/cookbook/hello-world.mdsimilarity index 83%rename from docs/home/4-cookbook-examples/hello-world.mdrename to docs/cookbook/hello-world.mdindex 5e3abee1c..8f8d98eeb 100644--- a/docs/home/4-cookbook-examples/hello-world.md+++ b/docs/cookbook/hello-world.md@@ -1,3 +1,8 @@+---+title: "Hello World Example"+description: "The Hello World of Pipelex — a simple pipeline demonstrating basic concepts. Verify your installation and get a first taste of how Pipelex works."+---+# Example: Hello WorldThis is the "Hello World" of Pipelex, a simple pipeline that demonstrates the basic concepts of Pipelex.@@ -82,3 +87,8 @@ Write a haiku about Hello World.```Expected output: A haiku about "Hello World" displayed with pretty formatting.++## Related Documentation++- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [Define Your Concepts](../building-methods/concepts/define_your_concepts.md) - How to define custom data types for your methodsdiff --git a/docs/home/4-cookbook-examples/index.md b/docs/cookbook/index.mdsimilarity index 89%rename from docs/home/4-cookbook-examples/index.mdrename to docs/cookbook/index.mdindex 03b318879..6ba1b5f26 100644--- a/docs/home/4-cookbook-examples/index.md+++ b/docs/cookbook/index.md@@ -1,3 +1,8 @@+---+title: "Cookbook Examples"+description: "Practical Pipelex examples and ready-to-use recipes: Hello World, OCR, document extraction, invoice processing, image generation, and more."+---+# Pipelex Cookbook ExamplesWelcome to the Pipelex Cookbook!@@ -18,7 +23,7 @@ We strongly encourage you to clone our [Pipelex Cookbook repository](https://git## Contribute to the Community!-Have you built a cool pipeline with Pipelex? Share it with the community! We welcome contributions. Check out our [contribution guidelines](../../contributing.md) and help us grow this collection of examples.+Have you built a cool pipeline with Pipelex? Share it with the community! We welcome contributions. Check out our [contribution guidelines](../contributing.md) and help us grow this collection of examples.## Available Examplesdiff --git a/docs/home/4-cookbook-examples/invoice-extractor.md b/docs/cookbook/invoice-extractor.mdsimilarity index 85%rename from docs/home/4-cookbook-examples/invoice-extractor.mdrename to docs/cookbook/invoice-extractor.mdindex 56b44bded..104fe9380 100644--- a/docs/home/4-cookbook-examples/invoice-extractor.md+++ b/docs/cookbook/invoice-extractor.md@@ -1,3 +1,8 @@+---+title: "Invoice Extractor Example"+description: "Process PDF invoices with Pipelex: extract key information into structured Invoice objects, generate reports, and track pipeline execution."+---+# Example: Invoice ExtractorThis example provides a comprehensive pipeline for processing invoices. It takes a PDF invoice, extracts key information, and returns a structured `Invoice` object. It also demonstrates how to generate reports and track pipeline execution.@@ -58,7 +63,7 @@ The entire method is defined in a MTHDS file. This declarative approach makes th[pipe.process_invoice]type = "PipeSequence"description = "Process relevant information from an invoice"-inputs = { document = "PDF" }+inputs = { document = "Document" }output = "Invoice"steps = [{ pipe = "extract_text_from_image", result = "invoice_pages" },@@ -68,7 +73,7 @@ steps = [[pipe.extract_text_from_image]type = "PipeExtract"description = "Extract page contents from an image"-inputs = { document = "PDF" }+inputs = { document = "Document" }output = "Page"page_views = truemodel = "base_extract_mistral"@@ -119,4 +124,11 @@ class extract_invoice sub_a;RRYZF -- "Extract invoice data" ----> RzjEzwGpkk5dXnrK3HXQJx-branch-0RzjEzwGpkk5dXnrK3HXQJx-branch-0 -...- 5SXqJZynbH -...- ZynbH-branch-0-```\ No newline at end of file+```++## Related Documentation++- [PipeExtract Operator](../building-methods/pipes/pipe-operators/PipeExtract.md) - Extract text and images from documents+- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [PipeSequence Controller](../building-methods/pipes/pipe-controllers/PipeSequence.md) - Chain pipes into sequential workflows+- [Cost Tracking](../features/cost-tracking.md) - Track and monitor AI usage costs\ No newline at end of filediff --git a/docs/home/4-cookbook-examples/simple-ocr.md b/docs/cookbook/simple-ocr.mdsimilarity index 71%rename from docs/home/4-cookbook-examples/simple-ocr.mdrename to docs/cookbook/simple-ocr.mdindex 1ac2726df..c8d6c35dd 100644--- a/docs/home/4-cookbook-examples/simple-ocr.md+++ b/docs/cookbook/simple-ocr.md@@ -1,3 +1,8 @@+---+title: "Simple OCR Example"+description: "Build a basic OCR pipeline with Pipelex. Extract text from PDF pages and save the content — a fundamental building block for document processing methods."+---+# Example: Simple OCRThis example demonstrates a basic OCR (Optical Character Recognition) pipeline. It takes a PDF file as input, extracts the text from each page, and saves the content.@@ -24,4 +29,9 @@ async def simple_ocr(pdf_url: str) -> ListContent[PageContent]:return page_content_list```-This showcases how easy it is to kick off a complex process with just a few lines of code. The `inputs` dictionary simply maps the input name to the PDF content, and the pipeline handles the rest.\ No newline at end of file+This showcases how easy it is to kick off a complex process with just a few lines of code. The `inputs` dictionary simply maps the input name to the PDF content, and the pipeline handles the rest.++## Related Documentation++- [PipeExtract Operator](../building-methods/pipes/pipe-operators/PipeExtract.md) - Extract text and images from documents+- [Document Extraction](../features/document-extraction.md) - Overview of document extraction capabilities\ No newline at end of filediff --git a/docs/home/4-cookbook-examples/write-tweet.md b/docs/cookbook/write-tweet.mdsimilarity index 91%rename from docs/home/4-cookbook-examples/write-tweet.mdrename to docs/cookbook/write-tweet.mdindex 2e9a0b872..eb56ee71a 100644--- a/docs/home/4-cookbook-examples/write-tweet.md+++ b/docs/cookbook/write-tweet.md@@ -1,3 +1,7 @@+---+description: "Generate optimized tweets with style transfer using Pipelex — define your writing workflow once in .mthds files, then run it reliably."+---+# Example: Tweet OptimizerThis example demonstrates how to create a pipeline that takes a draft of a tweet and a desired writing style, and then generates an optimized tweet. This is a practical example of "style transfer" for text.@@ -111,3 +115,8 @@ class optimize_tweet_sequence sub_a;EWhtJ -- "Optimize tweet" ----> 65Eb2i34D5 -- "Optimize tweet" ----> 65Eb2```++## Related Documentation++- [PipeLLM Operator](../building-methods/pipes/pipe-operators/PipeLLM.md) - The core operator for LLM interactions+- [PipeSequence Controller](../building-methods/pipes/pipe-controllers/PipeSequence.md) - Chain pipes into sequential workflowsdiff --git a/docs/features/advanced-customizations.md b/docs/features/advanced-customizations.mdnew file mode 100644index 000000000..ffc0f4ca6--- /dev/null+++ b/docs/features/advanced-customizations.md@@ -0,0 +1,29 @@+---+title: Advanced Customizations+description: "Customize Pipelex with dependency injection — plug in your own secrets, storage, reporting, and content generation providers without modifying the framework."+---++# Advanced Customizations++A dependency injection framework for extending and customizing Pipelex behavior.++## Overview++Pipelex provides well-defined injection points that let you replace or extend core behaviors without modifying the framework itself. Each injection point follows a strict protocol contract, making implementations testable and swappable. Register custom providers at initialization time and the runtime uses them throughout execution.++## Injection Points++| Injection Point | Purpose |+|-----------------|---------|+| **[Secrets Provider](../advanced/secrets-provider-injection.md)** | Custom secret management (environment, vaults, etc.) |+| **[Storage Provider](../advanced/storage-provider-injection.md)** | Custom cloud storage backends |+| **[Observer](../advanced/observer-provider-injection.md)** | Custom execution data capture |+| **[Reporting Delegate](../advanced/reporting-delegate-injection.md)** | Custom cost reporting |+| **[Content Generator](../advanced/content-generator-injection.md)** | Override LLM output generation |+| **[Pipe Router](../advanced/pipe-router-injection.md)** | Dynamic routing of pipes to implementations |++## Built-in Defaults++Some injection points provide safe built-in defaults or no-op implementations, so you only need to implement the ones relevant to your use case.++For detailed documentation, see [Advanced Customizations](../advanced/index.md).diff --git a/docs/home/1-features/claude-code-skills-plugin.md b/docs/features/claude-code-skills-plugin.mdsimilarity index 65%rename from docs/home/1-features/claude-code-skills-plugin.mdrename to docs/features/claude-code-skills-plugin.mdindex 37a34fe84..9292d1389 100644--- a/docs/home/1-features/claude-code-skills-plugin.md+++ b/docs/features/claude-code-skills-plugin.md@@ -1,5 +1,6 @@----title: Claude Code Skills Plugin+title: "Claude Code Skills Plugin"+description: "Build, run, validate, and edit AI methods directly from Claude Code. 10+ slash commands for the full Pipelex method lifecycle using the MTHDS skills plugin."---# Claude Code Skills Plugin@@ -8,7 +9,7 @@ Build, run, validate, and edit AI methods directly from Claude Code.## Overview-The **MTHDS skills plugin** for Claude Code brings the full Pipelex workflow into your AI coding assistant. Build methods from natural language, validate them, run them, and iterate — all through conversational slash commands. The plugin leverages the `pipelex-agent` CLI under the hood for structured JSON communication.+The **MTHDS skills plugin** for Claude Code brings the full Pipelex workflow into your AI coding assistant. Build methods from natural language, validate them, run them, and iterate through conversational slash commands. The plugin leverages the `pipelex-agent` CLI under the hood for structured JSON communication.Install from [mthds-ai/skills](https://github.com/mthds-ai/skills).@@ -24,7 +25,7 @@ Install from [mthds-ai/skills](https://github.com/mthds-ai/skills).| `/mthds-run` | Execute methods and interpret JSON output (supports dry runs and graph generation) || `/mthds-inputs` | Prepare inputs: placeholder templates, synthetic test data, or user-provided files || `/mthds-install` | Install method packages from GitHub or local directories |-| `/mthds-pkg` | Manage packages — initialize, add dependencies, lock, install, update, validate |+| `/mthds-pkg` | Manage package manifests and related package workflows || `/mthds-publish` | Publish methods to mthds.sh |## Getting Started@@ -36,3 +37,9 @@ Install from [mthds-ai/skills](https://github.com/mthds-ai/skills).```Once installed, type `/mthds-build` in Claude Code to create your first method from a natural language description.++## Related Documentation++- [Agent CLI](../tools/cli/agent-cli.md) - JSON contract used under the hood+- [Packages](../building-methods/packages.md) - `METHODS.toml` manifest workflow+- [Package Commands](../tools/cli/pkg.md) - Current `mthds package` commandsdiff --git a/docs/home/1-features/cli.md b/docs/features/cli.mdsimilarity index 77%rename from docs/home/1-features/cli.mdrename to docs/features/cli.mdindex 1604cdd78..77e171726 100644--- a/docs/home/1-features/cli.md+++ b/docs/features/cli.md@@ -1,5 +1,6 @@----title: CLI+title: "CLI"+description: "The Pipelex command-line interface for developing, validating, and running AI methods. Covers login, init, build, validate, run, graph, show, and more."---# Command-Line Interface@@ -24,6 +25,14 @@ The `pipelex` CLI is the primary tool for working with Pipelex methods. It cover| **`pipelex show`** | Display configuration, pipes, and list AI models || **`pipelex which`** | Locate where a pipe is defined, similar to `which` for executables |+## Related CLI++Package manifest management is currently exposed through the lowercase `mthds` CLI:++- `mthds package init`+- `mthds package list`+- `mthds package validate`+## Execution Options- **Dry run** — `--dry-run` executes with mocked LLM responses to test pipeline logic without API calls@@ -48,4 +57,10 @@ The `pipelex-agent` CLI is a machine-first interface designed for automated envi| `models` | List available model presets, aliases, and talent mappings || `doctor` | Check configuration health and auto-fix issues |-For detailed CLI documentation, see the [CLI reference](../9-tools/cli/index.md).+For detailed CLI documentation, see the [CLI reference](../tools/cli/index.md).++## Related Documentation++- [CLI Reference](../tools/cli/index.md) - Runtime CLI commands+- [Agent CLI](../tools/cli/agent-cli.md) - Machine-oriented JSON interface+- [Package Commands](../tools/cli/pkg.md) - Current `mthds package` manifest commandsdiff --git a/docs/home/1-features/cloud-storage.md b/docs/features/cloud-storage.mdsimilarity index 81%rename from docs/home/1-features/cloud-storage.mdrename to docs/features/cloud-storage.mdindex 28c73758c..5bad483d6 100644--- a/docs/home/1-features/cloud-storage.md+++ b/docs/features/cloud-storage.md@@ -1,5 +1,6 @@---title: Cloud Storage+description: "Store pipeline artifacts on AWS S3, Google Cloud Storage, or local disk. Pipelex handles uploads, signed URLs, and access control out of the box."---# Cloud Storage@@ -26,4 +27,4 @@ Pipelex can automatically upload generated artifacts — images, extracted pagesStorage is configured in `pipelex.toml` under `[pipelex.storage_config]`. Set `method` to `local`, `in_memory`, `s3`, or `gcp`, then provide provider-specific settings such as `bucket_name`, `region`, or `project_id` in the matching subsection.-For AWS configuration, see [AWS Configuration](../7-configuration/config-technical/aws-config.md).+For AWS configuration, see [AWS Configuration](../configuration/config-technical/aws-config.md).diff --git a/docs/home/1-features/concepts.md b/docs/features/concepts.mdsimilarity index 87%rename from docs/home/1-features/concepts.mdrename to docs/features/concepts.mdindex e735bd444..9d1c1e81a 100644--- a/docs/home/1-features/concepts.md+++ b/docs/features/concepts.md@@ -1,5 +1,6 @@----title: Concepts & Structured Types+title: "Concepts & Structured Types"+description: "Learn about Pipelex Concepts — the semantic typing system that defines what kind of data flows through your AI pipelines, including native types, inline structures, and Python classes."---# Concepts & Structured Types@@ -43,4 +44,4 @@ For advanced use cases, generate Pydantic BaseModels from your declarative conceCreate specialized versions of existing concepts using the `refines` keyword. Build concept hierarchies for domain modeling — for example, a `DetailedInvoice` that refines a base `Invoice` concept, inheriting its structure while adding more specific semantics.-For detailed guidance, see [Define Your Concepts](../6-build-reliable-ai-workflows/concepts/define_your_concepts.md).+For detailed guidance, see [Define Your Concepts](../building-methods/concepts/define_your_concepts.md).diff --git a/docs/home/1-features/configuration.md b/docs/features/configuration.mdsimilarity index 57%rename from docs/home/1-features/configuration.mdrename to docs/features/configuration.mdindex 78a890ce3..3a28d22ef 100644--- a/docs/home/1-features/configuration.md+++ b/docs/features/configuration.md@@ -1,5 +1,6 @@----title: Configuration System+title: "Configuration System"+description: "Multi-level TOML configuration for Pipelex: base defaults, project overrides, environment-specific, and run-mode-specific settings with environment variable support."---# Configuration System@@ -26,11 +27,11 @@ Use `${VAR_NAME}` syntax in TOML files for dynamic configuration from environmen## Key Configuration Areas-- **[Inference Backends](../7-configuration/config-technical/inference-backend-config.md)** — LLM providers, models, and routing-- **[Logging](../7-configuration/config-practical/logging-config.md)** — Log levels and output-- **[Telemetry](../7-configuration/config-practical/telemetry-config.md)** — Observability settings-- **[Reporting](../7-configuration/config-practical/reporting-config.md)** — Cost tracking and reports-- **[Dry Run](../7-configuration/config-pipeline-validation/dry-run-config.md)** — Mock generation settings-- **[Features](../7-configuration/config-advanced/feature-config.md)** — Feature flags+- **[Inference Backends](../configuration/config-technical/inference-backend-config.md)** — LLM providers, models, and routing+- **[Logging](../configuration/config-practical/logging-config.md)** — Log levels and output+- **[Telemetry](../configuration/config-practical/telemetry-config.md)** — Observability settings+- **[Reporting](../configuration/config-practical/reporting-config.md)** — Cost tracking and reports+- **[Dry Run](../configuration/config-pipeline-validation/dry-run-config.md)** — Mock generation settings+- **[Features](../configuration/config-advanced/feature-config.md)** — Feature flags-For full configuration reference, see [Configuration](../7-configuration/index.md).+For full configuration reference, see [Configuration](../configuration/index.md).diff --git a/docs/home/1-features/cost-tracking.md b/docs/features/cost-tracking.mdsimilarity index 79%rename from docs/home/1-features/cost-tracking.mdrename to docs/features/cost-tracking.mdindex 42bf139ff..228bebf40 100644--- a/docs/home/1-features/cost-tracking.md+++ b/docs/features/cost-tracking.md@@ -1,5 +1,6 @@---title: Cost Tracking & Reporting+description: "Track inference costs across your Pipelex pipelines. Monitor spending per model, per step, and per run with built-in console reporting and CSV export."---# Cost Tracking & Reporting@@ -22,4 +23,4 @@ Export detailed cost reports as CSV files for analysis, billing, and audit trailImplement custom reporting backends via the [Reporting Delegate](advanced-customizations.md) injection point. The reporting protocol receives structured cost events during execution, allowing you to push data to your own analytics, dashboards, or billing systems.-For configuration, see [Reporting Configuration](../7-configuration/config-practical/reporting-config.md).+For configuration, see [Reporting Configuration](../configuration/config-practical/reporting-config.md).diff --git a/docs/home/1-features/document-extraction.md b/docs/features/document-extraction.mdsimilarity index 79%rename from docs/home/1-features/document-extraction.mdrename to docs/features/document-extraction.mdindex 115107db1..eaca00546 100644--- a/docs/home/1-features/document-extraction.md+++ b/docs/features/document-extraction.md@@ -1,5 +1,6 @@----title: Document Extraction+title: "Document Extraction"+description: "Multi-provider OCR and document processing with Mistral OCR, Azure Document Intelligence, docling, and Deepseek-OCR. PDF processing, layout analysis, and table recognition."---# Document Extraction@@ -34,3 +35,9 @@ Unlike LLM APIs (partly standardized around OpenAI's completions API), the OCR l## Documents in LLM PromptsInclude PDFs directly in your prompts using `@variable` syntax. PipeLLM automatically handles document rendering — single documents, multiple documents, and mixed content combining text, images, and PDFs are all supported.++## Related Documentation++- [PipeExtract](../building-methods/pipes/pipe-operators/PipeExtract.md) - Operator reference and MTHDS fields+- [Simple OCR Example](../cookbook/simple-ocr.md) - Small end-to-end extraction example+- [Generic Document Extraction](../cookbook/extract-generic.md) - Multi-step document method examplediff --git a/docs/home/1-features/execution-graph.md b/docs/features/execution-graph.mdsimilarity index 85%rename from docs/home/1-features/execution-graph.mdrename to docs/features/execution-graph.mdindex 8f0c03f3d..6e7477c27 100644--- a/docs/home/1-features/execution-graph.md+++ b/docs/features/execution-graph.md@@ -1,5 +1,6 @@---title: Execution Graph Visualization+description: "Visualize pipeline execution as an interactive graph. Inspect data flow, step order, and intermediate outputs for full auditability of your AI workflows."---# Execution Graph Visualization@@ -34,4 +35,4 @@ View the actual data at each execution stage:- `--graph-no-data` — Generate a structural graph without data<!-- path verified: resolves to docs/images/flow-chart-example.png -->-{ width="400" }+{ width="400" }diff --git a/docs/home/1-features/gateway.md b/docs/features/gateway.mdsimilarity index 83%rename from docs/home/1-features/gateway.mdrename to docs/features/gateway.mdindex dffef976d..ce506f4b8 100644--- a/docs/home/1-features/gateway.md+++ b/docs/features/gateway.md@@ -1,5 +1,6 @@----title: Pipelex Gateway & Model Access+title: "Pipelex Gateway & Model Access"+description: "Access 60+ AI models through the Pipelex Gateway with a single API key, or bring your own keys for direct provider access. Supports OpenAI, Anthropic, Mistral, and more."---# Pipelex Gateway & Model Access@@ -15,7 +16,7 @@ A fully managed infrastructure providing unified access to AI models through a s- **Enterprise-grade architecture** — built for reliability and scale- **Extensive provider support** — OpenAI, Google, Anthropic, Mistral, xAI, and more-Browse all supported models in the [Gateway Models](../5-setup/gateway-models.md) reference.+Browse all supported models in the [Gateway Models](../setup/gateway-models.md) reference.Get your Gateway API key at [app.pipelex.com](https://app.pipelex.com/) or [join the waitlist](https://go.pipelex.com/waitlist).@@ -49,4 +50,4 @@ Run open-source models through dedicated providers:Routing profiles control which backend handles each model. Define pattern-based routes, defaults, and fallback orders in `routing_profiles.toml`. Switch a pipeline from one provider to another — or from Pipelex Gateway to your own keys — without changing the method definition.-See [Configure AI Providers](../5-setup/configure-ai-providers.md) for setup details.+See [Configure AI Providers](../setup/configure-ai-providers.md) for setup details.diff --git a/docs/home/1-features/image-generation.md b/docs/features/image-generation.mdsimilarity index 85%rename from docs/home/1-features/image-generation.mdrename to docs/features/image-generation.mdindex 406448bba..2ae18a277 100644--- a/docs/home/1-features/image-generation.md+++ b/docs/features/image-generation.md@@ -1,5 +1,6 @@----title: Image Generation+title: "Image Generation"+description: "Generate images from text prompts using FLUX, GPT Image, and other providers. PipeImgGen integrates text-to-image generation directly into your Pipelex pipelines."---# Image Generation@@ -38,4 +39,4 @@ Generated images can be automatically uploaded to AWS S3 or Google Cloud StorageUse PipeImgGen in your `.mthds` files to generate images as part of a pipeline. The operator accepts a text prompt (or an ImgGenPrompt concept) and outputs an Image concept. Model presets let you configure quality levels and default models in `2_img_gen_deck.toml`.-See [PipeImgGen reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeImgGen.md).+See [PipeImgGen reference](../building-methods/pipes/pipe-operators/PipeImgGen.md).diff --git a/docs/home/1-features/index.md b/docs/features/index.mdsimilarity index 88%rename from docs/home/1-features/index.mdrename to docs/features/index.mdindex af8eb0ec6..2100f5a8a 100644--- a/docs/home/1-features/index.md+++ b/docs/features/index.md@@ -1,10 +1,11 @@----title: Features+title: "Pipelex Features"+description: "Explore all Pipelex capabilities: declarative AI methods, 60+ model access, document extraction, image generation, pipeline orchestration, CLI tools, and production monitoring."---# Pipelex Features-Pipelex is the AI method framework that eliminates the complexity of building AI-powered applications. One framework for prompts, pipelines, and structured outputs. One API key for dozens of AI models. One method from prototype to production.+Pipelex is the reference runtime for AI methods written in MTHDS. This section covers the main capabilities you use to define methods, run them, and operate them in production.This section covers all Pipelex capabilities, organized by area.@@ -68,7 +69,7 @@ This section covers all Pipelex capabilities, organized by area.- **[Claude Code Skills Plugin](claude-code-skills-plugin.md)**- Build, run, validate, and edit AI methods directly from Claude Code with the MTHDS skills plugin. 10+ slash commands for the full method lifecycle.+ Build, run, validate, and edit AI methods directly from Claude Code with the MTHDS skills plugin. Slash commands cover the full method lifecycle.- **[CLI](cli.md)**diff --git a/docs/home/1-features/llm-integration.md b/docs/features/llm-integration.mdsimilarity index 77%rename from docs/home/1-features/llm-integration.mdrename to docs/features/llm-integration.mdindex 264d8c9dc..1fe16396c 100644--- a/docs/home/1-features/llm-integration.md+++ b/docs/features/llm-integration.md@@ -1,5 +1,6 @@----title: LLM Integration+title: "LLM Integration"+description: "Pipelex LLM integration: text generation, structured outputs, vision models, prompting styles, and system prompt inheritance. Write once, run on any supported model."---# LLM Integration@@ -17,7 +18,7 @@ Two approaches for structured outputs:- **Two-step** — Generate text first, then parse into a structured concept. More reliable for complex schemas.- **Direct JSON** — Generate structured JSON directly from the LLM using provider-native structured output features.-See [LLM Structured Generation](../6-build-reliable-ai-workflows/llm-structured-generation-config.md).+See [LLM Structured Generation](../building-methods/llm-structured-generation-config.md).## Vision Language Models@@ -27,7 +28,7 @@ Include images and PDFs directly in LLM prompts using `@variable` syntax. SupporAdapt prompts for different LLM families (OpenAI, Anthropic, Mistral) to get the best results from each provider. Pipelex applies provider-specific formatting, system prompt handling, and structured output instructions automatically.-See [LLM Prompting Style](../6-build-reliable-ai-workflows/adapt-to-llm-prompting-style-openai-anthropic-mistral.md).+See [LLM Prompting Style](../building-methods/adapt-to-llm-prompting-style-openai-anthropic-mistral.md).## System Prompt Inheritance@@ -37,4 +38,4 @@ Define system prompts at the domain level and have them automatically inheritedNamed configurations (temperature, max tokens, model selection, etc.) for consistent model behavior. Define presets once in the model deck, then reference them by name across all your pipelines using `$preset_name` syntax.-See [Optimize Cost & Quality](../6-build-reliable-ai-workflows/configure-ai-llm-to-optimize-methods.md).+See [Optimize Cost & Quality](../building-methods/configure-ai-llm-to-optimize-methods.md).diff --git a/docs/home/1-features/mthds-language.md b/docs/features/mthds-language.mdsimilarity index 68%rename from docs/home/1-features/mthds-language.mdrename to docs/features/mthds-language.mdindex fe42a8a92..7c487b43e 100644--- a/docs/home/1-features/mthds-language.md+++ b/docs/features/mthds-language.md@@ -1,5 +1,6 @@----title: MTHDS Language+title: "MTHDS Language"+description: "MTHDS is a declarative, TOML-based file format for defining AI methods without writing code. Method logic in .mthds files, execution by the Pipelex runtime."---# MTHDS Language@@ -20,7 +21,7 @@ A bundle is a complete method package defined in a single `.mthds` file. It cont## Packages & Dependencies-Package management with `METHODS.toml` manifest files. Declare package identity, dependencies with semantic version constraints (exact, caret, tilde, comparison), and export visibility controls. Packages can be installed from GitHub repositories or local directories.+Use `METHODS.toml` to declare package identity and exports. The current public package-manifest workflow is documented through the lowercase `mthds` CLI: `mthds package init`, `mthds package list`, and `mthds package validate`.## Cross-Package References@@ -32,4 +33,10 @@ Inline concept structures with nested concepts make Pipelex fully usable with ju## Language Specification-For the formal language specification, see [mthds.ai](https://mthds.ai).+For the formal language specification, see [mthds.ai](https://mthds.ai). For package-manifest details, see [Packages](../building-methods/packages.md).++## Related Documentation++- [Packages](../building-methods/packages.md) - `METHODS.toml` manifests and exports+- [Concepts](./concepts.md) - Semantic typing and structured content+- [Pipe Operators](./pipe-operators.md) - The operators you can declare in `.mthds` filesdiff --git a/docs/home/1-features/pipe-operators.md b/docs/features/pipe-operators.mdsimilarity index 72%rename from docs/home/1-features/pipe-operators.mdrename to docs/features/pipe-operators.mdindex cca450b9e..1eb672544 100644--- a/docs/home/1-features/pipe-operators.md+++ b/docs/features/pipe-operators.md@@ -1,5 +1,6 @@----title: Pipe Operators+title: "Pipe Operators Overview"+description: "Pipe operators are the building blocks of Pipelex methods: PipeLLM, PipeExtract, PipeImgGen, PipeSearch, PipeCompose, and PipeFunc — each handling a specific type of AI processing."---# Pipe Operators@@ -14,34 +15,34 @@ Pipe operators are the building blocks of Pipelex methods. Each operator performThe core operator for LLM interaction. Supports text generation, structured output generation (two-step or direct JSON), vision (images and PDFs in prompts via `@variable` syntax), system prompts, and model presets. Works with any supported LLM provider.-See [PipeLLM reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md).+See [PipeLLM reference](../building-methods/pipes/pipe-operators/PipeLLM.md).## PipeExtractOCR and document extraction from PDFs and images. Supports multiple providers (pypdfium2, Mistral OCR, Azure Document Intelligence, docling, Deepseek-OCR), page rendering, embedded image extraction, and layout analysis. Swap providers by changing configuration, no code changes needed.-See [PipeExtract reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md).+See [PipeExtract reference](../building-methods/pipes/pipe-operators/PipeExtract.md).## PipeImgGenText-to-image and image-to-image generation using models like FLUX, GPT Image, Nano Banana, and others. Outputs are stored locally or in cloud storage with configurable URL signing.-See [PipeImgGen reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeImgGen.md).+See [PipeImgGen reference](../building-methods/pipes/pipe-operators/PipeImgGen.md).## PipeSearchWeb search with structured results and source citations. Powered by Linkup or Pipelex Gateway, results come back as typed SearchResult concepts ready for downstream processing.-See [PipeSearch reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md).+See [PipeSearch reference](../building-methods/pipes/pipe-operators/PipeSearch.md).## PipeComposeDeterministic object construction without an LLM. Compose outputs from working memory variables, fixed values, Jinja2 templates, and nested structures. Ideal for aggregating results from previous steps or building inputs for downstream pipes.-See [PipeCompose reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeCompose.md).+See [PipeCompose reference](../building-methods/pipes/pipe-operators/PipeCompose.md).## PipeFuncExecute custom Python functions within pipelines. Functions are auto-discovered via the `@pipe_func()` decorator and receive the current working memory as their input. Use PipeFunc when you need logic that goes beyond what declarative operators provide.-See [PipeFunc reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeFunc.md).+See [PipeFunc reference](../building-methods/pipes/pipe-operators/PipeFunc.md).diff --git a/docs/home/1-features/pipeline-orchestration.md b/docs/features/pipeline-orchestration.mdsimilarity index 70%rename from docs/home/1-features/pipeline-orchestration.mdrename to docs/features/pipeline-orchestration.mdindex 2996a1104..b1b6dd713 100644--- a/docs/home/1-features/pipeline-orchestration.md+++ b/docs/features/pipeline-orchestration.md@@ -1,5 +1,6 @@----title: Pipeline Orchestration+title: "Pipeline Orchestration"+description: "Build complex AI workflows with pipeline controllers: PipeSequence, PipeParallel, PipeBatch, and PipeCondition — all declared in .mthds files."---# Pipeline Orchestration@@ -14,34 +15,34 @@ Pipeline controllers define how pipes are assembled and executed. They handle seRun pipes one after another, passing data through working memory. The most common controller for multi-step methods. Each step can read variables written by previous steps, enabling progressive data enrichment.-See [PipeSequence reference](../6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeSequence.md).+See [PipeSequence reference](../building-methods/pipes/pipe-controllers/PipeSequence.md).## PipeParallelExecute multiple independent pipes concurrently for faster throughput. Each branch starts with a deep copy of the current working memory, and their outputs are merged back when all branches complete.-See [PipeParallel reference](../6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeParallel.md).+See [PipeParallel reference](../building-methods/pipes/pipe-controllers/PipeParallel.md).## PipeBatchApply the same pipe to every item in a list — the map operation for pipelines. Takes a list input and produces a list output, processing each item independently.-See [PipeBatch reference](../6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeBatch.md).+See [PipeBatch reference](../building-methods/pipes/pipe-controllers/PipeBatch.md).## PipeConditionConditional branching based on Jinja2 expressions evaluated against working memory. Route execution to different pipes depending on runtime data, enabling dynamic method behavior.-See [PipeCondition reference](../6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeCondition.md).+See [PipeCondition reference](../building-methods/pipes/pipe-controllers/PipeCondition.md).## Working MemoryTemporary storage for data flowing between pipes within a single execution. Variables are typed by concepts and scoped to the pipeline. Each pipe reads from and writes to working memory, creating a shared data context across the method.-See [Working Memory](../6-build-reliable-ai-workflows/pipes/working-memory.md).+See [Working Memory](../building-methods/pipes/working-memory.md).## MultiplicityControl how many items pipes accept and produce: single values, variable-length lists (`[]`), or fixed-count lists (`[N]`). Multiplicity is declared in the pipe definition and validated at definition time.-See [Understanding Multiplicity](../6-build-reliable-ai-workflows/pipes/understanding-multiplicity.md).+See [Understanding Multiplicity](../building-methods/pipes/understanding-multiplicity.md).diff --git a/docs/home/1-features/plxt.md b/docs/features/plxt.mdsimilarity index 85%rename from docs/home/1-features/plxt.mdrename to docs/features/plxt.mdindex bab760bc2..f0701dadd 100644--- a/docs/home/1-features/plxt.md+++ b/docs/features/plxt.md@@ -1,5 +1,6 @@---title: plxt Formatter & Linter+description: "Format and lint .mthds files with plxt, a fast Rust-based tool with schema validation. Catch structural errors in declarative AI workflows before runtime."---# plxt Formatter & Linter@@ -26,4 +27,4 @@ Schema-based validation that catches structural and semantic issues beyond basicUse `plxt fmt --check` to validate formatting without modifying files, and run `plxt lint` separately for schema and semantic checks. Both commands exit with a non-zero code on errors, making them easy to enforce in automated workflows.-For details, see the [plxt reference](../9-tools/plxt.md).+For details, see the [plxt reference](../tools/plxt.md).diff --git a/docs/home/1-features/telemetry.md b/docs/features/telemetry.mdsimilarity index 84%rename from docs/home/1-features/telemetry.mdrename to docs/features/telemetry.mdindex ba89c5213..0c1d3c0ec 100644--- a/docs/home/1-features/telemetry.md+++ b/docs/features/telemetry.md@@ -1,5 +1,6 @@----title: Telemetry & Observability+title: "Telemetry & Observability"+description: "Production monitoring for Pipelex AI methods with Langfuse, OpenTelemetry, and PostHog integration. Track costs, latency, errors, and execution patterns."---# Telemetry & Observability@@ -33,4 +34,4 @@ When using Pipelex Gateway as your inference backend, privacy-respecting metrics- **Content redaction** — Control whether prompt/completion content is included in spans- **Mode-based gating** — Enable custom telemetry for CLI usage but disable it during unit tests-For configuration, see [Telemetry Configuration](../7-configuration/config-practical/telemetry-config.md) and [Telemetry Setup](../5-setup/telemetry.md).+For configuration, see [Telemetry Configuration](../configuration/config-practical/telemetry-config.md) and [Telemetry Setup](../setup/telemetry.md).diff --git a/docs/home/1-features/validation-dry-run.md b/docs/features/validation-dry-run.mdsimilarity index 84%rename from docs/home/1-features/validation-dry-run.mdrename to docs/features/validation-dry-run.mdindex 2d3039a0a..184d28304 100644--- a/docs/home/1-features/validation-dry-run.md+++ b/docs/features/validation-dry-run.md@@ -1,5 +1,6 @@---title: Validation & Dry Run+description: "Catch errors before they cost time and money. Validate .mthds files statically and dry-run pipelines with mocked LLM responses — no API calls required."---# Validation & Dry Run@@ -36,4 +37,4 @@ List specific pipe codes in `pipelex.dry_run_config.allowed_to_fail_pipes` so dr- `pipelex run pipe my_pipe --dry-run` — Dry run execution- `pipelex run pipe my_pipe --dry-run --mock-inputs` — Generate synthetic inputs-For configuration details, see [Dry Run Configuration](../7-configuration/config-pipeline-validation/dry-run-config.md).+For configuration details, see [Dry Run Configuration](../configuration/config-pipeline-validation/dry-run-config.md).diff --git a/docs/home/1-features/web-search.md b/docs/features/web-search.mdsimilarity index 63%rename from docs/home/1-features/web-search.mdrename to docs/features/web-search.mdindex d8a5f4a52..da2ae3013 100644--- a/docs/home/1-features/web-search.md+++ b/docs/features/web-search.md@@ -1,5 +1,6 @@----title: Web Search+title: "Web Search"+description: "Structured web search integrated into Pipelex pipelines. PipeSearch returns results with source citations, ready for downstream LLM processing."---# Web Search@@ -20,4 +21,8 @@ PipeSearch brings web search directly into your methods. Results come back as stUse PipeSearch in a PipeSequence to retrieve information from the web and then process it with an LLM. The search results are stored in working memory as SearchResult concepts, available to downstream pipes.-See [PipeSearch reference](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md).+## Related Documentation++- [PipeSearch](../building-methods/pipes/pipe-operators/PipeSearch.md) - Operator reference and supported output shapes+- [Pipeline Orchestration](./pipeline-orchestration.md) - Compose search with downstream pipes+- [Working Memory](../building-methods/pipes/working-memory.md) - How search outputs flow through a methoddiff --git a/docs/home/2-get-started/images/character_sheet.png b/docs/get-started/images/character_sheet.pngsimilarity index 100%rename from docs/home/2-get-started/images/character_sheet.pngrename to docs/get-started/images/character_sheet.pngdiff --git a/docs/home/2-get-started/images/extracted_character_metadata.png b/docs/get-started/images/extracted_character_metadata.pngsimilarity index 100%rename from docs/home/2-get-started/images/extracted_character_metadata.pngrename to docs/get-started/images/extracted_character_metadata.pngdiff --git a/docs/home/2-get-started/images/structured_character_sheet.png b/docs/get-started/images/structured_character_sheet.pngsimilarity index 100%rename from docs/home/2-get-started/images/structured_character_sheet.pngrename to docs/get-started/images/structured_character_sheet.pngdiff --git a/docs/home/2-get-started/images/structured_character_sheet_json.png b/docs/get-started/images/structured_character_sheet_json.pngsimilarity index 100%rename from docs/home/2-get-started/images/structured_character_sheet_json.pngrename to docs/get-started/images/structured_character_sheet_json.pngdiff --git a/docs/home/2-get-started/write-methods-manually.md b/docs/get-started/write-methods-manually.mdsimilarity index 86%rename from docs/home/2-get-started/write-methods-manually.mdrename to docs/get-started/write-methods-manually.mdindex 5b7bdeb12..a46737b9d 100644--- a/docs/home/2-get-started/write-methods-manually.md+++ b/docs/get-started/write-methods-manually.md@@ -1,8 +1,13 @@+---+title: "Getting Started — Writing Methods"+description: "Learn how to write Pipelex AI methods manually. Create methods, define concepts, and understand the `.mthds` language step by step."+---+# Writing Methods-Ready to dive deeper? This section shows you how to manually create pipelines and understand the `.mthds` language.+Ready to dive deeper? This section shows you how to manually create methods and understand the `.mthds` language.-## Write Your First Pipeline+## Write Your First MethodLet's build a **character generator** to understand the basics.Create a `.mthds` file anywhere in your project (we recommend a `pipelines` directory):@@ -22,14 +27,14 @@ Think of it and then output the character description."""```-This pipeline is a simple LLM call without any input, with the provided prompt and will output a `TextContent` object. See more about native concepts [here](../6-build-reliable-ai-workflows/concepts/define_your_concepts.md)+This pipeline is a simple LLM call without any input, with the provided prompt and will output a `TextContent` object. See more about native concepts [here](../building-methods/concepts/define_your_concepts.md)### Run Your First Pipelex Script**CLI:**```bash-pipelex run create_character+pipelex run pipe create_character```**Python:**@@ -67,7 +72,7 @@ As you might notice, this is plain text, and nothing is structured. Now we are g## Generate Structured Outputs-Let's create a rigorously structured `Character` object instead of plain text. We need to create the concept `Character`. The concept names MUST be in PascalCase. [Learn more about defining concepts](../6-build-reliable-ai-workflows/concepts/define_your_concepts.md)+Let's create a rigorously structured `Character` object instead of plain text. We need to create the concept `Character`. The concept names MUST be in PascalCase. [Learn more about defining concepts](../building-methods/concepts/define_your_concepts.md)### Option 1: Define the Structure in your `.mthds` file@@ -139,7 +144,7 @@ class Character(StructuredContent):!!! tip "Keep Structure Files Clean"Keep your `StructuredContent` classes in dedicated files with minimal module-level code. Pipelex imports these modules during auto-discovery, so any module-level code will be executed.-Learn more in [Inline Structures](../6-build-reliable-ai-workflows/concepts/inline-structures.md) or [Python StructuredContent Classes](../6-build-reliable-ai-workflows/concepts/python-classes.md).+Learn more in [Inline Structures](../building-methods/concepts/inline-structures.md) or [Python StructuredContent Classes](../building-methods/concepts/python-classes.md).### Use your Structured Concept in Your Pipe@@ -217,12 +222,12 @@ Your task is to extract specific data from the following description.```!!! tip "Template Syntax"- Our template syntax is based on [Jinja2](https://jinja.palletsprojects.com/en/stable/). Use `@` prefix for tagging a variable in the prompt. Learn more about prompting with Pipelex in the [PipeLLM documentation](../6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md).+ Our template syntax is based on [Jinja2](https://jinja.palletsprojects.com/en/stable/). Use `@` prefix for tagging a variable in the prompt. Learn more about prompting with Pipelex in the [PipeLLM documentation](../building-methods/pipes/pipe-operators/PipeLLM.md).!!! tip "Template Variables"`@character.description` grabs the `character` stuff from the instance and uses its `description` attribute.-Learn more about Jinja in the [PipeLLM documentation](../../home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md).+Learn more about Jinja in the [PipeLLM documentation](../building-methods/pipes/pipe-operators/PipeLLM.md).#### Execute from Python@@ -328,24 +333,24 @@ Now that you understand the basics, explore more:**Learn More about the PipeLLM:**-- [LLM Configuration: play with the models](../../home/6-build-reliable-ai-workflows/configure-ai-llm-to-optimize-methods.md) - Optimize cost and quality-- [Full configuration of the PipeLLM](../../home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md)+- [LLM Configuration: play with the models](../building-methods/configure-ai-llm-to-optimize-methods.md) - Optimize cost and quality+- [Full configuration of the PipeLLM](../building-methods/pipes/pipe-operators/PipeLLM.md)**Learn more about Pipelex (domains, project structure, best practices...)**-- [Build Reliable AI Methods](../../home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md) - Deep dive into pipeline design-- [Cookbook Examples](../../home/4-cookbook-examples/index.md) - Real-world examples and patterns+- [Build Reliable AI Methods](../building-methods/kick-off-a-methods-project.md) - Deep dive into pipeline design+- [Cookbook Examples](../cookbook/index.md) - Real-world examples and patterns**Learn More about the other pipes**-- [Pipe Operators](../../home/6-build-reliable-ai-workflows/pipes/pipe-operators/index.md) - PipeLLM, PipeExtract, PipeCompose, and more-- [Pipe Controllers](../../home/6-build-reliable-ai-workflows/pipes/pipe-controllers/index.md) - PipeSequence, PipeParallel, PipeBatch, PipeCondition+- [Pipe Operators](../building-methods/pipes/pipe-operators/index.md) - PipeLLM, PipeExtract, PipeCompose, and more+- [Pipe Controllers](../building-methods/pipes/pipe-controllers/index.md) - PipeSequence, PipeParallel, PipeBatch, PipeCondition**Explore Tools:**-- [Claude Code Skills Plugin](../../home/1-features/claude-code-skills-plugin.md) - Generate pipelines from natural language-- [CLI Commands](../9-tools/cli/index.md) - Command-line interface reference+- [Claude Code Skills Plugin](../features/claude-code-skills-plugin.md) - Generate pipelines from natural language+- [CLI Commands](../tools/cli/index.md) - Command-line interface reference**Configure:**-- [Inference Backend](../../home/7-configuration/config-technical/inference-backend-config.md) - Configure model providers+- [Inference Backend](../configuration/config-technical/inference-backend-config.md) - Configure model providersdiff --git a/docs/home/1-features/advanced-customizations.md b/docs/home/1-features/advanced-customizations.mddeleted file mode 100644index 43286d93e..000000000--- a/docs/home/1-features/advanced-customizations.md+++ /dev/null@@ -1,28 +0,0 @@-----title: Advanced Customizations------# Advanced Customizations--A dependency injection framework for extending and customizing Pipelex behavior.--## Overview--Pipelex provides well-defined injection points that let you replace or extend core behaviors without modifying the framework itself. Each injection point follows a strict protocol contract, making implementations testable and swappable. Register custom providers at initialization time and the runtime uses them throughout execution.--## Injection Points--| Injection Point | Purpose |-|-----------------|---------|-| **[Secrets Provider](../10-advanced-customizations/secrets-provider-injection.md)** | Custom secret management (environment, vaults, etc.) |-| **[Storage Provider](../10-advanced-customizations/storage-provider-injection.md)** | Custom cloud storage backends |-| **[Observer](../10-advanced-customizations/observer-provider-injection.md)** | Custom execution data capture |-| **[Reporting Delegate](../10-advanced-customizations/reporting-delegate-injection.md)** | Custom cost reporting |-| **[Content Generator](../10-advanced-customizations/content-generator-injection.md)** | Override LLM output generation |-| **[Pipe Router](../10-advanced-customizations/pipe-router-injection.md)** | Dynamic routing of pipes to implementations |--## Built-in Defaults--Some injection points provide safe built-in defaults or no-op implementations, so you only need to implement the ones relevant to your use case.--For detailed documentation, see [Advanced Customizations](../10-advanced-customizations/index.md).diff --git a/docs/home/10-advanced-customizations/content-generator-injection.md b/docs/home/10-advanced-customizations/content-generator-injection.mddeleted file mode 100644index dad784bac..000000000--- a/docs/home/10-advanced-customizations/content-generator-injection.md+++ /dev/null@@ -1,4 +0,0 @@-# Content Generator Injection--!!! warning "Under Construction"- This section is currently under development.diff --git a/docs/home/10-advanced-customizations/pipe-router-injection.md b/docs/home/10-advanced-customizations/pipe-router-injection.mddeleted file mode 100644index 9cc3929f8..000000000--- a/docs/home/10-advanced-customizations/pipe-router-injection.md+++ /dev/null@@ -1,4 +0,0 @@-# Pipe Router Injection--!!! warning "Under Construction"- This section is currently under development.diff --git a/docs/home/10-advanced-customizations/reporting-delegate-injection.md b/docs/home/10-advanced-customizations/reporting-delegate-injection.mddeleted file mode 100644index 3d9fe0a65..000000000--- a/docs/home/10-advanced-customizations/reporting-delegate-injection.md+++ /dev/null@@ -1,4 +0,0 @@-# Reporting Delegate Injection--!!! warning "Under Construction"- This section is currently under development.diff --git a/docs/home/10-advanced-customizations/secrets-provider-injection.md b/docs/home/10-advanced-customizations/secrets-provider-injection.mddeleted file mode 100644index a8b79188f..000000000--- a/docs/home/10-advanced-customizations/secrets-provider-injection.md+++ /dev/null@@ -1,4 +0,0 @@-# Secrets Provider Injection--!!! warning "Under Construction"- This section is currently under development.diff --git a/docs/home/10-advanced-customizations/storage-provider-injection.md b/docs/home/10-advanced-customizations/storage-provider-injection.mddeleted file mode 100644index 4d93eafd8..000000000--- a/docs/home/10-advanced-customizations/storage-provider-injection.md+++ /dev/null@@ -1,4 +0,0 @@-# Storage Provider Injection--!!! warning "Under Construction"- This section is currently under development.diff --git a/docs/home/5-setup/gateway-models.md b/docs/home/5-setup/gateway-models.mddeleted file mode 100644index d9081b667..000000000--- a/docs/home/5-setup/gateway-models.md+++ /dev/null@@ -1,6 +0,0 @@-----title: Gateway Available Models--------8<-- ".pipelex/inference/backends/pipelex_gateway_models.md"-diff --git a/docs/home/6-build-reliable-ai-workflows/packages.md b/docs/home/6-build-reliable-ai-workflows/packages.mddeleted file mode 100644index ef6ff7dfb..000000000--- a/docs/home/6-build-reliable-ai-workflows/packages.md+++ /dev/null@@ -1,474 +0,0 @@-# Packages--A **package** is a self-contained collection of `.mthds` bundles with a `METHODS.toml` manifest at the root. The manifest gives your project an identity, declares dependencies on other packages, and controls which pipes are visible to the outside world.--## What is a Package?--A package groups related bundles under a single manifest that provides:--- **Identity** — a unique address and semantic version for your project-- **Dependency declarations** — references to other packages your pipes rely on-- **Visibility control** — fine-grained exports that determine which pipes other domains can reference--!!! info "Backward Compatibility"- If your project has no `METHODS.toml`, everything works exactly as before — all pipes are treated as public. The manifest is entirely opt-in.--## The Package Manifest: `METHODS.toml`--Place a `METHODS.toml` file at the root of your project (next to your `.mthds` files or their parent directories). Here is a fully annotated example:--```toml-[package]-address = "github.com/acme/legal-tools"-version = "1.0.0"-description = "Legal document analysis and contract review methods."-authors = ["Acme Corp"]-license = "MIT"-mthds_version = ">=0.5.0"--[dependencies]-scoring_lib = { address = "github.com/acme/scoring-lib", version = "^2.0.0" }--[exports.legal.contracts]-pipes = ["extract_clause", "analyze_contract"]--[exports.scoring]-pipes = ["compute_weighted_score"]-```--### Field Reference--| Field | Required | Description |-|-------|----------|-------------|-| `address` | Yes | Package address following a hostname/path pattern (e.g. `github.com/org/repo`) |-| `version` | Yes | Semantic version (e.g. `1.0.0`, `2.1.3-beta.1`) |-| `description` | Yes | Human-readable package description (must not be empty) |-| `authors` | No | List of author names |-| `license` | No | SPDX license identifier (e.g. `MIT`, `Apache-2.0`) |-| <nobr>`mthds_version`</nobr> | No | Required MTHDS runtime version constraint |--## Dependencies--Dependencies are declared in the `[dependencies]` section using an alias-as-key format.--### Declaring Dependencies--Each dependency entry maps a **snake_case alias** to a package address and version constraint:--```toml-[dependencies]-scoring_lib = { address = "github.com/acme/scoring-lib", version = "^2.0.0" }-nlp_utils = { address = "github.com/acme/nlp-utils", version = ">=1.0.0, <3.0.0" }-```--- The **alias** (left-hand key) must be `snake_case`. It is used when making cross-package references with the `->` syntax (e.g. `scoring_lib->scoring.compute_weighted_score`).-- The **address** follows the same hostname/path pattern as the package address.-- Each dependency alias must be unique within the manifest.--### Version Constraints--The **version** field accepts standard version constraint syntax:--| Syntax | Meaning | Example |-|--------|---------|---------|-| `1.0.0` | Exact version | `1.0.0` |-| `^1.0.0` | Compatible release (same major) | `^2.0.0` |-| `~1.0.0` | Approximately compatible (same major.minor) | `~1.2.0` |-| `>=`, `<=`, `>`, `<` | Comparison operators | `>=1.0.0` |-| `==`, `!=` | Equality / inequality | `!=1.3.0` |-| Comma-separated | Compound constraints | `>=1.0.0, <2.0.0` |-| `*`, `1.*`, `1.0.*` | Wildcards | `2.*` |--### Local Path Dependencies--For development or when you maintain related packages side by side, declare a dependency with a `path` field pointing to a local directory:--```toml-[dependencies]-scoring_lib = { address = "github.com/acme/scoring-lib", version = "2.0.0", path = "../scoring-lib" }-```--When a `path` is present:--- The local directory is used directly — no VCS fetch occurs.-- The dependency is **excluded from the lock file** (`methods.lock`).-- Cross-package references work identically to remote dependencies.--!!! tip "Development Workflow"- Local path dependencies are ideal during active development of multiple packages. Point to a sibling checkout, iterate on both packages together, and remove the `path` field when you are ready to publish.--### Remote Dependencies--Dependencies without a `path` field are resolved via Git. Pipelex maps the package address to a clone URL (e.g. `github.com/acme/scoring-lib` becomes `https://github.com/acme/scoring-lib.git`), lists the remote version tags, selects the best match for the version constraint, and caches the result locally.--See [Dependency Workflow](#dependency-workflow) below for the full lock → install → update lifecycle.--## Cross-Package References--Once a dependency is declared in `METHODS.toml`, you can reference its exported pipes and concepts from your `.mthds` bundles using the **`->`** syntax.--### The `->` Syntax--A cross-package reference has the form:--```-alias->domain.code-```--| Part | Description |-|------|-------------|-| `alias` | The dependency alias declared in `[dependencies]` |-| `->` | Cross-package reference operator |-| `domain` | The dot-separated domain path inside the dependency package |-| `code` | The pipe code (`snake_case`) or concept code (`PascalCase`) |--### Referencing Pipes Across Packages--To call a pipe from a dependency inside a `PipeSequence` step, use the `->` syntax in the `pipe` field.--**Dependency package** (`scoring-lib`):--```toml title="METHODS.toml"-[package]-address = "github.com/acme/scoring-lib"-version = "2.0.0"-description = "Scoring utilities for weighted analysis."--[exports.scoring]-pipes = ["compute_weighted_score"]-```--```toml title="scoring.mthds"-domain = "scoring"--[concept.WeightedScore]-description = "A weighted score result"--[pipe.compute_weighted_score]-type = "PipeLLM"-description = "Compute a weighted score"-output = "WeightedScore"-prompt = "Compute a weighted score for: {{ item }}"-```--**Consumer package**:--```toml title="METHODS.toml"-[package]-address = "github.com/acme/analysis-app"-version = "1.0.0"-description = "Analysis application using the scoring library."--[dependencies]-scoring_lib = { address = "github.com/acme/scoring-lib", version = "^2.0.0" }--[exports.analysis]-pipes = ["analyze_item"]-```--```toml title="analysis.mthds"-domain = "analysis"-main_pipe = "analyze_item"--[pipe.analyze_item]-type = "PipeSequence"-description = "Analyze an item using the scoring dependency"-output = "AnalysisResult"-steps = [- { pipe = "scoring_lib->scoring.compute_weighted_score" },- { pipe = "summarize" },-]-```--The first step calls `compute_weighted_score` from the `scoring` domain of the `scoring_lib` dependency. The second step calls a local pipe.--!!! important- The referenced pipe must be listed in the dependency's `[exports]` section (or be a bundle's `main_pipe`, which is auto-exported). Referencing a non-exported pipe raises a visibility error at load time.--### Referencing Concepts Across Packages--Concepts from a dependency can be used in pipe inputs and outputs using the same `->` syntax:--```toml-[pipe.display_score]-type = "PipeLLM"-description = "Format a score for display"-inputs = { score = "scoring_lib->scoring.WeightedScore" }-output = "Text"-prompt = "Format this score for display: {{ score }}"-```--### Cross-Package Concept Refinement--You can refine a concept from a dependency — creating a more specialized version that inherits its structure:--```toml-[concept.DetailedScore]-description = "An extended score with additional detail"-refines = "scoring_lib->scoring.WeightedScore"-```--The refined concept inherits the structure of `WeightedScore` from the `scoring_lib` dependency's `scoring` domain. The base concept must be exported by the dependency.--For a complete guide on concept refinement, see [Refining Concepts](./concepts/refining-concepts.md#cross-package-refinement).--## Dependency Workflow--Managing dependencies follows a **lock → install → update** lifecycle, similar to other package managers.--### Lock File (`methods.lock`)--Running `pipelex pkg lock` generates a `methods.lock` file next to your `METHODS.toml`. The lock file records the exact resolved version, an integrity hash, and the source URL for every remote dependency:--```toml-["github.com/acme/scoring-lib"]-version = "2.0.0"-hash = "sha256:a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2"-source = "https://github.com/acme/scoring-lib"--["github.com/acme/nlp-utils"]-version = "1.3.0"-hash = "sha256:1234567890abcdef1234567890abcdef1234567890abcdef1234567890abcdef"-source = "https://github.com/acme/nlp-utils"-```--| Field | Description |-|-------|-------------|-| Table key | The package address |-| `version` | Exact resolved version (semantic version) |-| `hash` | SHA-256 integrity hash of all files in the package (excluding `.git/`) |-| `source` | HTTPS URL to the package source |--!!! note "Commit to Version Control"- You should commit `methods.lock` to your repository. This ensures that every collaborator and CI run installs the exact same dependency versions.--Local path dependencies are **not** recorded in the lock file — they are always resolved from the filesystem directly.--### Resolving and Locking (`pkg lock`)--```bash-pipelex pkg lock-```--This command:--1. Reads your `METHODS.toml` dependencies-2. Resolves each remote dependency via Git (listing tags, selecting the best version match)-3. Resolves transitive dependencies (dependencies of your dependencies)-4. Computes SHA-256 integrity hashes-5. Writes the `methods.lock` file--See the [Pkg Lock CLI reference](../9-tools/cli/pkg.md#pkg-lock) for details.--### Installing Dependencies (`pkg install`)--```bash-pipelex pkg install-```--This command:--1. Reads the `methods.lock` file-2. Fetches any packages not already present in the local cache-3. Verifies SHA-256 integrity of all cached packages against the lock file--If a hash mismatch is detected, the command fails with an integrity error.--See the [Pkg Install CLI reference](../9-tools/cli/pkg.md#pkg-install) for details.--### Updating Dependencies (`pkg update`)--```bash-pipelex pkg update-```--This command performs a **fresh resolve** — it ignores the existing lock file, re-resolves all dependencies from scratch, and rewrites `methods.lock`. It displays a diff showing added, removed, and updated packages.--!!! tip- Use `pkg update` after changing version constraints in `METHODS.toml`. For day-to-day reproducible builds, use `pkg install` instead.--See the [Pkg Update CLI reference](../9-tools/cli/pkg.md#pkg-update) for details.--### Transitive Dependencies--Pipelex resolves transitive dependencies automatically. If your dependency `A` depends on package `B`, then `B` is resolved and locked as well.--**Minimum Version Selection (MVS):** When multiple dependency paths request different versions of the same package (a "diamond dependency"), Pipelex selects the minimum version that satisfies all constraints simultaneously. This provides deterministic, reproducible builds.--**Cycle detection:** Circular dependencies (A depends on B, B depends on A) are detected during resolution and raise an error immediately.--**Local path dependencies are not recursed:** If a dependency has a `path` field, its own sub-dependencies are not resolved transitively. Only remote dependencies participate in transitive resolution.--### Package Cache--Fetched remote packages are stored in a local cache at:--```-~/.mthds/packages/{address}/{version}/-```--For example:--```-~/.mthds/packages/github.com/acme/scoring-lib/2.0.0/-```--- The `.git/` directory is stripped from cached copies to save space.-- Writes use a staging directory with atomic rename for safety.-- The cache is shared across all your projects — a package fetched for one project is available to all others.--## Exports and Visibility--The `[exports]` section controls which pipes are visible to other domains. This is the core access-control mechanism of the package system.--### Default Behavior--- **Without `METHODS.toml`**: all pipes are public. Any domain can reference any pipe.-- **With `METHODS.toml`**: pipes are **private by default**. Only pipes listed in `[exports]` (and `main_pipe` entries) are accessible from other domains.--### Declaring Exports--Exports are organized by domain path. Each entry lists the pipes that domain exposes:--```toml-[exports.legal.contracts]-pipes = ["extract_clause", "analyze_contract"]--[exports.scoring]-pipes = ["compute_weighted_score"]-```--In this example, the `legal.contracts` domain exports two pipes, and the `scoring` domain exports one.--### Visibility Rules--| Reference Type | Visibility Check |-|----------------|-----------------|-| Bare reference (no domain prefix) | Always allowed |-| Same-domain reference | Always allowed |-| Cross-domain to exported pipe | Allowed |-| Cross-domain to `main_pipe` | Allowed (auto-exported) |-| Cross-domain to non-exported pipe | **Blocked** |--!!! important- A bundle's `main_pipe` is **automatically exported** — it is always accessible from other domains, even if it is not listed in the `[exports]` section.--!!! note "Actionable Error Messages"- Visibility violations are detected at load time. When a pipe reference is blocked, the error message tells you exactly which pipe is inaccessible and suggests adding it to the appropriate `[exports]` section in `METHODS.toml`.--### Example--Given two bundles:--```toml-# contracts.mthds-domain = "legal.contracts"-main_pipe = "review_contract"--[pipe.extract_clause]-# ...--[pipe.analyze_contract]-# ...--[pipe.internal_helper]-# ...-```--```toml-# scoring.mthds-domain = "scoring"--[pipe.compute_weighted_score]-# ...-```--And this manifest:--```toml-[exports.legal.contracts]-pipes = ["extract_clause", "analyze_contract"]-```--Then from a different domain (e.g. `reporting`):--- `legal.contracts.extract_clause` — allowed (exported)-- `legal.contracts.analyze_contract` — allowed (exported)-- `legal.contracts.review_contract` — allowed (auto-exported as `main_pipe`)-- `legal.contracts.internal_helper` — **blocked** (not exported)--## Package Directory Structure--A typical package layout:--```-your-project/-├── METHODS.toml # Package manifest-├── methods.lock # Lock file (commit to VCS)-├── my_project/-│ ├── finance/-│ │ ├── services.py-│ │ ├── invoices.mthds-│ │ └── invoices_struct.py-│ └── legal/-│ ├── contracts.mthds-│ ├── contracts_struct.py-│ └── services.py-├── .pipelex/-│ └── pipelex.toml-└── requirements.txt-```--The `METHODS.toml` sits at the project root. Pipelex discovers it by walking up from any `.mthds` file until it finds the manifest (stopping at a `.git` boundary or filesystem root).--## Quick Start--**1. Scaffold a manifest** from your existing bundles:--```bash-pipelex pkg init-```--This scans all `.mthds` files in the current directory, discovers domains and pipes, and generates a skeleton `METHODS.toml` with placeholder values. Edit the generated file to set the correct address and tune your exports.--**2. Add a dependency:**--```bash-pipelex pkg add github.com/acme/scoring-lib --version "^2.0.0"-```--This appends a dependency entry to your `METHODS.toml`. The alias is auto-derived from the address (`scoring_lib`), or you can specify one with `--alias`.--**3. Lock your dependencies:**--```bash-pipelex pkg lock-```--This resolves all remote dependencies (including transitive ones), computes integrity hashes, and writes `methods.lock`.--**4. Install dependencies:**--```bash-pipelex pkg install-```--This fetches any packages not already cached and verifies their integrity.--**5. Inspect the current manifest:**--```bash-pipelex pkg list-```--This displays the package metadata, dependencies, and exports in formatted tables.--See the [Pkg CLI reference](../9-tools/cli/pkg.md) for full command details.--## Related Documentation--- [Domain](./domain.md) — How domains organize concepts and pipes-- [Libraries](./libraries.md) — How libraries load and validate bundles-- [Pipelex Bundle Specification](./pipelex-bundle-specification.md) — The `.mthds` file format-- [Refining Concepts](./concepts/refining-concepts.md) — How to specialize concepts, including cross-package refinement-- [Pkg CLI](../9-tools/cli/pkg.md) — CLI commands for package managementdiff --git a/docs/home/9-tools/cli/pkg.md b/docs/home/9-tools/cli/pkg.mddeleted file mode 100644index 9a5d922ae..000000000--- a/docs/home/9-tools/cli/pkg.md+++ /dev/null@@ -1,160 +0,0 @@-# Pkg Commands--Manage package manifests and dependencies for your Pipelex project.--## Pkg Init--```bash-pipelex pkg init-pipelex pkg init --force-```--Scans `.mthds` files in the current directory, discovers domains and pipes, and generates a skeleton `METHODS.toml` manifest.--The generated manifest includes:--- A placeholder `address` (edit this to your actual package address)-- Version set to `0.1.0`-- All discovered domains listed in the `[exports]` section with their pipes--**Options:**--| Option | Description |-|--------|-------------|-| `--force`, `-f` | Overwrite an existing `METHODS.toml` |--**Examples:**--```bash-# Generate a manifest from .mthds files-pipelex pkg init--# Overwrite an existing manifest-pipelex pkg init --force-```--!!! note- The command refuses to overwrite an existing `METHODS.toml` unless `--force` is specified. If no `.mthds` files are found in the current directory, the command exits with an error.--## Pkg List--```bash-pipelex pkg list-```--Finds the nearest `METHODS.toml` by walking up from the current directory and displays its contents in Rich-formatted tables:--- **Package** — address, version, description, authors, license, MTHDS version-- **Dependencies** — alias, address, and version constraint for each dependency-- **Exports** — domain path and exported pipe names--**Examples:**--```bash-# Display the package manifest-pipelex pkg list-```--!!! note- If no `METHODS.toml` is found in the current directory or any parent directory (up to the `.git` boundary), the command exits with an error and suggests running `pipelex pkg init`.--## Pkg Add--```bash-pipelex pkg add ADDRESS [OPTIONS]-```--Adds a dependency entry to the `METHODS.toml` in the current directory.--**Arguments:**--| Argument | Required | Description |-|----------|----------|-------------|-| `ADDRESS` | Yes | Package address (e.g. `github.com/org/repo`) |--**Options:**--| Option | Default | Description |-|--------|---------|-------------|-| `--alias`, `-a` | Auto-derived | Dependency alias (snake_case) |-| `--version`, `-v` | `0.1.0` | Version constraint |-| `--path`, `-p` | — | Local filesystem path to the dependency |--When no `--alias` is provided, the alias is automatically derived from the last segment of the address. For example, `github.com/acme/scoring-lib` produces the alias `scoring_lib` (hyphens and dots are replaced with underscores).--**Examples:**--```bash-# Add a remote dependency (alias auto-derived as "scoring_lib")-pipelex pkg add github.com/acme/scoring-lib --version "^2.0.0"--# Add with an explicit alias-pipelex pkg add github.com/acme/scoring-lib --alias scoring --version "^2.0.0"--# Add a local development dependency-pipelex pkg add github.com/acme/scoring-lib --version "2.0.0" --path "../scoring-lib"-```--!!! note- A `METHODS.toml` must already exist in the current directory. Run `pipelex pkg init` first if needed. The command also checks that the alias is unique — duplicate aliases are rejected.--## Pkg Lock--```bash-pipelex pkg lock-```--Resolves all remote dependencies (including transitive ones) and generates a `methods.lock` file next to `METHODS.toml`. The lock file records the exact version, SHA-256 integrity hash, and source URL for each resolved package.--Local path dependencies are skipped — they are resolved from the filesystem and do not appear in the lock file.--**Examples:**--```bash-# Resolve dependencies and write the lock file-pipelex pkg lock-```--!!! note "Commit to Version Control"- You should commit `methods.lock` to your repository so that every collaborator and CI run installs the exact same dependency versions.--## Pkg Install--```bash-pipelex pkg install-```--Reads the `methods.lock` file and fetches any packages not already present in the local cache (`~/.mthds/packages/`). After fetching, it verifies the SHA-256 integrity of all cached packages against the lock file.--**Examples:**--```bash-# Install dependencies from the lock file-pipelex pkg install-```--!!! note- A `methods.lock` file must exist. Run `pipelex pkg lock` first to generate one. If a cached package's hash does not match the lock file, the command fails with an integrity error.--## Pkg Update--```bash-pipelex pkg update-```--Performs a **fresh resolve** of all dependencies — the existing `methods.lock` is ignored. After resolving, it rewrites the lock file and displays a diff showing added, removed, and updated packages.--**Examples:**--```bash-# Re-resolve all dependencies and update the lock file-pipelex pkg update-```--!!! tip- Use `pkg update` after changing version constraints in `METHODS.toml`. For day-to-day reproducible installs, use `pkg install` instead.--## Related Documentation--- [Packages](../../6-build-reliable-ai-workflows/packages.md) — Package system concepts, dependency workflow, and manifest reference-- [Validate](validate.md) — Validating pipelines and configurationdiff --git a/docs/index.md b/docs/index.mdindex 9e647675d..89dd717b0 100644--- a/docs/index.md+++ b/docs/index.md@@ -1,16 +1,17 @@---title: "What is Pipelex?"+description: "Pipelex is the open-source reference runtime for executable AI methods written in MTHDS. Build repeatable AI methods with typed concepts, focused pipes, and broad model support."---# What is Pipelex?-Pipelex is an open-source language that enables agents to build and run **repeatable AI methods**. Instead of cramming everything into one complex prompt, you break tasks into focused steps, each pipe handling one clear transformation.+Pipelex is the open-source reference runtime for **executable AI methods** written in MTHDS. Instead of cramming everything into one complex prompt, you break tasks into focused steps, each pipe handling one clear transformation.-Each pipe processes information using **Concepts** (typing with meaning) to ensure your pipelines make sense. The Pipelex language (`.mthds` files) is simple and human-readable, even for non-technical users.+Each pipe processes information using **Concepts** (typing with meaning) to keep method inputs and outputs explicit. MTHDS (`.mthds` files) is a human-readable format for defining those methods, and Pipelex validates and runs them.-Each step can be structured and validated, so you benefit from the reliability of software, and the intelligence of AI.+Each step can be structured and validated, so you get the reliability of software and the flexibility of AI.---@@ -55,8 +56,9 @@ Pipelex solves these problems by:Ready to get started?-- [:material-rocket-launch: Get Started](./home/2-get-started/write-methods-manually.md){ .md-button .md-button--primary }-- [:material-book-open: Read the Know-How Graph](./home/3-understand-pipelex/viewpoint.md){ .md-button }+- [:material-rocket-launch: Get Started](./get-started/write-methods-manually.md){ .md-button .md-button--primary }+- [:material-shape-outline: Learn MTHDS](./features/mthds-language.md){ .md-button }+- [:material-book-open: Read the Know-How Graph](./viewpoint/viewpoint.md){ .md-button }**Explore Examples:**diff --git a/docs/license.md b/docs/license.mdindex 3ddc5d7b5..fdf562b5d 100644--- a/docs/license.md+++ b/docs/license.md@@ -1,5 +1,6 @@---title: License+description: "Pipelex license — MIT-licensed open-source runtime for the Methods standard, maintained by Evotis S.A.S."hide:- feedback---diff --git a/docs/overrides/404.html b/docs/overrides/404.htmlnew file mode 100644index 000000000..e3f25f51b--- /dev/null+++ b/docs/overrides/404.html@@ -0,0 +1,13 @@+{% extends "main.html" %}++{% block extrahead %}+{{ super() }}+<meta name="robots" content="noindex, nofollow">+<link rel="canonical" href="{{ config.site_url }}">+{% endblock %}++{% block content %}+<h1>Page not found</h1>+<p>The page you requested does not exist in this documentation version.</p>+<p><a href="{{ config.site_url }}">Go to the latest docs</a></p>+{% endblock %}diff --git a/docs/overrides/main.html b/docs/overrides/main.htmlindex 5378d5f05..f68e4814e 100644--- a/docs/overrides/main.html+++ b/docs/overrides/main.html@@ -2,18 +2,50 @@{% extends "base.html" %}{% block extrahead %}-{{ super() }} {# keep anything Material already outputs #}-{% if page and page.title and page.meta %}-<meta property="og:type" content="article">-<meta property="og:title" content="{{ page.meta.title or page.title }}">-<meta property="og:description" content="{{ page.meta.description }}">-<meta property="og:image" content="{{ page.meta.image }}">+{{ super() }}+{% if page %}+{% set desc = page.meta.description if page.meta and page.meta.description else config.site_description %}+{% set title = page.meta.title if page.meta and page.meta.title else page.title %}+{% set img = page.meta.image if page.meta and page.meta.image else "https://d2cinlfp2qnig1.cloudfront.net/docs/pipelex_banner_1200x630.png?v=1" %}+{% set og_type = "website" if page.is_homepage or page.file.url in ('.', './', 'index.html') else "article" %}+<meta property="og:type" content="{{ og_type }}">+<meta property="og:site_name" content="{{ config.site_name }}">+<meta property="og:locale" content="en_US">+<meta property="og:title" content="{{ title }}">+<meta property="og:description" content="{{ desc }}">+<meta property="og:image" content="{{ img }}"><meta property="og:image:width" content="1200"><meta property="og:image:height" content="630"><meta property="og:url" content="{{ page.canonical_url }}"><meta name="twitter:card" content="summary_large_image">-<meta name="twitter:title" content="{{ page.meta.title or page.title }}">-<meta name="twitter:description" content="{{ page.meta.description }}">-<meta name="twitter:image" content="{{ page.meta.image }}">+<meta name="twitter:title" content="{{ title }}">+<meta name="twitter:description" content="{{ desc }}">+<meta name="twitter:image" content="{{ img }}">+{% if page.is_homepage or page.file.url in ('.', './', 'index.html') %}+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "WebSite",+ "name": "{{ config.site_name }}",+ "url": "{{ config.site_url }}",+ "description": "{{ config.site_description }}"+}+</script>+{% else %}+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "TechArticle",+ "headline": "{{ title }}",+ "description": "{{ desc }}",+ "url": "{{ page.canonical_url }}",+ "publisher": {+ "@type": "Organization",+ "name": "Pipelex",+ "url": "https://pipelex.com"+ }+}+</script>{% endif %}-{% endblock %}\ No newline at end of file+{% endif %}+{% endblock %}diff --git a/docs/robots.txt b/docs/robots.txtnew file mode 100644index 000000000..ae3b2691e--- /dev/null+++ b/docs/robots.txt@@ -0,0 +1,3 @@+User-agent: *+Allow: /+Sitemap: https://docs.pipelex.com/sitemap.xmldiff --git a/docs/home/5-setup/configure-ai-providers.md b/docs/setup/configure-ai-providers.mdsimilarity index 85%rename from docs/home/5-setup/configure-ai-providers.mdrename to docs/setup/configure-ai-providers.mdindex 1238cd1c8..8598db9d2 100644--- a/docs/home/5-setup/configure-ai-providers.md+++ b/docs/setup/configure-ai-providers.md@@ -1,3 +1,7 @@+---+description: "Set up API keys for OpenAI, Anthropic, Mistral, and other providers to power your Pipelex executable AI methods — or use the gateway for instant access."+---+# Configure AI Providers## Configure API Access@@ -102,7 +106,7 @@ When using your own keys, enable the corresponding backends:# Enable any providers you have keys for```-See [Inference Backend Configuration](../../home/7-configuration/config-technical/inference-backend-config.md) for all options.+See [Inference Backend Configuration](../configuration/config-technical/inference-backend-config.md) for all options.### Option 3: Local AI (No API Keys Required)@@ -127,7 +131,7 @@ Run AI models locally without any API keys. This is perfect if you:- **LM Studio**: User-friendly local model interface- **llama.cpp**: Lightweight C++ inference-Configure these in `.pipelex/inference/backends.toml`. See our [Inference Backend Configuration](../../home/7-configuration/config-technical/inference-backend-config.md) for details.+Configure these in `.pipelex/inference/backends.toml`. See our [Inference Backend Configuration](../configuration/config-technical/inference-backend-config.md) for details.---@@ -155,7 +159,7 @@ This creates a `.pipelex/` directory with:└── routing_profiles.toml # Model routing configuration```-Learn more in our [Inference Backend Configuration](../../home/7-configuration/config-technical/inference-backend-config.md) guide.+Learn more in our [Inference Backend Configuration](../configuration/config-technical/inference-backend-config.md) guide.---@@ -164,9 +168,9 @@ Learn more in our [Inference Backend Configuration](../../home/7-configuration/cNow that you have your backend configured:1. **Organize your project**: [Project Organization](./project-organization.md)-2. **Learn the concepts**: [Writing Methods Tutorial](../../home/2-get-started/write-methods-manually.md)+2. **Learn the concepts**: [Writing Methods Tutorial](../get-started/write-methods-manually.md)3. **Explore examples**: [Cookbook Repository](https://github.com/Pipelex/pipelex-cookbook/tree/main)-4. **Deep dive**: [Build Reliable AI Methods](../../home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md)+4. **Deep dive**: [Build Reliable AI Methods](../building-methods/kick-off-a-methods-project.md)!!! tip "Advanced Configuration"- For detailed backend configuration options, see [Inference Backend Configuration](../../home/7-configuration/config-technical/inference-backend-config.md).+ For detailed backend configuration options, see [Inference Backend Configuration](../configuration/config-technical/inference-backend-config.md).diff --git a/docs/setup/gateway-models.md b/docs/setup/gateway-models.mdnew file mode 100644index 000000000..45d9019ac--- /dev/null+++ b/docs/setup/gateway-models.md@@ -0,0 +1,7 @@+---+title: Gateway Available Models+description: "Browse every AI model available through the Pipelex gateway — from GPT and Claude to Gemini and open-source, ready for your executable AI methods."+---++--8<-- ".pipelex/inference/backends/pipelex_gateway_models.md"+diff --git a/docs/home/5-setup/index.md b/docs/setup/index.mdsimilarity index 66%rename from docs/home/5-setup/index.mdrename to docs/setup/index.mdindex 2051dd126..f8d7f04c0 100644--- a/docs/home/5-setup/index.md+++ b/docs/setup/index.md@@ -1,8 +1,13 @@+---+title: "Setup"+description: "Set up Pipelex for your first MTHDS methods project. Configure AI providers, organize `.mthds` files, and choose your project layout."+---+# Setup (first run)This section is for **first-time onboarding**: the key choices you need to make to get a project running quickly and safely.-If you already have a project running and want to tune behavior, jump to [Configuration (TOML reference)](../7-configuration/index.md).+If you already have a project running and want to tune behavior, jump to [Configuration (TOML reference)](../configuration/index.md).## What belongs where?@@ -11,9 +16,9 @@ If you already have a project running and want to tune behavior, jump to [Config## Quick guide-- **Need to run pipelines with LLMs?** Start with [Configure AI Providers](./configure-ai-providers.md).+- **Need to run methods with LLMs?** Start with [Configure AI Providers](./configure-ai-providers.md).- **Need a recommended repo layout for `.mthds` and Python code?** See [Project Organization](./project-organization.md).- **Need to understand telemetry and privacy trade-offs?** See [Telemetry](./telemetry.md).-- **Ready to tune the knobs?** Go to [Configuration Overview](../7-configuration/index.md).+- **Ready to tune the knobs?** Go to [Configuration Overview](../configuration/index.md).diff --git a/docs/home/5-setup/project-organization.md b/docs/setup/project-organization.mdsimilarity index 71%rename from docs/home/5-setup/project-organization.mdrename to docs/setup/project-organization.mdindex a4ab6fe79..e30754050 100644--- a/docs/home/5-setup/project-organization.md+++ b/docs/setup/project-organization.md@@ -1,3 +1,7 @@+---+description: "Learn how to structure your Pipelex project so that .mthds files, Python code, and executable AI methods stay organized and easy to maintain."+---+# Project Organization## Overview@@ -24,7 +28,7 @@ your_project/└── requirements.txt```-- **Package manifest**: `METHODS.toml` at your project root declares package identity and pipe visibility. See [Packages](../6-build-reliable-ai-workflows/packages.md) for details.+- **Package manifest**: `METHODS.toml` at your project root declares package identity and pipe visibility. See [Packages](../building-methods/packages.md) for details.## Alternative: Centralize pipelines@@ -38,7 +42,7 @@ your_project/└── pipelex.toml```-Learn more in our [Project Structure documentation](../../home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md).+Learn more in our [Project Structure documentation](../building-methods/kick-off-a-methods-project.md).---@@ -53,8 +57,8 @@ Learn more in our [Project Structure documentation](../../home/6-build-reliable-Now that you understand project organization:-1. **Start building**: [Get Started](../../home/2-get-started/write-methods-manually.md)-2. **Learn the concepts**: [Writing Methods Tutorial](../../home/2-get-started/write-methods-manually.md)+1. **Start building**: [Get Started](../get-started/write-methods-manually.md)+2. **Learn the concepts**: [Writing Methods Tutorial](../get-started/write-methods-manually.md)3. **Explore examples**: [Cookbook Repository](https://github.com/Pipelex/pipelex-cookbook/tree/main)-4. **Deep dive**: [Build Reliable AI Methods](../../home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md)+4. **Deep dive**: [Build Reliable AI Methods](../building-methods/kick-off-a-methods-project.md)diff --git a/docs/home/5-setup/telemetry.md b/docs/setup/telemetry.mdsimilarity index 94%rename from docs/home/5-setup/telemetry.mdrename to docs/setup/telemetry.mdindex 35622cac2..d84bc6845 100644--- a/docs/home/5-setup/telemetry.md+++ b/docs/setup/telemetry.md@@ -1,3 +1,7 @@+---+description: "Understand Pipelex telemetry options — what data is collected, how to opt out, and how privacy works for gateway and anonymous usage streams."+---+# TelemetryPipelex supports two independent telemetry streams that serve different purposes. Understanding how they work helps you make informed decisions about data collection.@@ -101,6 +105,6 @@ We take your privacy seriously:- PostHog tracing includes privacy controls to redact sensitive content- All telemetry can be completely disabled-For detailed configuration options, see [Telemetry Configuration](../7-configuration/config-practical/telemetry-config.md).+For detailed configuration options, see [Telemetry Configuration](../configuration/config-practical/telemetry-config.md).For more information about our data practices, see our [Privacy Policy](https://go.pipelex.com/privacy-policy).diff --git a/docs/home/9-tools/cli/agent-cli.md b/docs/tools/cli/agent-cli.mdsimilarity index 89%rename from docs/home/9-tools/cli/agent-cli.mdrename to docs/tools/cli/agent-cli.mdindex 528d42e06..36f4834eb 100644--- a/docs/home/9-tools/cli/agent-cli.md+++ b/docs/tools/cli/agent-cli.md@@ -1,3 +1,7 @@+---+description: "Use the pipelex-agent CLI for machine-oriented JSON output — designed for AI agents, IDE extensions, and automation toolchains."+---+# Agent CLI (`pipelex-agent`)The `pipelex-agent` CLI is a machine-oriented companion to the main `pipelex` CLI. It is designed for programmatic consumption by AI agents, IDE extensions, and other automation tools. All output is structured JSON written to stdout (success) or stderr (error), with no Rich formatting or interactive prompts.@@ -91,25 +95,28 @@ These commands do not have subcommands:## Output Contract-Every command (except `fmt` and `lint`) returns structured JSON via one of two functions:+Every command (except `fmt` and `lint`) returns structured JSON.**Success** — written to stdout:```json{- "status": "success",- "data": { ... }+ "success": true,+ "target_dir": "/path/to/.pipelex",+ "backends_enabled": ["openai"]}```+Successful commands return the result object directly. They are not wrapped in a `status` or `data` envelope.+**Error** — written to stderr:```json{- "status": "error",+ "error": true,"error_type": "specific_error_type","message": "Human-readable description",- "domain": "input | config | runtime",+ "error_domain": "input","hint": "Suggested fix or next step","retryable": false}diff --git a/docs/home/9-tools/cli/build/index.md b/docs/tools/cli/build/index.mdsimilarity index 77%rename from docs/home/9-tools/cli/build/index.mdrename to docs/tools/cli/build/index.mdindex 99ec8f19b..cf6697b5f 100644--- a/docs/home/9-tools/cli/build/index.md+++ b/docs/tools/cli/build/index.md@@ -1,3 +1,7 @@+---+description: "Generate runner code, Pydantic structures, and JSON templates from your pipeline definitions using the Pipelex build commands."+---+# Build CommandsGenerate pipelines, runner code, Python structures, and JSON templates from natural language descriptions.diff --git a/docs/home/9-tools/cli/build/inputs.md b/docs/tools/cli/build/inputs.mdsimilarity index 92%rename from docs/home/9-tools/cli/build/inputs.mdrename to docs/tools/cli/build/inputs.mdindex b0bed3163..3c81149ee 100644--- a/docs/home/9-tools/cli/build/inputs.md+++ b/docs/tools/cli/build/inputs.md@@ -1,3 +1,7 @@+---+description: "Generate example input JSON for any pipe — see the expected input structure based on the pipe's declared input types in .mthds files."+---+# Build InputsGenerate example input JSON for a pipe, showing the expected input structure based on the pipe's input types.@@ -137,4 +141,4 @@ When an input has multiplicity (accepts multiple items), the content is wrapped- [Build Output](output.md) - Generate example output JSON for a pipe- [Build Runner](runner.md) - Generate Python code to run a pipe-- [Provide Inputs](../../../6-build-reliable-ai-workflows/pipes/provide-inputs.md) - Learn about input formats+- [Provide Inputs](../../../building-methods/pipes/provide-inputs.md) - Learn about input formatsdiff --git a/docs/home/9-tools/cli/build/output.md b/docs/tools/cli/build/output.mdsimilarity index 96%rename from docs/home/9-tools/cli/build/output.mdrename to docs/tools/cli/build/output.mdindex 44ae054af..b907bb4e1 100644--- a/docs/home/9-tools/cli/build/output.md+++ b/docs/tools/cli/build/output.md@@ -1,3 +1,7 @@+---+description: "Generate output representations for a pipe — preview expected output structure in JSON or JSON Schema for TypeScript/Zod integration."+---+# Build OutputGenerate output representation for a pipe, showing the expected output structure based on the pipe's output concept type. Supports multiple output formats including JSON Schema for TypeScript/Zod integration.@@ -251,4 +255,4 @@ This helps you understand all possible output structures that the pipe could ret- [Build Inputs](inputs.md) - Generate example input JSON for a pipe- [Build Runner](runner.md) - Generate Python code to run a pipe-- [Pipe Output](../../../6-build-reliable-ai-workflows/pipes/pipe-output.md) - Learn about pipe outputs+- [Pipe Output](../../../building-methods/pipes/pipe-output.md) - Learn about pipe outputsdiff --git a/docs/home/9-tools/cli/build/runner.md b/docs/tools/cli/build/runner.mdsimilarity index 91%rename from docs/home/9-tools/cli/build/runner.mdrename to docs/tools/cli/build/runner.mdindex 0d9d8c07b..9032d27e5 100644--- a/docs/home/9-tools/cli/build/runner.md+++ b/docs/tools/cli/build/runner.md@@ -1,3 +1,7 @@+---+description: "Generate ready-to-use Python code for running a pipe, complete with imports and example inputs from your .mthds bundles."+---+# Build RunnerGenerate Python code to run a pipe with all necessary imports and example inputs.@@ -81,7 +85,7 @@ The generated Python file includes:## Input Type Handling-- **Native concepts** (Text, Image, PDF, etc.) - Automatically generates appropriate content objects+- **Native concepts** (Text, Image, Document, etc.) - Automatically generates appropriate content objects- **Custom concepts** - Recursively generates the structure with example values- **Structured content** - Creates example data matching the concept's fieldsdiff --git a/docs/home/9-tools/cli/build/structures.md b/docs/tools/cli/build/structures.mdsimilarity index 91%rename from docs/home/9-tools/cli/build/structures.mdrename to docs/tools/cli/build/structures.mdindex cf5e6084d..f435dace2 100644--- a/docs/home/9-tools/cli/build/structures.md+++ b/docs/tools/cli/build/structures.md@@ -1,3 +1,7 @@+---+description: "Generate Pydantic models from concept definitions in your .mthds files — turn declarative types into Python code automatically."+---+# Build StructuresGenerate Pydantic models from your concept definitions.@@ -88,5 +92,5 @@ class CandidateProfile(StructuredContent):- [Build Runner](runner.md) - Generate Python runner scripts- [Build Inputs](inputs.md) - Generate example input JSON for a pipe- [Build Output](output.md) - Generate example output JSON for a pipe-- [Concepts](../../../6-build-reliable-ai-workflows/concepts/define_your_concepts.md) - Understanding concept definitions+- [Concepts](../../../building-methods/concepts/define_your_concepts.md) - Understanding concept definitionsdiff --git a/docs/home/9-tools/cli/index.md b/docs/tools/cli/index.mdsimilarity index 61%rename from docs/home/9-tools/cli/index.mdrename to docs/tools/cli/index.mdindex 4f950cb79..6b2c9b579 100644--- a/docs/home/9-tools/cli/index.md+++ b/docs/tools/cli/index.md@@ -1,6 +1,11 @@+---+title: "CLI Reference"+description: "Master the `pipelex` runtime CLI and understand where the `mthds` CLI fits for package manifest management."+---+# Pipelex CLI Documentation-The Pipelex CLI provides a command-line interface for managing and interacting with your Pipelex projects. This document outlines all available commands and their usage.+The `pipelex` CLI is the runtime and project-configuration CLI for Pipelex. Use it to initialize config, validate methods, run pipes, inspect the runtime state, and generate supporting files.## Overview@@ -13,7 +18,12 @@ The Pipelex CLI is organized into several command groups:| [**show**](show.md) | Inspect configuration, pipes, and AI models || [**run**](run.md) | Execute pipelines || [**build**](build/index.md) | Generate pipelines, runners, and structures |-| [**pkg**](pkg.md) | Package management: initialize manifests, manage dependencies, and lock versions |++## Related CLI Surface++Package manifest management currently lives in the `mthds` CLI:++- [**package**](pkg.md) — `mthds package init`, `mthds package list`, and `mthds package validate`## Usage Tips@@ -30,7 +40,7 @@ The Pipelex CLI is organized into several command groups:3. **Running Pipelines**- - Use `pipelex show pipes` to see available pipes+ - Use `pipelex show pipe --all` to see available pipes- Use `pipelex show pipe pipe_code` to inspect pipe details- Run with `pipelex run pipe pipe_code`, add the required inputs using `--inputs`@@ -42,6 +52,7 @@ The Pipelex CLI is organized into several command groups:## Related Documentation-- [Configure AI Providers](../../5-setup/configure-ai-providers.md) - Set up LLM backends-- [Design and Run Pipelines](../../6-build-reliable-ai-workflows/pipes/index.md) - Pipeline development guide+- [Configure AI Providers](../../setup/configure-ai-providers.md) - Set up LLM backends+- [Design and Run Pipelines](../../building-methods/pipes/index.md) - Pipeline development guide+- [Packages](../../building-methods/packages.md) - `METHODS.toml` manifests and exportsdiff --git a/docs/home/9-tools/cli/init.md b/docs/tools/cli/init.mdsimilarity index 62%rename from docs/home/9-tools/cli/init.mdrename to docs/tools/cli/init.mdindex 5c25b03ac..e2e2a4888 100644--- a/docs/home/9-tools/cli/init.md+++ b/docs/tools/cli/init.md@@ -1,14 +1,19 @@+---+description: "Initialize your Pipelex project configuration — create .pipelex directory structure, set up backends, and configure telemetry destinations."+---+# Init Commands-Initialize project configuration files in your project's `.pipelex` directory.+Initialize Pipelex configuration files and related setup flows.## Initialize Configuration```bashpipelex init [FOCUS]+pipelex init --local [FOCUS]```-Creates the `.pipelex` directory structure, copies default configuration files, and guides you through backend and telemetry setup.+By default, `pipelex init` writes to the global config directory at `~/.pipelex/`. Use `--local` to create a project-level `.pipelex/` directory at the detected project root. Credentials and Gateway service terms always remain in the global `~/.pipelex/` directory regardless of `--local`.!!! note "Config updates not yet supported"The `pipelex init` command always performs a full reset of the configuration. Incremental config updates will be supported in a future release.@@ -17,7 +22,9 @@ Creates the `.pipelex` directory structure, copies default configuration files,- `FOCUS` - What to initialize (optional):- `all` (default) - Initialize everything+ - `agreement` - Review or accept Pipelex Gateway terms- `config` - Only configuration files+ - `credentials` - Prompt for missing credentials only- `inference` - Only inference backend setup- `routing` - Only routing profile setup- `telemetry` - Only telemetry configuration@@ -25,22 +32,31 @@ Creates the `.pipelex` directory structure, copies default configuration files,**Examples:**```bash-# Initialize everything (recommended for first-time setup)+# Initialize global config (recommended for first-time setup)pipelex init+# Initialize project-local config+pipelex init --local+# Initialize only configuration filespipelex init config+# Prompt only for missing credentials+pipelex init credentials+# Reconfigure inference backendspipelex init inference# Reconfigure telemetry settingspipelex init telemetry++# Review gateway terms+pipelex init agreement```## What Gets Initialized-This command creates the `.pipelex/` directory with:+This command creates or resets a Pipelex config directory with:- **pipelex.toml** - Main configuration file for logging, reporting, etc.- **inference/** - AI backend and routing configuration@@ -52,11 +68,13 @@ This command creates the `.pipelex/` directory with:## Interactive Setup Flow-When you run `pipelex init`, you'll be guided through:+When you run `pipelex init`, Pipelex can guide you through:-1. **Backend Selection** - Choose which AI providers to enable (OpenAI, Anthropic, Mistral, Pipelex Gateway, etc.)-2. **Routing Configuration** - Set up how models are routed to backends-3. **Telemetry Setup** - Configure observability and analytics+1. **Config reset** - Recreate the selected config files+2. **Backend selection** - Choose which AI providers to enable+3. **Credential prompts** - Fill in missing keys when relevant+4. **Routing configuration** - Set up how models are routed to backends+5. **Telemetry setup** - Configure observability and analytics## Non-Interactive Init (`pipelex-agent init`)@@ -103,7 +121,7 @@ pipelex-agent init -g --config '{"backends": ["pipelex_gateway"], "accept_gatewa## Related Configuration-- [Configure AI Providers](../../5-setup/configure-ai-providers.md)-- [Inference Backend Configuration](../../7-configuration/config-technical/inference-backend-config.md)-- [Telemetry Configuration](../../7-configuration/config-practical/telemetry-config.md)+- [Configure AI Providers](../../setup/configure-ai-providers.md)+- [Inference Backend Configuration](../../configuration/config-technical/inference-backend-config.md)+- [Telemetry Configuration](../../configuration/config-practical/telemetry-config.md)diff --git a/docs/tools/cli/pkg.md b/docs/tools/cli/pkg.mdnew file mode 100644index 000000000..2850597e7--- /dev/null+++ b/docs/tools/cli/pkg.md@@ -0,0 +1,82 @@+---+title: "Package Commands"+description: "Manage `METHODS.toml` manifests with the `mthds package` CLI. Initialize, inspect, and validate package metadata for your MTHDS methods."+---++# Package Commands++Package manifest management is currently exposed through the `mthds` CLI, not the `pipelex` CLI.++Use these commands when you need to create, inspect, or validate a `METHODS.toml` file for a method package.++## Overview++```bash+mthds package init+mthds package list+mthds package validate+```++All three commands also accept `-C, --package-dir <path>` to target a package directory other than the current one.++## `mthds package init`++```bash+mthds package init+mthds package init -C ./my-package+```++Create a new `METHODS.toml` manifest interactively.++The command prompts for:++- package `address`+- `version`+- `description`+- optional `authors`+- optional `license`++It writes a manifest with package metadata and an empty `[exports]` section. If `METHODS.toml` already exists, the CLI asks whether to overwrite it.++## `mthds package list`++```bash+mthds package list+mthds package list -C ./my-package+```++Read and display the current `METHODS.toml` manifest from the target directory.++The output includes:++- package address, version, and description+- optional display name, authors, and license+- declared exports by domain++If no `METHODS.toml` exists in the target directory, the command reports an error and suggests running `mthds package init`.++## `mthds package validate`++```bash+mthds package validate+mthds package validate -C ./my-package+```++Validate the `METHODS.toml` manifest in the target directory.++This checks manifest syntax and package metadata fields, then reports the parsed manifest back on success.++## Current Scope++The public package-management commands currently documented in this repo are:++- `mthds package init`+- `mthds package list`+- `mthds package validate`++Older `pipelex pkg ...` examples and dependency-management commands such as `add`, `lock`, `install`, and `update` are not part of the current Python `pipelex` CLI surface and should not be used here.++## Related Documentation++- [Packages](../../building-methods/packages.md) — Package manifest concepts and `METHODS.toml` structure+- [CLI](index.md) — Runtime CLI vs `mthds` CLI overviewdiff --git a/docs/home/9-tools/cli/run.md b/docs/tools/cli/run.mdsimilarity index 93%rename from docs/home/9-tools/cli/run.mdrename to docs/tools/cli/run.mdindex a62e89969..b02333adc 100644--- a/docs/home/9-tools/cli/run.md+++ b/docs/tools/cli/run.md@@ -1,3 +1,7 @@+---+description: "Execute pipelines from your project library, .mthds bundle files, or installed method packages with optional inputs and outputs."+---+# Run CommandsExecute a pipeline with optional inputs and outputs.@@ -164,6 +168,6 @@ The output JSON contains the complete working memory after pipeline execution, i## Related Documentation-- [Executing Pipelines](../../6-build-reliable-ai-workflows/pipes/executing-pipelines.md)-- [Providing Inputs to Pipelines](../../6-build-reliable-ai-workflows/pipes/provide-inputs.md)-- [Design and Run Pipelines](../../6-build-reliable-ai-workflows/pipes/index.md)+- [Executing Pipelines](../../building-methods/pipes/executing-pipelines.md)+- [Providing Inputs to Pipelines](../../building-methods/pipes/provide-inputs.md)+- [Design and Run Pipelines](../../building-methods/pipes/index.md)diff --git a/docs/home/9-tools/cli/show.md b/docs/tools/cli/show.mdsimilarity index 87%rename from docs/home/9-tools/cli/show.mdrename to docs/tools/cli/show.mdindex 1b27f3c53..b0440eff8 100644--- a/docs/home/9-tools/cli/show.md+++ b/docs/tools/cli/show.md@@ -1,6 +1,10 @@+---+description: "Inspect your Pipelex configuration, browse pipeline definitions, and list available AI models directly from the command line."+---+# Show Commands-Inspect your Pipelex configuration, pipelines, and available AI models.+Inspect your Pipelex configuration, pipes, and available AI models.## Show Configuration@@ -23,7 +27,7 @@ pipelex show config## List All Pipes```bash-pipelex show pipes+pipelex show pipe --all```Lists all pipes discovered in your project and imported packages, showing their pipe codes and basic information.@@ -32,7 +36,7 @@ Lists all pipes discovered in your project and imported packages, showing their```bash# List all available pipes-pipelex show pipes+pipelex show pipe --all```This includes:@@ -121,7 +125,7 @@ pipelex show backends --all## Related Configuration-- [Inference Backend Configuration](../../7-configuration/config-technical/inference-backend-config.md)+- [Inference Backend Configuration](../../configuration/config-technical/inference-backend-config.md)- Backend configuration files: `.pipelex/inference/backends.toml`- Routing configuration: `.pipelex/inference/routing_profiles.toml`diff --git a/docs/home/9-tools/cli/validate.md b/docs/tools/cli/validate.mdsimilarity index 92%rename from docs/home/9-tools/cli/validate.mdrename to docs/tools/cli/validate.mdindex dd6b723db..f75cf7b3d 100644--- a/docs/home/9-tools/cli/validate.md+++ b/docs/tools/cli/validate.md@@ -1,3 +1,7 @@+---+description: "Validate your pipeline definitions, .mthds bundles, and installed method packages for correctness before running them in Pipelex."+---+# Validate CommandsValidate your pipeline definitions and configuration for correctness.@@ -121,4 +125,4 @@ All validation commands check:## Related Configuration-- [Dry Run Configuration](../../7-configuration/config-pipeline-validation/dry-run-config.md)+- [Dry Run Configuration](../../configuration/config-pipeline-validation/dry-run-config.md)diff --git a/docs/home/9-tools/logging.md b/docs/tools/logging.mdsimilarity index 88%rename from docs/home/9-tools/logging.mdrename to docs/tools/logging.mdindex bd39b04a8..a3c58ee67 100644--- a/docs/home/9-tools/logging.md+++ b/docs/tools/logging.md@@ -1,3 +1,8 @@+---+title: "Logging"+description: "Explore Pipelex logging: custom log levels, Rich console formatting, caller information, and structured data logging for debugging."+---+# Pipelex Logging System## Overview@@ -120,3 +125,8 @@ log.verbose("Detailed debug information")- Use `include_exception=True` for error context- Include relevant data in error logs- Use appropriate log levels for exceptions++## Related Documentation++- [Logging Configuration](../configuration/config-practical/logging-config.md) - Configure log behavior in `pipelex.toml`+- [CLI](./cli/index.md) - Commands that surface runtime logs during developmentdiff --git a/docs/home/9-tools/plxt.md b/docs/tools/plxt.mdsimilarity index 95%rename from docs/home/9-tools/plxt.mdrename to docs/tools/plxt.mdindex 56e0e63c6..6d955b2c5 100644--- a/docs/home/9-tools/plxt.md+++ b/docs/tools/plxt.md@@ -1,3 +1,7 @@+---+description: "Keep your TOML configuration and .mthds files consistently formatted with plxt, the fast linter and formatter for Pipelex projects."+---+# plxt (Formatter & Linter)## Overviewdiff --git a/docs/under-the-hood/architecture-overview.md b/docs/under-the-hood/architecture-overview.mdindex bfa93168c..0fbd67167 100644--- a/docs/under-the-hood/architecture-overview.md+++ b/docs/under-the-hood/architecture-overview.md@@ -1,10 +1,11 @@---title: "Architecture Overview"+description: "Understand the two-layer architecture behind Pipelex — how declarative .mthds files become executable AI methods at runtime."---# Architecture Overview-Pipelex is a Python framework for building and running **repeatable AI methods** using a declarative language (`.mthds` files).+Pipelex is a Python framework for building and running **executable AI methods** using a declarative language (`.mthds` files).---diff --git a/docs/under-the-hood/dry-run-mock-generation.md b/docs/under-the-hood/dry-run-mock-generation.mdindex 2615e2acd..06e45babb 100644--- a/docs/under-the-hood/dry-run-mock-generation.md+++ b/docs/under-the-hood/dry-run-mock-generation.md@@ -1,5 +1,6 @@---title: "Dry Run Mock Generation"+description: "Learn how Pipelex generates format-compliant mock data for dry runs — validating pipeline structure without calling inference APIs."---# Dry Run Mock Generationdiff --git a/docs/under-the-hood/execution-graph-tracing.md b/docs/under-the-hood/execution-graph-tracing.mdindex ba1482ec9..f98562ed5 100644--- a/docs/under-the-hood/execution-graph-tracing.md+++ b/docs/under-the-hood/execution-graph-tracing.md@@ -1,5 +1,6 @@---title: "Execution Graph Tracing"+description: "Capture pipeline executions as directed graphs for visualization and debugging — render with Mermaid or ReactFlow backends."---# Execution Graph Tracing@@ -29,7 +30,7 @@ Pipe Execution → GraphTracer → GraphSpec → Renderers → HTML/Mermaid| Scenario | CLI | API | Result ||----------|-----|-----|--------|-| Generate execution graph | `pipelex run my_pipe --graph` | `PipelexRunner(execution_config=...).execute_pipeline(...)` | GraphSpec JSON + HTML viewers |+| Generate execution graph | `pipelex run pipe my_pipe --graph` | `PipelexRunner(execution_config=...).execute_pipeline(...)` | GraphSpec JSON + HTML viewers || Force include full data | `--graph --graph-full-data` | `data_inclusion.stuff_json_content=True` | Data embedded in IOSpec || Force exclude data | `--graph --graph-no-data` | All `data_inclusion.*=False` | Previews only || Dry run with graph | `--dry-run --graph` | `dry_run_pipe_with_graph(pipe)` | Graph of mock execution |@@ -45,16 +46,16 @@ Pipe Execution → GraphTracer → GraphSpec → Renderers → HTML/Mermaid```bash# Run pipeline and generate graph-pipelex run my_pipe --graph+pipelex run pipe my_pipe --graph# Include full serialized data-pipelex run my_pipe --graph --graph-full-data+pipelex run pipe my_pipe --graph --graph-full-data# Exclude data (previews only)-pipelex run my_pipe --graph --graph-no-data+pipelex run pipe my_pipe --graph --graph-no-data# Dry run with graph tracing-pipelex run my_pipe --dry-run --graph --mock-inputs+pipelex run pipe my_pipe --dry-run --graph --mock-inputs```### APIdiff --git a/docs/under-the-hood/image-handling-in-llm-prompts.md b/docs/under-the-hood/image-handling-in-llm-prompts.mdindex 05ab93e98..a6fed66f9 100644--- a/docs/under-the-hood/image-handling-in-llm-prompts.md+++ b/docs/under-the-hood/image-handling-in-llm-prompts.md@@ -1,5 +1,6 @@---title: "Image Handling in LLM Prompts"+description: "How Pipelex routes images to LLM calls — a template-driven inclusion model where prompts control exactly which images are sent."---# Image Handling in LLM Prompts@@ -453,5 +454,5 @@ Pages:## Next Steps-- [:material-book-open: Learn about PipeLLM](../home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md){ .md-button }+- [:material-book-open: Learn about PipeLLM](../building-methods/pipes/pipe-operators/PipeLLM.md){ .md-button }- [:material-sitemap: Architecture Overview](./architecture-overview.md){ .md-button }diff --git a/docs/under-the-hood/index.md b/docs/under-the-hood/index.mdindex 975c1f308..d25894e1d 100644--- a/docs/under-the-hood/index.md+++ b/docs/under-the-hood/index.md@@ -1,5 +1,6 @@---title: "Under the Hood"+description: "Technical deep-dives into Pipelex internals — architecture, execution tracing, image handling, reasoning controls, and more."---# Under the Hooddiff --git a/docs/under-the-hood/init-cli-flows.md b/docs/under-the-hood/init-cli-flows.mdindex e298234ab..4e5cbfe3b 100644--- a/docs/under-the-hood/init-cli-flows.md+++ b/docs/under-the-hood/init-cli-flows.md@@ -1,5 +1,6 @@---title: "Init CLI Flows"+description: "Inside the pipelex init command — how focus-based dispatch sets up config files, backends, routing profiles, and telemetry independently."---# Init CLI Flowsdiff --git a/docs/under-the-hood/reasoning-controls.md b/docs/under-the-hood/reasoning-controls.mdindex f465f8dd8..306363cdc 100644--- a/docs/under-the-hood/reasoning-controls.md+++ b/docs/under-the-hood/reasoning-controls.md@@ -1,5 +1,6 @@---title: "Reasoning Controls"+description: "Control LLM reasoning effort and budget across providers — a unified abstraction for chain-of-thought and extended thinking."---# Reasoning Controlsdiff --git a/docs/under-the-hood/stuffartefact-and-image-rendering.md b/docs/under-the-hood/stuffartefact-and-image-rendering.mdindex dfa6c965a..fbfb77ec9 100644--- a/docs/under-the-hood/stuffartefact-and-image-rendering.md+++ b/docs/under-the-hood/stuffartefact-and-image-rendering.md@@ -1,5 +1,6 @@---title: "StuffArtefact & Image Rendering"+description: "How StuffArtefact enables Jinja2 template access to Stuff objects and the ImageRenderable protocol extracts images from nested content."---# StuffArtefact & Image Renderingdiff --git a/docs/under-the-hood/test-profile-configuration.md b/docs/under-the-hood/test-profile-configuration.mdindex fba003d7e..766be1bbb 100644--- a/docs/under-the-hood/test-profile-configuration.md+++ b/docs/under-the-hood/test-profile-configuration.md@@ -1,5 +1,6 @@---title: "Test Profile Configuration"+description: "Configure test profiles to control which AI models run in parametrized tests — iterate fast with small sets, then test comprehensively."---# Test Profile Configurationdiff --git a/docs/home/3-understand-pipelex/viewpoint.md b/docs/viewpoint/viewpoint.mdsimilarity index 98%rename from docs/home/3-understand-pipelex/viewpoint.mdrename to docs/viewpoint/viewpoint.mdindex e74002829..7712a0aee 100644--- a/docs/home/3-understand-pipelex/viewpoint.md+++ b/docs/viewpoint/viewpoint.md@@ -1,3 +1,7 @@+---+description: "Why AI agents need the MTHDS open standard — the Know-How Graph philosophy behind executable AI methods and the Pipelex runtime."+---+### This is our viewpoint, this is why we built [Pipelex](https://pipelex.com).Web version: https://knowhowgraph.com/diff --git a/mkdocs.yml b/mkdocs.ymlindex e12316443..74b4701bc 100644--- a/mkdocs.yml+++ b/mkdocs.yml@@ -1,11 +1,12 @@site_name: Pipelex Documentation-site_url: https://docs.pipelex.com/-site_description: "Official documentation for Pipelex, an open-source library/CLI for building and running deterministic, repeatable AI methods."+site_url: https://docs.pipelex.com/latest/+site_description: "Official documentation for Pipelex, an open-source library/CLI for building and running executable AI methods."docs_dir: docsrepo_url: "https://github.com/Pipelex/pipelex"repo_name: "Pipelex on GitHub"theme:name: material+ language: encustom_dir: docs/overridesfavicon: images/pipelex-favicon-32.pnglogo: https://pipelex-web.s3.amazonaws.com/logo/Pipelex-logo-wot-mono-560x176.png@@ -28,7 +29,7 @@ theme:icon: material/weather-sunnyname: Switch to light mode-copyright: "© 2025 Evotis S.A.S. <br/>Pipelex is a trademark of Evotis S.A.S."+copyright: "© 2025–2026 Evotis S.A.S. <br/>Pipelex is a trademark of Evotis S.A.S."extra:social:@@ -49,7 +50,111 @@ extra:provider: mikeplugins:- - search+ - search:+ separator: '[\s\-\.]+'+ - redirects:+ redirect_maps:+ 'home/1-features/advanced-customizations.md': 'features/advanced-customizations.md'+ 'home/1-features/claude-code-skills-plugin.md': 'features/claude-code-skills-plugin.md'+ 'home/1-features/cli.md': 'features/cli.md'+ 'home/1-features/cloud-storage.md': 'features/cloud-storage.md'+ 'home/1-features/concepts.md': 'features/concepts.md'+ 'home/1-features/configuration.md': 'features/configuration.md'+ 'home/1-features/cost-tracking.md': 'features/cost-tracking.md'+ 'home/1-features/document-extraction.md': 'features/document-extraction.md'+ 'home/1-features/execution-graph.md': 'features/execution-graph.md'+ 'home/1-features/gateway.md': 'features/gateway.md'+ 'home/1-features/image-generation.md': 'features/image-generation.md'+ 'home/1-features/index.md': 'features/index.md'+ 'home/1-features/llm-integration.md': 'features/llm-integration.md'+ 'home/1-features/mthds-language.md': 'features/mthds-language.md'+ 'home/1-features/pipe-operators.md': 'features/pipe-operators.md'+ 'home/1-features/pipeline-orchestration.md': 'features/pipeline-orchestration.md'+ 'home/1-features/plxt.md': 'features/plxt.md'+ 'home/1-features/telemetry.md': 'features/telemetry.md'+ 'home/1-features/validation-dry-run.md': 'features/validation-dry-run.md'+ 'home/1-features/web-search.md': 'features/web-search.md'+ 'home/10-advanced-customizations/content-generator-injection.md': 'advanced/content-generator-injection.md'+ 'home/10-advanced-customizations/index.md': 'advanced/index.md'+ 'home/10-advanced-customizations/observer-provider-injection.md': 'advanced/observer-provider-injection.md'+ 'home/10-advanced-customizations/pipe-router-injection.md': 'advanced/pipe-router-injection.md'+ 'home/10-advanced-customizations/reporting-delegate-injection.md': 'advanced/reporting-delegate-injection.md'+ 'home/10-advanced-customizations/secrets-provider-injection.md': 'advanced/secrets-provider-injection.md'+ 'home/10-advanced-customizations/storage-provider-injection.md': 'advanced/storage-provider-injection.md'+ 'home/2-get-started/write-methods-manually.md': 'get-started/write-methods-manually.md'+ 'home/3-understand-pipelex/viewpoint.md': 'viewpoint/viewpoint.md'+ 'home/4-cookbook-examples/extract-dpe.md': 'cookbook/extract-dpe.md'+ 'home/4-cookbook-examples/extract-gantt.md': 'cookbook/extract-gantt.md'+ 'home/4-cookbook-examples/extract-generic.md': 'cookbook/extract-generic.md'+ 'home/4-cookbook-examples/extract-proof-of-purchase.md': 'cookbook/extract-proof-of-purchase.md'+ 'home/4-cookbook-examples/extract-table.md': 'cookbook/extract-table.md'+ 'home/4-cookbook-examples/hello-world.md': 'cookbook/hello-world.md'+ 'home/4-cookbook-examples/index.md': 'cookbook/index.md'+ 'home/4-cookbook-examples/invoice-extractor.md': 'cookbook/invoice-extractor.md'+ 'home/4-cookbook-examples/simple-ocr.md': 'cookbook/simple-ocr.md'+ 'home/4-cookbook-examples/write-tweet.md': 'cookbook/write-tweet.md'+ 'home/5-setup/configure-ai-providers.md': 'setup/configure-ai-providers.md'+ 'home/5-setup/gateway-models.md': 'setup/gateway-models.md'+ 'home/5-setup/index.md': 'setup/index.md'+ 'home/5-setup/project-organization.md': 'setup/project-organization.md'+ 'home/5-setup/telemetry.md': 'setup/telemetry.md'+ 'home/6-build-reliable-ai-workflows/adapt-to-llm-prompting-style-openai-anthropic-mistral.md': 'building-methods/adapt-to-llm-prompting-style-openai-anthropic-mistral.md'+ 'home/6-build-reliable-ai-workflows/concepts/define_your_concepts.md': 'building-methods/concepts/define_your_concepts.md'+ 'home/6-build-reliable-ai-workflows/concepts/inline-structures.md': 'building-methods/concepts/inline-structures.md'+ 'home/6-build-reliable-ai-workflows/concepts/native-concepts.md': 'building-methods/concepts/native-concepts.md'+ 'home/6-build-reliable-ai-workflows/concepts/python-classes.md': 'building-methods/concepts/python-classes.md'+ 'home/6-build-reliable-ai-workflows/concepts/refining-concepts.md': 'building-methods/concepts/refining-concepts.md'+ 'home/6-build-reliable-ai-workflows/configure-ai-llm-to-optimize-methods.md': 'building-methods/configure-ai-llm-to-optimize-methods.md'+ 'home/6-build-reliable-ai-workflows/domain.md': 'building-methods/domain.md'+ 'home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md': 'building-methods/kick-off-a-methods-project.md'+ 'home/6-build-reliable-ai-workflows/libraries.md': 'building-methods/libraries.md'+ 'home/6-build-reliable-ai-workflows/llm-structured-generation-config.md': 'building-methods/llm-structured-generation-config.md'+ 'home/6-build-reliable-ai-workflows/packages.md': 'building-methods/packages.md'+ 'home/6-build-reliable-ai-workflows/pipelex-bundle-specification.md': 'building-methods/pipelex-bundle-specification.md'+ 'home/6-build-reliable-ai-workflows/pipes/executing-pipelines.md': 'building-methods/pipes/executing-pipelines.md'+ 'home/6-build-reliable-ai-workflows/pipes/index.md': 'building-methods/pipes/index.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeBatch.md': 'building-methods/pipes/pipe-controllers/PipeBatch.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeCondition.md': 'building-methods/pipes/pipe-controllers/PipeCondition.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeParallel.md': 'building-methods/pipes/pipe-controllers/PipeParallel.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeSequence.md': 'building-methods/pipes/pipe-controllers/PipeSequence.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-controllers/index.md': 'building-methods/pipes/pipe-controllers/index.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeCompose.md': 'building-methods/pipes/pipe-operators/PipeCompose.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md': 'building-methods/pipes/pipe-operators/PipeExtract.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeFunc.md': 'building-methods/pipes/pipe-operators/PipeFunc.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeImgGen.md': 'building-methods/pipes/pipe-operators/PipeImgGen.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md': 'building-methods/pipes/pipe-operators/PipeLLM.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md': 'building-methods/pipes/pipe-operators/PipeSearch.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-operators/index.md': 'building-methods/pipes/pipe-operators/index.md'+ 'home/6-build-reliable-ai-workflows/pipes/pipe-output.md': 'building-methods/pipes/pipe-output.md'+ 'home/6-build-reliable-ai-workflows/pipes/provide-inputs.md': 'building-methods/pipes/provide-inputs.md'+ 'home/6-build-reliable-ai-workflows/pipes/understanding-multiplicity.md': 'building-methods/pipes/understanding-multiplicity.md'+ 'home/6-build-reliable-ai-workflows/pipes/working-memory.md': 'building-methods/pipes/working-memory.md'+ 'home/7-configuration/config-advanced/feature-config.md': 'configuration/config-advanced/feature-config.md'+ 'home/7-configuration/config-pipeline-validation/dry-run-config.md': 'configuration/config-pipeline-validation/dry-run-config.md'+ 'home/7-configuration/config-practical/logging-config.md': 'configuration/config-practical/logging-config.md'+ 'home/7-configuration/config-practical/pipe-run-config.md': 'configuration/config-practical/pipe-run-config.md'+ 'home/7-configuration/config-practical/reporting-config.md': 'configuration/config-practical/reporting-config.md'+ 'home/7-configuration/config-practical/telemetry-config.md': 'configuration/config-practical/telemetry-config.md'+ 'home/7-configuration/config-technical/aws-config.md': 'configuration/config-technical/aws-config.md'+ 'home/7-configuration/config-technical/cogt-config.md': 'configuration/config-technical/cogt-config.md'+ 'home/7-configuration/config-technical/inference-backend-config.md': 'configuration/config-technical/inference-backend-config.md'+ 'home/7-configuration/config-technical/library-config.md': 'configuration/config-technical/library-config.md'+ 'home/7-configuration/index.md': 'configuration/index.md'+ 'home/8-analytics/data-extraction.md': 'analytics/data-extraction.md'+ 'home/9-tools/cli/agent-cli.md': 'tools/cli/agent-cli.md'+ 'home/9-tools/cli/build/index.md': 'tools/cli/build/index.md'+ 'home/9-tools/cli/build/inputs.md': 'tools/cli/build/inputs.md'+ 'home/9-tools/cli/build/output.md': 'tools/cli/build/output.md'+ 'home/9-tools/cli/build/runner.md': 'tools/cli/build/runner.md'+ 'home/9-tools/cli/build/structures.md': 'tools/cli/build/structures.md'+ 'home/9-tools/cli/index.md': 'tools/cli/index.md'+ 'home/9-tools/cli/init.md': 'tools/cli/init.md'+ 'home/9-tools/cli/pkg.md': 'tools/cli/pkg.md'+ 'home/9-tools/cli/run.md': 'tools/cli/run.md'+ 'home/9-tools/cli/show.md': 'tools/cli/show.md'+ 'home/9-tools/cli/validate.md': 'tools/cli/validate.md'+ 'home/9-tools/logging.md': 'tools/logging.md'+ 'home/9-tools/plxt.md': 'tools/plxt.md'- meta-manager- glightbox:touchNavigation: true@@ -91,133 +196,133 @@ extra_css:nav:- Home:- What is Pipelex?: index.md- - Getting Started: home/2-get-started/write-methods-manually.md+ - Getting Started: get-started/write-methods-manually.md- Features:- - Overview: home/1-features/index.md+ - Overview: features/index.md- Declarative AI Methods:- - MTHDS Language: home/1-features/mthds-language.md- - Concepts & Structured Types: home/1-features/concepts.md- - Pipe Operators: home/1-features/pipe-operators.md- - Pipeline Orchestration: home/1-features/pipeline-orchestration.md+ - MTHDS Language: features/mthds-language.md+ - Concepts & Structured Types: features/concepts.md+ - Pipe Operators: features/pipe-operators.md+ - Pipeline Orchestration: features/pipeline-orchestration.md- AI Capabilities:- - Pipelex Gateway & Model Access: home/1-features/gateway.md- - LLM Integration: home/1-features/llm-integration.md- - Document Extraction: home/1-features/document-extraction.md- - Image Generation: home/1-features/image-generation.md- - Web Search: home/1-features/web-search.md+ - Pipelex Gateway & Model Access: features/gateway.md+ - LLM Integration: features/llm-integration.md+ - Document Extraction: features/document-extraction.md+ - Image Generation: features/image-generation.md+ - Web Search: features/web-search.md- Developer Tools:- - Claude Code Skills Plugin: home/1-features/claude-code-skills-plugin.md- - CLI: home/1-features/cli.md- - plxt Formatter & Linter: home/1-features/plxt.md- - Execution Graph Visualization: home/1-features/execution-graph.md+ - Claude Code Skills Plugin: features/claude-code-skills-plugin.md+ - CLI: features/cli.md+ - plxt Formatter & Linter: features/plxt.md+ - Execution Graph Visualization: features/execution-graph.md- Production & Operations:- - Validation & Dry Run: home/1-features/validation-dry-run.md- - Telemetry & Observability: home/1-features/telemetry.md- - Cloud Storage: home/1-features/cloud-storage.md- - Cost Tracking & Reporting: home/1-features/cost-tracking.md+ - Validation & Dry Run: features/validation-dry-run.md+ - Telemetry & Observability: features/telemetry.md+ - Cloud Storage: features/cloud-storage.md+ - Cost Tracking & Reporting: features/cost-tracking.md- Configuration & Extensibility:- - Configuration System: home/1-features/configuration.md- - Advanced Customizations: home/1-features/advanced-customizations.md+ - Configuration System: features/configuration.md+ - Advanced Customizations: features/advanced-customizations.md- Cookbook Examples:- - Overview: home/4-cookbook-examples/index.md- - Hello World: home/4-cookbook-examples/hello-world.md+ - Overview: cookbook/index.md+ - Hello World: cookbook/hello-world.md- Document Processing:- - Simple OCR: home/4-cookbook-examples/simple-ocr.md- - Generic Document Extraction: home/4-cookbook-examples/extract-generic.md- - Invoice Extractor: home/4-cookbook-examples/invoice-extractor.md- - Proof of Purchase Extraction: home/4-cookbook-examples/extract-proof-of-purchase.md+ - Simple OCR: cookbook/simple-ocr.md+ - Generic Document Extraction: cookbook/extract-generic.md+ - Invoice Extractor: cookbook/invoice-extractor.md+ - Proof of Purchase Extraction: cookbook/extract-proof-of-purchase.md- Graphical Extraction:- - Gantt Chart Extraction: home/4-cookbook-examples/extract-gantt.md- - Table Extraction from Image: home/4-cookbook-examples/extract-table.md- - DPE Extraction: home/4-cookbook-examples/extract-dpe.md+ - Gantt Chart Extraction: cookbook/extract-gantt.md+ - Table Extraction from Image: cookbook/extract-table.md+ - DPE Extraction: cookbook/extract-dpe.md- Text Generation:- - Tweet Optimizer (wip): home/4-cookbook-examples/write-tweet.md+ - Tweet Optimizer (wip): cookbook/write-tweet.md- Setup (first run):- - Overview: home/5-setup/index.md- - Configure AI Providers: home/5-setup/configure-ai-providers.md- - Gateway Available Models: home/5-setup/gateway-models.md- - Project Organization: home/5-setup/project-organization.md- - Telemetry: home/5-setup/telemetry.md+ - Overview: setup/index.md+ - Configure AI Providers: setup/configure-ai-providers.md+ - Gateway Available Models: setup/gateway-models.md+ - Project Organization: setup/project-organization.md+ - Telemetry: setup/telemetry.md- Build Reliable AI Methods:- - Kick off a Method Project: home/6-build-reliable-ai-workflows/kick-off-a-methods-project.md- - Pipelex Bundle Specification: home/6-build-reliable-ai-workflows/pipelex-bundle-specification.md- - Domain: home/6-build-reliable-ai-workflows/domain.md+ - Kick off a Method Project: building-methods/kick-off-a-methods-project.md+ - Pipelex Bundle Specification: building-methods/pipelex-bundle-specification.md+ - Domain: building-methods/domain.md- Concepts:- - Define Your Concepts: home/6-build-reliable-ai-workflows/concepts/define_your_concepts.md- - Inline structures: home/6-build-reliable-ai-workflows/concepts/inline-structures.md- - Python classes: home/6-build-reliable-ai-workflows/concepts/python-classes.md- - Native Concepts: home/6-build-reliable-ai-workflows/concepts/native-concepts.md- - Refining Concepts: home/6-build-reliable-ai-workflows/concepts/refining-concepts.md+ - Define Your Concepts: building-methods/concepts/define_your_concepts.md+ - Inline structures: building-methods/concepts/inline-structures.md+ - Python classes: building-methods/concepts/python-classes.md+ - Native Concepts: building-methods/concepts/native-concepts.md+ - Refining Concepts: building-methods/concepts/refining-concepts.md- Design and Run Methods:- - Overview: home/6-build-reliable-ai-workflows/pipes/index.md- - Libraries: home/6-build-reliable-ai-workflows/libraries.md- - Packages: home/6-build-reliable-ai-workflows/packages.md- - Executing Pipelines: home/6-build-reliable-ai-workflows/pipes/executing-pipelines.md- - Providing Inputs to Pipelines: home/6-build-reliable-ai-workflows/pipes/provide-inputs.md- - Working Memory: home/6-build-reliable-ai-workflows/pipes/working-memory.md- - Pipe Output: home/6-build-reliable-ai-workflows/pipes/pipe-output.md- - Understanding Multiplicity: home/6-build-reliable-ai-workflows/pipes/understanding-multiplicity.md+ - Overview: building-methods/pipes/index.md+ - Libraries: building-methods/libraries.md+ - Packages: building-methods/packages.md+ - Executing Pipelines: building-methods/pipes/executing-pipelines.md+ - Providing Inputs to Pipelines: building-methods/pipes/provide-inputs.md+ - Working Memory: building-methods/pipes/working-memory.md+ - Pipe Output: building-methods/pipes/pipe-output.md+ - Understanding Multiplicity: building-methods/pipes/understanding-multiplicity.md- Pipe Operators:- - Overview: home/6-build-reliable-ai-workflows/pipes/pipe-operators/index.md- - PipeLLM: home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeLLM.md- - PipeExtract: home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeExtract.md- - PipeImgGen: home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeImgGen.md- - PipeSearch: home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md- - PipeCompose: home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeCompose.md- - PipeFunc: home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeFunc.md+ - Overview: building-methods/pipes/pipe-operators/index.md+ - PipeLLM: building-methods/pipes/pipe-operators/PipeLLM.md+ - PipeExtract: building-methods/pipes/pipe-operators/PipeExtract.md+ - PipeImgGen: building-methods/pipes/pipe-operators/PipeImgGen.md+ - PipeSearch: building-methods/pipes/pipe-operators/PipeSearch.md+ - PipeCompose: building-methods/pipes/pipe-operators/PipeCompose.md+ - PipeFunc: building-methods/pipes/pipe-operators/PipeFunc.md- Pipe Controllers:- - Overview: home/6-build-reliable-ai-workflows/pipes/pipe-controllers/index.md- - PipeSequence: home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeSequence.md- - PipeParallel: home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeParallel.md- - PipeBatch: home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeBatch.md- - PipeCondition: home/6-build-reliable-ai-workflows/pipes/pipe-controllers/PipeCondition.md- - Optimize Cost & Quality: home/6-build-reliable-ai-workflows/configure-ai-llm-to-optimize-methods.md- - LLM Structured Generation: home/6-build-reliable-ai-workflows/llm-structured-generation-config.md- - LLM Prompting Style: home/6-build-reliable-ai-workflows/adapt-to-llm-prompting-style-openai-anthropic-mistral.md+ - Overview: building-methods/pipes/pipe-controllers/index.md+ - PipeSequence: building-methods/pipes/pipe-controllers/PipeSequence.md+ - PipeParallel: building-methods/pipes/pipe-controllers/PipeParallel.md+ - PipeBatch: building-methods/pipes/pipe-controllers/PipeBatch.md+ - PipeCondition: building-methods/pipes/pipe-controllers/PipeCondition.md+ - Optimize Cost & Quality: building-methods/configure-ai-llm-to-optimize-methods.md+ - LLM Structured Generation: building-methods/llm-structured-generation-config.md+ - LLM Prompting Style: building-methods/adapt-to-llm-prompting-style-openai-anthropic-mistral.md- Configuration (TOML reference):- - Overview: home/7-configuration/index.md+ - Overview: configuration/index.md- Pipeline Validation Configuration:- - Dry Run: home/7-configuration/config-pipeline-validation/dry-run-config.md+ - Dry Run: configuration/config-pipeline-validation/dry-run-config.md- Practical Configuration:- - Logging: home/7-configuration/config-practical/logging-config.md- - Pipe Run: home/7-configuration/config-practical/pipe-run-config.md- - Reporting: home/7-configuration/config-practical/reporting-config.md- - Telemetry: home/7-configuration/config-practical/telemetry-config.md+ - Logging: configuration/config-practical/logging-config.md+ - Pipe Run: configuration/config-practical/pipe-run-config.md+ - Reporting: configuration/config-practical/reporting-config.md+ - Telemetry: configuration/config-practical/telemetry-config.md- Technical Configuration:- - AWS: home/7-configuration/config-technical/aws-config.md- - Cogt: home/7-configuration/config-technical/cogt-config.md- - LLM Providers & Models: home/7-configuration/config-technical/inference-backend-config.md- - Library: home/7-configuration/config-technical/library-config.md- - Feature: home/7-configuration/config-advanced/feature-config.md+ - AWS: configuration/config-technical/aws-config.md+ - Cogt: configuration/config-technical/cogt-config.md+ - LLM Providers & Models: configuration/config-technical/inference-backend-config.md+ - Library: configuration/config-technical/library-config.md+ - Feature: configuration/config-advanced/feature-config.md- Analytics:- - Observer Data Extraction: home/8-analytics/data-extraction.md+ - Observer Data Extraction: analytics/data-extraction.md- Tools:- CLI:- - Overview: home/9-tools/cli/index.md- - Init: home/9-tools/cli/init.md- - Validate: home/9-tools/cli/validate.md- - Run: home/9-tools/cli/run.md- - Show: home/9-tools/cli/show.md- - Pkg: home/9-tools/cli/pkg.md+ - Overview: tools/cli/index.md+ - Init: tools/cli/init.md+ - Validate: tools/cli/validate.md+ - Run: tools/cli/run.md+ - Show: tools/cli/show.md+ - Pkg: tools/cli/pkg.md- Build:- - Overview: home/9-tools/cli/build/index.md- - Runner: home/9-tools/cli/build/runner.md- - Structures: home/9-tools/cli/build/structures.md- - Inputs: home/9-tools/cli/build/inputs.md- - Output: home/9-tools/cli/build/output.md- - Agent CLI: home/9-tools/cli/agent-cli.md- - plxt (Formatter & Linter): home/9-tools/plxt.md- - Logging: home/9-tools/logging.md+ - Overview: tools/cli/build/index.md+ - Runner: tools/cli/build/runner.md+ - Structures: tools/cli/build/structures.md+ - Inputs: tools/cli/build/inputs.md+ - Output: tools/cli/build/output.md+ - Agent CLI: tools/cli/agent-cli.md+ - plxt (Formatter & Linter): tools/plxt.md+ - Logging: tools/logging.md- Advanced Customizations:- - Overview: home/10-advanced-customizations/index.md- - Secrets Provider: home/10-advanced-customizations/secrets-provider-injection.md- - Reporting Delegate: home/10-advanced-customizations/reporting-delegate-injection.md- - Storage Provider: home/10-advanced-customizations/storage-provider-injection.md- - Observer: home/10-advanced-customizations/observer-provider-injection.md- - Content Generator: home/10-advanced-customizations/content-generator-injection.md- - Pipe Router: home/10-advanced-customizations/pipe-router-injection.md+ - Overview: advanced/index.md+ - Secrets Provider: advanced/secrets-provider-injection.md+ - Reporting Delegate: advanced/reporting-delegate-injection.md+ - Storage Provider: advanced/storage-provider-injection.md+ - Observer: advanced/observer-provider-injection.md+ - Content Generator: advanced/content-generator-injection.md+ - Pipe Router: advanced/pipe-router-injection.md- Viewpoint:- - The Know-How Graph: home/3-understand-pipelex/viewpoint.md+ - The Know-How Graph: viewpoint/viewpoint.md- Under the Hood:- Overview: under-the-hood/index.md- Architecture Overview: under-the-hood/architecture-overview.mddiff --git a/pipelex/core/concepts/structure_generation/generator.py b/pipelex/core/concepts/structure_generation/generator.pyindex 061435ec4..cbedb669b 100644--- a/pipelex/core/concepts/structure_generation/generator.py+++ b/pipelex/core/concepts/structure_generation/generator.py@@ -90,7 +90,7 @@ class StructureGenerator:"If you want to customize this structure:\n"" 1. Copy this file to your own module\n"" 2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file\n"- " and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)\n"+ " and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)\n"" 3. Make sure your custom class is importable and registered\n""\n""To regenerate: pipelex build structures <target_directory>\n"diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway.toml b/pipelex/kit/configs/inference/backends/pipelex_gateway.tomlindex bca075b7c..5b02901ee 100644--- a/pipelex/kit/configs/inference/backends/pipelex_gateway.toml+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway.toml@@ -30,7 +30,7 @@# with direct provider backends (openai, anthropic, etc.) instead.## Documentation:-# https://docs.pipelex.com/home/7-configuration/config-technical/inference-backend-config/+# https://docs.pipelex.com/latest/configuration/config-technical/inference-backend-config/# Support: https://go.pipelex.com/discord#################################################################################diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.mdindex 8b0e2adc8..93433838b 100644--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md@@ -1,6 +1,6 @@# Pipelex Gateway — Available ModelsThis file lists the LLMs, document extraction models, and image generation models currently available through Pipelex Gateway.-For configuration details, see the [documentation](https://docs.pipelex.com/latest/home/5-setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-for-getting-started).+For configuration details, see the [documentation](https://docs.pipelex.com/latest/setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-and-most-powerful-for-getting-started).## Language Models (LLM)diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.mdindex 4d38f25c9..3c9410327 100644--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md@@ -1,7 +1,7 @@# Pipelex Gateway — Available Models (Plain Text)This file lists the LLMs, document extraction models, and image generation models currently available through Pipelex Gateway.-For configuration details, see the [documentation](https://docs.pipelex.com/latest/home/5-setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-for-getting-started).+For configuration details, see the [documentation](https://docs.pipelex.com/latest/setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-and-most-powerful-for-getting-started).**Note:** This is the plain-text readable version. See `pipelex_gateway_models.md` for the HTML-styled version.diff --git a/pipelex/pipe_operators/extract/pipe_extract.py b/pipelex/pipe_operators/extract/pipe_extract.pyindex e4217c2e4..74a52b6f2 100644--- a/pipelex/pipe_operators/extract/pipe_extract.py+++ b/pipelex/pipe_operators/extract/pipe_extract.py@@ -57,7 +57,7 @@ class PipeExtract(PipeOperator[PipeExtractOutput]):@model_validator(mode="after")def validate_fields(self) -> Self:if self.image_stuff_name is None and self.document_stuff_name is None:- msg = "For PipeExtract you must provide either a document or an image or a concept that refines one of them"+ msg = "For PipeExtract you must provide either a Document or an Image or a concept that refines one of them"raise ValueError(msg)return selfdiff --git a/pipelex/pipe_operators/extract/pipe_extract_blueprint.py b/pipelex/pipe_operators/extract/pipe_extract_blueprint.pyindex 4a20fe06b..d569e573f 100644--- a/pipelex/pipe_operators/extract/pipe_extract_blueprint.py+++ b/pipelex/pipe_operators/extract/pipe_extract_blueprint.py@@ -19,7 +19,7 @@ class PipeExtractBlueprint(PipeBlueprint):def validate_inputs(self):nb_inputs = self.nb_inputsmsg = (- "Exactly one input must be provided for the PipeExtract, and it must be a pdf or an image or a concept that refines one of them."+ "Exactly one input must be provided for the PipeExtract, and it must be a Document or an Image or a concept that refines one of them."f"{nb_inputs} inputs were provided.")if self.inputs is None:diff --git a/pipelex/system/telemetry/telemetry_config.py b/pipelex/system/telemetry/telemetry_config.pyindex 548c1d8bb..d60ee2857 100644--- a/pipelex/system/telemetry/telemetry_config.py+++ b/pipelex/system/telemetry/telemetry_config.py@@ -141,8 +141,8 @@ class PipelexGatewayTelemetryConfig(BaseModel):provider backends (OpenAI, Anthropic, Azure, Bedrock, etc.) instead.See Also:- - docs/home/5-setup/telemetry.md: Overview of telemetry streams- - docs/home/7-configuration/config-practical/telemetry-config.md: Custom telemetry configuration+ - docs/setup/telemetry.md: Overview of telemetry streams+ - docs/configuration/config-practical/telemetry-config.md: Custom telemetry configuration"""model_config = ConfigDict(extra="forbid")diff --git a/pipelex/urls.py b/pipelex/urls.pyindex e00b280ce..14c4c3778 100644--- a/pipelex/urls.py+++ b/pipelex/urls.py@@ -8,11 +8,13 @@ class URLs:changelog = "https://docs.pipelex.com/latest/changelog/"discord = "https://go.pipelex.com/discord"privacy_policy = "https://go.pipelex.com/privacy-policy"- telemetry_docs = "https://docs.pipelex.com/latest/home/5-setup/telemetry/"- gateway_docs = "https://docs.pipelex.com/latest/home/5-setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-for-getting-started"- pipe_func_docs = "https://docs.pipelex.com/latest/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeFunc/"- backend_provider_docs = "https://docs.pipelex.com/latest/home/5-setup/configure-ai-providers/"- native_concepts_docs = "https://docs.pipelex.com/latest/home/6-build-reliable-ai-workflows/concepts/native-concepts/"+ telemetry_docs = "https://docs.pipelex.com/latest/setup/telemetry/"+ gateway_docs = (+ "https://docs.pipelex.com/latest/setup/configure-ai-providers/#option-1-pipelex-gateway-easiest-and-most-powerful-for-getting-started"+ )+ pipe_func_docs = "https://docs.pipelex.com/latest/building-methods/pipes/pipe-operators/PipeFunc/"+ backend_provider_docs = "https://docs.pipelex.com/latest/setup/configure-ai-providers/"+ native_concepts_docs = "https://docs.pipelex.com/latest/building-methods/concepts/native-concepts/"app_cli_auth = "https://app.pipelex.com/auth/cli"jpg_example_1 = "https://pipelex-pytest-assets.s3.eu-west-3.amazonaws.com/jpg_example_1.jpg"diff --git a/pyproject.toml b/pyproject.tomlindex 5039587f0..27e11ae14 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -79,6 +79,7 @@ docs = ["mkdocs-material>=9.6.14","mkdocs-meta-manager>=1.1.0","mike>=2.1.3",+ "mkdocs-redirects==1.2.2",]dev = [diff --git a/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__customer.py b/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__customer.pyindex b722d64c9..fea69271d 100644--- a/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__customer.py+++ b/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__customer.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__invoice.py b/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__invoice.pyindex 943274969..a727ed40e 100644--- a/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__invoice.py+++ b/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__invoice.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__line_item.py b/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__line_item.pyindex 1b1333162..5e29bc6db 100644--- a/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__line_item.py+++ b/tests/e2e/pipelex/concepts/nested_concepts/generated_models/nested_concepts_test__line_item.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_analysis.py b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_analysis.pyindex 588a1e206..289e3f698 100644--- a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_analysis.py+++ b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_analysis.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_question.py b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_question.pyindex 131392fdc..6adfc197d 100644--- a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_question.py+++ b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_question.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_sheet.py b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_sheet.pyindex 8b959acaf..244f1662b 100644--- a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_sheet.py+++ b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_itvw_sheet.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_job_requirements.py b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_job_requirements.pyindex 1e611255a..5660c7885 100644--- a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_job_requirements.py+++ b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_job_requirements.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_match_analysis.py b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_match_analysis.pyindex 735e1280e..edc20b9a4 100644--- a/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_match_analysis.py+++ b/tests/e2e/pipelex/pipes/pipe_operators/pipe_compose/cv_job_matching_match_analysis.py@@ -3,7 +3,7 @@If you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator.py b/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator.pyindex 180c2082c..c05e47a66 100644--- a/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator.py+++ b/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator.py@@ -30,7 +30,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -86,7 +86,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -128,7 +128,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -182,7 +182,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -218,7 +218,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -254,7 +254,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -291,7 +291,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -343,7 +343,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -385,7 +385,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -439,7 +439,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -494,7 +494,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -552,7 +552,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -616,7 +616,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -666,7 +666,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -712,7 +712,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -789,7 +789,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -851,7 +851,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -905,7 +905,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -958,7 +958,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -1005,7 +1005,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -1061,7 +1061,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_concept_refs.py b/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_concept_refs.pyindex fbbef723d..b09815666 100644--- a/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_concept_refs.py+++ b/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_concept_refs.py@@ -15,7 +15,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_escaping.py b/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_escaping.pyindex b7ca21a7e..d4fdbdfd1 100644--- a/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_escaping.py+++ b/tests/unit/pipelex/core/concepts/structure_generation/test_structure_generator_escaping.py@@ -40,7 +40,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -85,7 +85,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -130,7 +130,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -175,7 +175,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -220,7 +220,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -265,7 +265,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -311,7 +311,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -357,7 +357,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -405,7 +405,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -450,7 +450,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -501,7 +501,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -546,7 +546,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -591,7 +591,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>@@ -650,7 +650,7 @@ AUTOGENERATED CODE - DO NOT EDITIf you want to customize this structure:1. Copy this file to your own module2. Remove the 'structure' or 'refines' declaration from the concept in the MTHDS file- and declare it in inline mode (see https://docs.pipelex.com/home/6-build-reliable-ai-workflows/concepts/define_your_concepts/#basic-concept-definition)+ and declare it in inline mode (see https://docs.pipelex.com/latest/building-methods/concepts/define_your_concepts/#basic-concept-definition)3. Make sure your custom class is importable and registeredTo regenerate: pipelex build structures <target_directory>diff --git a/uv.lock b/uv.lockindex f20cf0f7a..3991145f9 100644--- a/uv.lock+++ b/uv.lock@@ -2290,6 +2290,18 @@ wheels = [{ url = "https://files.pythonhosted.org/packages/fc/5b/0a90ae6576cd7fa2593e7bdde4fa52fe4e79f5812b8f1ada001414aaaa54/mkdocs_meta_manager-1.1.0-py3-none-any.whl", hash = "sha256:bdd1b5e9403bcfe222720dcd93102e0f1df5befef9b40a6ff91ad67926528658", size = 3186, upload-time = "2025-01-20T21:58:02.314Z" },]+[[package]]+name = "mkdocs-redirects"+version = "1.2.2"+source = { registry = "https://pypi.org/simple" }+dependencies = [+ { name = "mkdocs" },+]+sdist = { url = "https://files.pythonhosted.org/packages/f1/a8/6d44a6cf07e969c7420cb36ab287b0669da636a2044de38a7d2208d5a758/mkdocs_redirects-1.2.2.tar.gz", hash = "sha256:3094981b42ffab29313c2c1b8ac3969861109f58b2dd58c45fc81cd44bfa0095", size = 7162, upload-time = "2024-11-07T14:57:21.109Z" }+wheels = [+ { url = "https://files.pythonhosted.org/packages/c4/ec/38443b1f2a3821bbcb24e46cd8ba979154417794d54baf949fefde1c2146/mkdocs_redirects-1.2.2-py3-none-any.whl", hash = "sha256:7dbfa5647b79a3589da4401403d69494bd1f4ad03b9c15136720367e1f340ed5", size = 6142, upload-time = "2024-11-07T14:57:19.143Z" },+]+[[package]]name = "moto"version = "5.1.22"@@ -3483,6 +3495,7 @@ docs = [{ name = "mkdocs-glightbox" },{ name = "mkdocs-material" },{ name = "mkdocs-meta-manager" },+ { name = "mkdocs-redirects" },]fal = [{ name = "fal-client" },@@ -3542,6 +3555,7 @@ requires-dist = [{ name = "mkdocs-glightbox", marker = "extra == 'docs'", specifier = ">=0.4.0" },{ name = "mkdocs-material", marker = "extra == 'docs'", specifier = ">=9.6.14" },{ name = "mkdocs-meta-manager", marker = "extra == 'docs'", specifier = ">=1.1.0" },+ { name = "mkdocs-redirects", marker = "extra == 'docs'", specifier = "==1.2.2" },{ name = "moto", extras = ["s3"], marker = "extra == 'dev'", specifier = ">=5.0.0" },{ name = "mthds", specifier = ">=0.1.1" },{ name = "mypy", marker = "extra == 'dev'", specifier = "==1.19.1" },