Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Go agentagenticaichatbotdsh-pluginembeddingsevaluationgenerative-aigolangknowledge-basellmmulti-tenantollamaopenaiquestion-answeringragrerankingsemantic-searchvector-searchwiki
docs: restructure the English and Chinese READMEs
wizardchen5d00985f7204
diff --git a/README.md b/README.mdindex 8b9ce408e..90c7cf47c 100644--- a/README.md+++ b/README.md@@ -1,78 +1,188 @@<p align="center">- <picture>- <img src="./docs/images/logo.png" alt="WeKnora Logo" height="120"/>- </picture>+ <img src="./docs/images/logo.png" alt="WeKnora Logo" height="120"/></p>+<h3 align="center">Turn documents into living knowledge — RAG, Agents and Auto-Wiki in one self-hostable framework</h3>+<p align="center">- <picture>- <a href="https://trendshift.io/repositories/15289" target="_blank">- <img src="https://trendshift.io/api/badge/repositories/15289" alt="Tencent/WeKnora | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>- </a>- </picture>+ <a href="https://trendshift.io/repositories/15289" target="_blank">+ <img src="https://trendshift.io/api/badge/repositories/15289" alt="Tencent/WeKnora | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>+ </a></p>+<p align="center">- <a href="https://weknora.weixin.qq.com" target="_blank">- <img alt="Official Website" src="https://img.shields.io/badge/Official Website-WeKnora-4e6b99">- </a>- <a href="https://chatbot.weixin.qq.com" target="_blank">- <img alt="WeChat Dialog Open Platform" src="https://img.shields.io/badge/WeChat Dialog Open Platform-5ac725">- </a>- <a href="https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd" target="_blank">- <img alt="Chrome Extension" src="https://img.shields.io/badge/Chrome Extension-WeKnora-4285F4">- </a>- <a href="https://clawhub.ai/lyingbug/weknora" target="_blank">- <img alt="ClawHub Skill" src="https://img.shields.io/badge/ClawHub Skill-WeKnora-ff6b35">- </a>- <a href="https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora" target="_blank">- <img alt="npm @wxg-prc-cpg/dsh-weknora" src="https://img.shields.io/npm/v/@wxg-prc-cpg/dsh-weknora?label=dsh-weknora">- </a>- <a href="https://github.com/Tencent/WeKnora/blob/main/LICENSE">- <img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License">- </a>- <a href="./CHANGELOG.md">- <img alt="Version" src="https://img.shields.io/badge/version-0.8.2-2e6cc4?labelColor=d4eaf7">- </a>+ <a href="https://weknora.weixin.qq.com" target="_blank"><img alt="Official Website" src="https://img.shields.io/badge/Official Website-WeKnora-4e6b99"></a>+ <a href="https://weknora.weixin.qq.com/docs/" target="_blank"><img alt="Documentation" src="https://img.shields.io/badge/Docs-weknora.weixin.qq.com-2e6cc4"></a>+ <a href="https://chatbot.weixin.qq.com" target="_blank"><img alt="WeChat Dialog Open Platform" src="https://img.shields.io/badge/WeChat Dialog Open Platform-5ac725"></a>+ <a href="https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd" target="_blank"><img alt="Chrome Extension" src="https://img.shields.io/badge/Chrome Extension-WeKnora-4285F4"></a>+ <a href="https://clawhub.ai/lyingbug/weknora" target="_blank"><img alt="ClawHub Skill" src="https://img.shields.io/badge/ClawHub Skill-WeKnora-ff6b35"></a>+ <a href="https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora" target="_blank"><img alt="npm @wxg-prc-cpg/dsh-weknora" src="https://img.shields.io/npm/v/@wxg-prc-cpg/dsh-weknora?label=dsh-weknora"></a>+ <a href="https://github.com/Tencent/WeKnora/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License"></a>+ <a href="./CHANGELOG.md"><img alt="Version" src="https://img.shields.io/badge/version-0.8.2-2e6cc4?labelColor=d4eaf7"></a></p><p align="center">-| <b>English</b> | <a href="./README_CN.md"><b>简体中文</b></a> | <a href="./README_JA.md"><b>日本語</b></a> | <a href="./README_KO.md"><b>한국어</b></a> |+ <b>English</b> | <a href="./README_CN.md">简体中文</a> | <a href="./README_JA.md">日本語</a> | <a href="./README_KO.md">한국어</a></p><p align="center">- <h4 align="center">-- [Overview](#-overview) • [Architecture](#-architecture) • [Key Features](#-key-features) • [Getting Started](#-getting-started) • [API Reference](#-api-reference) • [Developer Guide](#-developer-guide)-- </h4>+ <a href="#-overview">Overview</a> •+ <a href="#-quick-start">Quick Start</a> •+ <a href="#-whats-new">What's New</a> •+ <a href="#-features">Features</a> •+ <a href="#-clients-and-integrations">Clients</a> •+ <a href="#-documentation">Docs</a> •+ <a href="#-development">Development</a></p>-# 💡 WeKnora — Turn Documents into Living Knowledge with RAG, Agents and Auto-Wiki+---## 📌 Overview-[**WeKnora**](https://weknora.weixin.qq.com) is an open-source, LLM-powered knowledge framework built for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning.+[**WeKnora**](https://weknora.weixin.qq.com) is an open-source, LLM-powered knowledge framework built for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning. It turns scattered documents into a queryable, reasoning-capable, continuously evolving knowledge asset — and runs entirely on your own infrastructure.https://github.com/user-attachments/assets/19b28ce2-a62f-4f54-b289-c983576259bc-*2:25 · 1080p · English narration & captions.*+<p align="center"><sub>2:25 · 1080p · English narration & captions</sub></p>++WeKnora is organized around three core capabilities:++<table>+ <tr>+ <td width="33%" valign="top">+ <h4>💬 RAG Quick Q&A</h4>+ Fast, grounded answers over your knowledge bases for everyday lookups, with inline citations and stage-by-stage pipeline progress.+ </td>+ <td width="33%" valign="top">+ <h4>🤖 ReAct Agent</h4>+ Autonomously orchestrates retrieval, MCP tools, a <b>tenant skill catalog</b>, session-persistent <b>Docker / E2B / Cube sandboxes</b>, the user's own browser via <b>BrowserSkill</b>, and web search to handle complex multi-step tasks.+ </td>+ <td width="33%" valign="top">+ <h4>📖 Wiki Mode</h4>+ Agents distill raw documents into a self-maintaining, interlinked Markdown knowledge base with an interactive knowledge graph — plus manual editing, revision history and one-click rollback.+ </td>+ </tr>+</table>++Around that core:-It is organized around three core capabilities: **RAG-based Quick Q&A** for everyday lookups, a **ReAct Agent** that autonomously orchestrates retrieval, MCP tools, a **tenant skill catalog**, session-persistent **Docker / E2B / Cube sandboxes**, the user's own browser via **BrowserSkill** and web search to handle complex multi-step tasks, and a brand-new **Wiki Mode** in which agents distill raw documents into a self-maintaining, interlinked markdown knowledge base with an interactive knowledge graph, complete with manual editing, revision history and one-click rollback. **Cross-session long-term memory** remembers who you are and what you keep asking about. Knowledge curation is equally hands-on: a **tree-structured folder view** preserves the directory layout of uploads, and **chunk editing with revision history** lets retrieval chunks be edited, diffed and reverted like documents. Combined with multi-source ingestion (Feishu wiki / Feishu Drive / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / RSS, and growing), **website embed widgets** for publishing agents to external sites, a **built-in MCP Server** that publishes knowledge bases to Cursor, Claude and other AI tools, **scoped API keys with a principal model** for programmatic integrations, **multi-instance storage backends** per workspace for flexible data placement, 27 built-in model vendors backed by a generated model catalog (including LiteLLM), full Langfuse observability plus a **runtime task-queue dashboard with worker-pool governance**, **enterprise-ready multi-workspace RBAC** (4-tier role matrix + per-resource ownership + per-workspace audit log), and a fully self-hostable modular architecture, WeKnora turns scattered documents into a queryable, reasoning-capable, continuously evolving knowledge asset.+- **Remembers and curates** — **cross-session long-term memory** remembers who you are and what you keep asking about; a **tree-structured folder view** preserves upload directory layout; **chunk editing with revision history** lets retrieval chunks be edited, diffed and reverted like documents.+- **Ingests from anywhere** — auto-sync from Feishu wiki / Feishu Drive / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / RSS (and growing); 10+ document formats including PDF, Word, images, Excel and XMind; Office files parsed in-process with **anydoc**.+- **Answers everywhere** — IM channels such as WeCom, Feishu, Slack and Telegram; **website embed widgets** to publish agents on external sites; a **built-in MCP Server** that publishes knowledge bases to Cursor, Claude and other AI tools; **scoped API keys with a principal model** for programmatic integrations.+- **Works with your models** — 27 built-in model vendors backed by a generated model catalog, including OpenAI, DeepSeek, Qwen (Alibaba Cloud), Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, LiteLLM and Ollama.+- **Enterprise-ready** — **multi-workspace RBAC** (4-tier role matrix + per-resource ownership + per-workspace audit log), **multi-instance storage backends** per workspace, a **runtime task-queue dashboard with worker-pool governance**, and full **Langfuse** observability into agent reasoning, token usage and pipeline tracing.+- **Fully self-hostable** — a modular architecture where LLMs, vector databases and storage backends are all swappable, with local and private-cloud deployment for complete data sovereignty.-The framework supports auto-syncing knowledge from Feishu, Confluence, DingTalk Docs, GitLab, Tencent IMA, Notion, and Yuque (more data sources coming soon), handles 10+ document formats including PDF, Word, images, Excel and XMind, and can serve Q&A directly through IM channels like WeCom, Feishu, Slack, and Telegram. It is compatible with major LLM providers including OpenAI, DeepSeek, Qwen (Alibaba Cloud), Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, LiteLLM, and Ollama. Office files can be parsed in-process with **anydoc**. Its fully modular design allows swapping LLMs, vector databases, and storage backends, with support for local and private cloud deployment ensuring complete data sovereignty. WeKnora also integrates with **Langfuse** for comprehensive observability into agent reasoning, token usage, and pipeline tracing.+## 🚀 Quick Start+**Prerequisites:** [Docker](https://www.docker.com/), [Docker Compose](https://docs.docker.com/compose/) and [Git](https://git-scm.com/).++```bash+git clone https://github.com/Tencent/WeKnora.git+cd WeKnora+cp .env.example .env # Edit .env as needed, see comments in the file+docker compose pull # Pull the latest images+docker compose up -d # Start core services+```++Then open **http://localhost** and follow the onboarding guide. A guided walkthrough with sample data is in the [Quickstart](https://weknora.weixin.qq.com/docs/01-getting-started/03-quickstart).++> [!TIP]+> To use a local Ollama model, run `ollama serve > /dev/null 2>&1 &` first. For the Ollama embedding model name, `OLLAMA_BASE_URL`, and RAM notes, see [Configuration](https://weknora.weixin.qq.com/docs/01-getting-started/04-configuration).++| Service | URL |+|---------|-----|+| Web UI | `http://localhost` |+| Backend API | `http://localhost:8080` |+| Langfuse Tracing | `http://localhost:3000` |++### Optional services++Add `--profile` flags to enable additional components; multiple profiles can be combined.++| Profile | Adds |+|---------|------|+| _(default)_ | Core services |+| `full` | All features |+| `neo4j` | Knowledge Graph (Neo4j) |+| `minio` | Object Storage (MinIO) |+| `langfuse` | Tracing (Langfuse) |++```bash+docker compose --profile neo4j --profile minio pull+docker compose --profile neo4j --profile minio up -d+docker compose down # Stop services+```-## ✨ Latest Updates+### Upgrading-- **v0.8.2** — **Local Browser (BrowserSkill)**: agents drive the user's own Chrome / Edge through the open-source BrowserSkill extension, with a live task preview, pause / resume and hand-off for logins and CAPTCHAs; **built-in MCP Server** (per-workspace `/mcp/<endpoint_id>` endpoints over Streamable HTTP, each with its own token, knowledge-base scope, rate limit and tool groups; the Python `mcp-server/` is deprecated); a sidebar **Toolbox** for skills, MCP services and the browser connection; **conversation control** (append requirements to a running turn, fork from any earlier question, rewind in place with sandbox checkpoints, per-session reasoning effort); **artifacts library**; sandbox **interactive terminal** and **graphical desktop**; macOS **Lite host sandbox** with project folders; rebuilt **model catalog** (27 built-in vendors with generated context-window, max-output, reasoning and vision metadata); agent retrieval tools consolidated into `search_knowledge` / `read_document` / `list_documents`; Confluence and DingTalk Docs data sources; Bocha and Serply web search; Japanese UI; per-channel IM reply language; whitelist-only outbound mode. Breaking: DingTalk channels are Stream-only, and sandbox commands run as `root`. See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.8.0** — **Skill sandbox runtime** (session-persistent Docker / E2B / Cube backends with per-tenant network policy; Local host-process backend removed; Docker opt-in); **tenant skill catalog** (install from ClawHub / SkillHub / git / zip, per-sandbox snapshots, live progress, file browse/edit, personal and workspace env vars); **cross-session long-term memory** (profile / preference / fact / task / interest, auto-extract with confirm, `search_memory`); **in-process anydoc office parser**; official **DeepSeek Harness plugin** `@wxg-prc-cpg/dsh-weknora`; GitLab and Tencent IMA data sources; LiteLLM; Exa and Metaso web search; XMind parsing; chat artifacts, question outline and timestamps; context compaction and provider prompt-cache markers. Plus OIDC JWKS verification, optional complex passwords, document auto-tagging, and broad sandbox/security hardening. See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.7.2** — Launched the **official product documentation site** (VitePress; six sections, ~50 pages covering ~360 API endpoints and ~150 environment variables, with standalone Docker/Nginx deployment, quickstart sample data and a local MCP demo); **knowledge base folder tree** (upload paths stored as first-class data, browse/rename/re-file documents like a file manager); **chunk editing with revision history** (edit retrieval chunks in the UI, per-version diff and rollback, automatic reindexing, plus custom document metadata); **Wiki page revision history** (snapshots + line-level diff + one-click rollback + in-browser manual editing); **directly loadable file URLs** via `resource_urls=public` / `RESOURCE_URL_MODE` (third-party apps render images and files without a second authenticated proxy call); **Feishu Drive data source** and docx sync through the blocks API; batch document tagging; **MCP Server 1.1.x** (migrated to the mcp 2.x high-level API, official PyPI package `tencent-weknora-mcp`, new `create_knowledge_from_text` and `list_shared_knowledge_bases` for 29 tools total); AWS S3 default credential chain (IAM Role / IRSA); local HTML upload parsing; QQBot markdown replies; new PR CI checks for app / frontend / docreader / mcp-server. Plus large-scale router and `modelcontext` refactors, rerank and chunking quality work, and broad stability fixes. See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.7.1** — New **Yunzhijia (云之家) IM integration** (WebSocket + image messages + markdown replies); **Volcengine rerank** provider (with request batching) and **Zhipu AI web search** provider; **platform-scoped API keys** for control-plane automation (tenant management, system settings, runtime queues, audit logs); **per-KB activity audit trail**; FAQ management enhancements (filtering, tagging, export, import tracking); **Langfuse OTLP/OTel tracing** migration with W3C traceparent propagation; chat header actions with one-click **Markdown export** and wiki tool results in the references drawer; prompt-cache observability; session channel governance (admin-scoped IM/embed/API sessions); resilient Feishu large-wiki sync; and removal of the legacy Neo4j conversation-memory dependency. Plus broad slug-integrity, SSRF-transport, and state-sync hardening. See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.7.0** — Fine-grained **scoped API keys & principal model** (capability-level grants + per-KB restriction + API integration playground); **runtime task-queue observability dashboard & worker-pool governance** (per-stage pools + per-model concurrency governors + failed-task inspection/retry); **multi-instance storage backends** (multiple storage instances per workspace, per-KB binding, default instance); **session-scoped temporary attachments** (async image/doc parsing + combined limits); question & follow-up suggestions; stable resource registry with LLM-context alias compaction; `@Skill / @MCP` mentions with scoped agent runtime; mid-conversation MCP OAuth; QQBot & Lark (Feishu International) IM integration; Redis TLS; Requesty model provider + Keenable web search; tenantless provisioning & gated self-service workspaces; admin password reset; knowledge base duplicate flow; `weknora` CLI v0.10. Plus broad security hardening (SSRF, secret redaction, SQL validation, IDOR). See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.6.3** — Website embed widget & Integrations Center (secure-mode token exchange + rate limits); chat experience overhaul (citation popovers, RAG pipeline progress, streaming markdown); document multi-tag & batch reparse; Wiki folders & hierarchy navigation; RSS data source; MCP OAuth2; EPUB / MHTML parsing; agent model-readiness checks; model test debugger; session source filter; workspace deletion UI. See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.6.2** — Per-upload process configuration with upload-confirm dialog; document reparse with `process_config`; `weknora` CLI v0.9 (bundled Agent Skills, `session stop`, auth/profile harmonization); KB marquee multi-select; HNSW index for 1024-dim pgvector embeddings; chat resources store refactor; Langfuse-only tracing (Jaeger removed). See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.6.1** — Document parsing trace timeline (Langfuse-style span tree with stage-by-stage progress + stop-parse); OpenSearch vector store driver; declarative built-in models via YAML; system admin & consolidated platform settings + audit log; new-user onboarding guide; settings UI redesign; `weknora` CLI v0.7 / v0.8 (agent-first wire contract, NDJSON, `--dry-run`); OpenDataLoader + PaddleOCR-VL parsers; MCP server multi-transport (stdio / SSE / HTTP); per-model thinking-mode config; Tencent LKEAP rerank + native Gemini embeddings + MiniMax-M3. See [`CHANGELOG.md`](./CHANGELOG.md).-- **v0.6.0** — Workspace RBAC (4-tier role matrix `Owner` / `Admin` / `Contributor` / `Viewer` + per-KB ownership + per-workspace audit log), workspace member management & multi-workspace UX, self-service workspaces; `weknora` CLI v0.4 GA with `mcp serve`; KB retrieval fan-out across vector stores; AES-256-GCM credential encryption + docreader gRPC TLS + Token; Zhipu embedder + Huawei OBS; server-side user preferences; Go 1.26.0. See [`website-docs/03-features/01-tenant-auth.md`](./website-docs/03-features/01-tenant-auth.md) and [`CHANGELOG.md`](./CHANGELOG.md).+If you already have WeKnora running and downloaded a newer release:++```bash+# Set WEKNORA_VERSION in .env to the target release (e.g. 0.8.2), or keep latest+docker compose pull # Pull images matching WEKNORA_VERSION+docker compose up -d # Recreate containers with new images+```++> [!NOTE]+> `docker compose up -d` alone reuses locally cached images and may leave the UI version out of sync with the release you downloaded. Read the [upgrade notes](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#upgrade-notes) before moving from v0.8.0.++### Other ways to deploy++| Option | When to use it |+|--------|----------------|+| **Docker Compose** | The standard deployment above — all features, multi-service |+| **Kubernetes (Helm)** | Production clusters; chart lives in [`helm/`](./helm) |+| **Lite single binary** | Local or low-resource use with zero external dependencies (SQLite + in-memory queue); see [Lite vs. standard](./docs/LITE.md) |+| **Desktop app** | Lite runtime with a GUI, login-free start and a macOS host sandbox; not yet shipped as an installer — build from source |++All options, hardware requirements and deployment topologies: [Installation guide](https://weknora.weixin.qq.com/docs/01-getting-started/02-installation).++> [!WARNING]+> WeKnora ships with login authentication, but for production deployments we strongly recommend that you:+> - deploy it in an internal / private network rather than on the public internet;+> - avoid exposing the service directly to public networks, to prevent information leakage;+> - configure proper firewall rules and access controls for the deployment environment;+> - regularly update to the latest version for security patches and improvements.++## ✨ What's New++### v0.8.2 <sub>· 2026-09-24 · [release notes](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2)</sub>++Agents step outside the chat box: they can drive the browser on your computer, knowledge bases can be published to other AI tools as an MCP Server, and conversations become steerable mid-flight.++- 🌐 **[Local Browser (BrowserSkill)](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#local-browser)** — agents drive the user's own Chrome / Edge through the open-source BrowserSkill extension, with a live task preview, pause / resume and hand-off for logins and CAPTCHAs.+- 🔌 **[Built-in MCP Server](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#mcp-server)** — per-workspace `/mcp/<endpoint_id>` endpoints over Streamable HTTP, each with its own token, knowledge-base scope, rate limit and tool groups; the Python `mcp-server/` is deprecated.+- 🧭 **[Conversation control](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#conversation-control)** — append requirements to a running turn, fork from any earlier question, rewind in place with sandbox checkpoints, and pick reasoning effort per session; plus an **artifacts library**.+- 🖥️ **[Sandbox](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#sandbox)** — **interactive terminal** and **graphical desktop**; macOS **Lite host sandbox** with project folders; a sidebar **Toolbox** gathers skills, MCP services and the browser connection.+- 🧠 **[Models](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#models)** — rebuilt **model catalog** (27 built-in vendors with generated context-window, max-output, reasoning and vision metadata); agent retrieval tools consolidated into `search_knowledge` / `read_document` / `list_documents`.+- 📚 **[Knowledge & platform](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#knowledge)** — Confluence and DingTalk Docs data sources; Bocha and Serply web search; Japanese UI; per-channel IM reply language; whitelist-only outbound mode.++> [!IMPORTANT]+> **Breaking:** DingTalk channels are Stream-only, and sandbox commands run as `root`. See the [upgrade notes](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#upgrade-notes).++### v0.8.0 <sub>· [release notes](https://weknora.weixin.qq.com/docs/07-releases/v0.8.0)</sub>++- 🧪 **Skill sandbox runtime** — session-persistent Docker / E2B / Cube backends with per-tenant network policy; Local host-process backend removed; Docker opt-in.+- 📦 **Tenant skill catalog** — install from ClawHub / SkillHub / git / zip, per-sandbox snapshots, live progress, file browse/edit, personal and workspace env vars.+- 🧠 **Cross-session long-term memory** — profile / preference / fact / task / interest, auto-extract with confirm, `search_memory`.+- 📄 **Parsing & sources** — in-process **anydoc** office parser; GitLab and Tencent IMA data sources; XMind parsing.+- 🧩 **Ecosystem** — official **DeepSeek Harness plugin** `@wxg-prc-cpg/dsh-weknora`; LiteLLM; Exa and Metaso web search.+- 💬 **Chat** — chat artifacts, question outline and timestamps; context compaction and provider prompt-cache markers.+- 🔒 **Security** — OIDC JWKS verification, optional complex passwords, document auto-tagging, and broad sandbox/security hardening.++<details>+<summary><b>Earlier releases (v0.2.0 – v0.7.2)</b></summary>++<br/>++- **v0.7.2** — Launched the **official product documentation site** (VitePress; six sections, ~50 pages covering ~360 API endpoints and ~150 environment variables, with standalone Docker/Nginx deployment, quickstart sample data and a local MCP demo); **knowledge base folder tree** (upload paths stored as first-class data, browse/rename/re-file documents like a file manager); **chunk editing with revision history** (edit retrieval chunks in the UI, per-version diff and rollback, automatic reindexing, plus custom document metadata); **Wiki page revision history** (snapshots + line-level diff + one-click rollback + in-browser manual editing); **directly loadable file URLs** via `resource_urls=public` / `RESOURCE_URL_MODE` (third-party apps render images and files without a second authenticated proxy call); **Feishu Drive data source** and docx sync through the blocks API; batch document tagging; **MCP Server 1.1.x** (migrated to the mcp 2.x high-level API, official PyPI package `tencent-weknora-mcp`, new `create_knowledge_from_text` and `list_shared_knowledge_bases` for 29 tools total); AWS S3 default credential chain (IAM Role / IRSA); local HTML upload parsing; QQBot markdown replies; new PR CI checks for app / frontend / docreader / mcp-server. Plus large-scale router and `modelcontext` refactors, rerank and chunking quality work, and broad stability fixes.+- **v0.7.1** — New **Yunzhijia (云之家) IM integration** (WebSocket + image messages + markdown replies); **Volcengine rerank** provider (with request batching) and **Zhipu AI web search** provider; **platform-scoped API keys** for control-plane automation (tenant management, system settings, runtime queues, audit logs); **per-KB activity audit trail**; FAQ management enhancements (filtering, tagging, export, import tracking); **Langfuse OTLP/OTel tracing** migration with W3C traceparent propagation; chat header actions with one-click **Markdown export** and wiki tool results in the references drawer; prompt-cache observability; session channel governance (admin-scoped IM/embed/API sessions); resilient Feishu large-wiki sync; and removal of the legacy Neo4j conversation-memory dependency. Plus broad slug-integrity, SSRF-transport, and state-sync hardening.+- **v0.7.0** — Fine-grained **scoped API keys & principal model** (capability-level grants + per-KB restriction + API integration playground); **runtime task-queue observability dashboard & worker-pool governance** (per-stage pools + per-model concurrency governors + failed-task inspection/retry); **multi-instance storage backends** (multiple storage instances per workspace, per-KB binding, default instance); **session-scoped temporary attachments** (async image/doc parsing + combined limits); question & follow-up suggestions; stable resource registry with LLM-context alias compaction; `@Skill / @MCP` mentions with scoped agent runtime; mid-conversation MCP OAuth; QQBot & Lark (Feishu International) IM integration; Redis TLS; Requesty model provider + Keenable web search; tenantless provisioning & gated self-service workspaces; admin password reset; knowledge base duplicate flow; `weknora` CLI v0.10. Plus broad security hardening (SSRF, secret redaction, SQL validation, IDOR).+- **v0.6.3** — Website embed widget & Integrations Center (secure-mode token exchange + rate limits); chat experience overhaul (citation popovers, RAG pipeline progress, streaming markdown); document multi-tag & batch reparse; Wiki folders & hierarchy navigation; RSS data source; MCP OAuth2; EPUB / MHTML parsing; agent model-readiness checks; model test debugger; session source filter; workspace deletion UI.+- **v0.6.2** — Per-upload process configuration with upload-confirm dialog; document reparse with `process_config`; `weknora` CLI v0.9 (bundled Agent Skills, `session stop`, auth/profile harmonization); KB marquee multi-select; HNSW index for 1024-dim pgvector embeddings; chat resources store refactor; Langfuse-only tracing (Jaeger removed).+- **v0.6.1** — Document parsing trace timeline (Langfuse-style span tree with stage-by-stage progress + stop-parse); OpenSearch vector store driver; declarative built-in models via YAML; system admin & consolidated platform settings + audit log; new-user onboarding guide; settings UI redesign; `weknora` CLI v0.7 / v0.8 (agent-first wire contract, NDJSON, `--dry-run`); OpenDataLoader + PaddleOCR-VL parsers; MCP server multi-transport (stdio / SSE / HTTP); per-model thinking-mode config; Tencent LKEAP rerank + native Gemini embeddings + MiniMax-M3.+- **v0.6.0** — Workspace RBAC (4-tier role matrix `Owner` / `Admin` / `Contributor` / `Viewer` + per-KB ownership + per-workspace audit log), workspace member management & multi-workspace UX, self-service workspaces; `weknora` CLI v0.4 GA with `mcp serve`; KB retrieval fan-out across vector stores; AES-256-GCM credential encryption + docreader gRPC TLS + Token; Zhipu embedder + Huawei OBS; server-side user preferences; Go 1.26.0. See [Tenants & auth](https://weknora.weixin.qq.com/docs/03-features/01-tenant-auth).- **v0.5.2** — Wiki ingest scales to 40k-document KBs (task queue + DLQ); MCP human-in-the-loop tool approval; Anthropic / Apache Doris / Tencent VectorDB / KS3 / SearXNG backends; adaptive 3-tier chunking with live preview; global ⌘K command palette; Yuque connector + WeChat Mini Program; `weknora` CLI preview.- **v0.5.1** — Knowledge-base batch management; workspace-wide IM channels overview; session search + user-scoped pinning; unified Model / Web Search / MCP settings cards; per-agent LLM timeout; desktop workspace switching.- **v0.5.0** — Wiki Mode GA — agents auto-generate structured, interlinked Markdown wiki pages with a knowledge graph; wiki browser + visual graph in the UI.@@ -85,8 +195,11 @@ The framework supports auto-syncing knowledge from Feishu, Confluence, DingTalk- **v0.3.0** — Shared Space; Agent Skills + sandboxed execution; custom agents; Data Analyst agent; thinking mode; Bing / Google web search; API Key auth; Helm chart; Korean i18n; Qdrant.- **v0.2.0** — Agent Mode (ReACT); multi-type knowledge bases (FAQ + document); conversation strategy config; DuckDuckGo web search; MCP tool integration; new UI with agent mode switching; MQ async task management.+Full history: [`CHANGELOG.md`](./CHANGELOG.md).-## 📱 Interface Showcase+</details>++## 📸 Screenshots<table><tr>@@ -115,107 +228,100 @@ The framework supports auto-syncing knowledge from Feishu, Confluence, DingTalk## 🏗️ Architecture-+++A fully modular pipeline from document parsing, vectorization and retrieval to LLM inference — every component is swappable and extensible. Supports local / private-cloud deployment with full data sovereignty and a zero-barrier Web UI for quick onboarding. Deep dive: [Architecture overview](https://weknora.weixin.qq.com/docs/02-architecture/01-overview) · [RAG pipeline](https://weknora.weixin.qq.com/docs/02-architecture/04-rag-pipeline) · [Extension points](https://weknora.weixin.qq.com/docs/06-development/03-extension-points).-Fully modular pipeline from document parsing, vectorization, and retrieval to LLM inference — every component is swappable and extensible. Supports local / private cloud deployment with full data sovereignty and a zero-barrier Web UI for quick onboarding.+## 🧩 Features-## 🧩 Feature Overview+### Intelligent Conversation-**Intelligent Conversation**+<sub>Docs: [Agent](https://weknora.weixin.qq.com/docs/03-features/07-agent) · [Wiki](https://weknora.weixin.qq.com/docs/03-features/14-wiki) · [Skills & sandbox](https://weknora.weixin.qq.com/docs/03-features/22-skills-sandbox) · [Memory](https://weknora.weixin.qq.com/docs/03-features/23-memory) · [Chat experience](https://weknora.weixin.qq.com/docs/03-features/18-chat-experience)</sub>| Capability | Details ||------------|---------|| Intelligent Reasoning | ReACT progressive multi-step reasoning, autonomously orchestrating knowledge retrieval, MCP tools, skill sandboxes, the local browser, and web search || Quick Q&A | RAG-based Q&A over knowledge bases for fast and accurate answers |-| Wiki Mode | Agent-driven auto-generation of structured, interlinked markdown Wiki pages from raw documents; in-browser manual editing, page revision history, line-level diff and one-click rollback |-| Skill Catalog & Sandbox | Workspace skill catalog (ClawHub / SkillHub / git / zip) installed onto session-persistent Docker / E2B / Cube sandboxes; `shell_exec`, file tools, artifacts, per-config network policy; Local host-process backend removed; an interactive terminal and a browser-based graphical desktop beside the chat; the macOS desktop app runs sessions without a pinned sandbox in an OS sandbox (Seatbelt), bound to a chosen project folder or a dated temporary workspace |+| Wiki Mode | Agent-driven auto-generation of structured, interlinked Markdown Wiki pages from raw documents; in-browser manual editing, page revision history, line-level diff and one-click rollback |+| Skill Catalog & Sandbox | Workspace skill catalog (ClawHub / SkillHub / git / zip) installed onto session-persistent Docker / E2B / Cube sandboxes · `shell_exec`, file tools, artifacts, per-config network policy · interactive terminal and browser-based graphical desktop beside the chat · the macOS desktop app runs sessions without a pinned sandbox in an OS sandbox (Seatbelt), bound to a chosen project folder or a dated temporary workspace · Local host-process backend removed || Local Browser | Agents drive the user's own Chrome / Edge through the open-source BrowserSkill extension in a dedicated task window (open pages, click, fill forms, read content), with a live preview, pause / resume / end, and hand-off to the user for logins and CAPTCHAs || Conversation Control | Append requirements to a running turn, fork a conversation from any earlier question, rewind in place (resetting the sandbox workspace to the matching checkpoint), and choose reasoning effort per session || Artifacts Library | A sidebar page listing every generated file across conversations, with type filters, search, date grouping and version history || Long-term Memory | Cross-session memory (profile / preference / fact / task / interest) with auto-extract, user confirm, and on-demand `search_memory` |-| Tool Calling | Built-in tools, MCP tools (incl. OAuth2 remote services, mid-conversation OAuth), web search; `@Skill / @MCP` mentions to scope the agent runtime per turn; MCP tools are discovered and called on demand and can be enabled per tool |+| Tool Calling | Built-in tools, MCP tools (incl. OAuth2 remote services, mid-conversation OAuth), web search · `@Skill / @MCP` mentions scope the agent runtime per turn · MCP tools are discovered and called on demand and can be enabled per tool || Conversation Strategy | Online Prompt editing, retrieval threshold tuning, multi-turn context awareness, per-agent citation output toggle || Suggested Questions | Auto-generated question suggestions and after-answer follow-ups based on knowledge base content || Temporary Attachments | Session-scoped image / document uploads with async parsing for one-off Q&A, with a combined image + attachment limit || Citations & RAG Progress | Inline citation popovers and a references drawer (web / KB source distinction), shared markdown rendering, and stage-by-stage RAG pipeline progress in chat || Session Management | Filter and group sidebar sessions by source (Web / IM / Embed), with inline session-title rename |-**Knowledge Management**+### Knowledge Management++<sub>Docs: [Knowledge bases](https://weknora.weixin.qq.com/docs/03-features/02-knowledge-base) · [Parsing](https://weknora.weixin.qq.com/docs/03-features/03-document-parsing) · [Chunking](https://weknora.weixin.qq.com/docs/03-features/04-chunking) · [Retrieval](https://weknora.weixin.qq.com/docs/03-features/05-retrieval-engines) · [Knowledge graph](https://weknora.weixin.qq.com/docs/03-features/09-knowledge-graph) · [Data sources](https://weknora.weixin.qq.com/docs/03-features/10-datasource)</sub>| Capability | Details ||------------|---------|| Knowledge Base Types | FAQ / Document / Wiki with folder import, URL import, multi-tag management, and online entry || Folder Tree | Folder uploads keep their original directory structure, with a sidebar tree for browsing, folder rename, and re-filing documents into another folder |-| Chunk Editing & Revisions | Edit retrieval chunks directly in the UI with per-version snapshots, diff and one-click rollback, and automatic reindexing after an edit; generated questions can be added, edited, deleted and regenerated; custom document metadata supported |-| Per-Upload Process Config | Override parser, chunking, multimodal (VLM / ASR), graph extraction, and question generation per upload batch via upload-confirm dialog or `process_config` API; reparse with new settings |+| Chunk Editing & Revisions | Edit retrieval chunks directly in the UI with per-version snapshots, diff and one-click rollback, and automatic reindexing after an edit · generated questions can be added, edited, deleted and regenerated · custom document metadata |+| Per-Upload Process Config | Override parser, chunking, multimodal (VLM / ASR), graph extraction, and question generation per upload batch via the upload-confirm dialog or `process_config` API; reparse with new settings || Batch Reparse | Re-queue parsing for multiple documents at once with optional per-batch `process_config` |-| Data Source Import | Auto-sync from Feishu wiki / Feishu Drive / Lark / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / RSS feeds (more data sources coming soon); incremental and full sync |+| Data Source Import | Auto-sync from Feishu wiki / Feishu Drive / Lark / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / RSS feeds (more coming soon); incremental and full sync || Document Formats | PDF / Word / Txt / Markdown / HTML / EPUB / MHTML / Images / CSV / Excel / PPT / JSON / XMind || Auto-Tagging | After parse, pick matching tags from the knowledge base's existing set without creating tags or overwriting manual ones || Retrieval Strategies | BM25 sparse / Dense retrieval / GraphRAG / parent-child chunking / HNSW-accelerated pgvector (1024-dim) / multi-dimensional indexing |+| Knowledge Graph | Turns documents into a graph of relationships between passages, giving indexing and retrieval structured support for more relevant, broader results (requires Neo4j: start the `neo4j` profile and set `NEO4J_ENABLE=true`) || Batch Selection & Tagging | Marquee drag-select multiple documents in the KB list for batch reparse and batch tagging (common tags pre-selected) || E2E Testing | Full-pipeline visualization with recall hit rate, BLEU / ROUGE metric evaluation |-**Integrations & Extensions**+### Integrations & Extensions++<sub>Docs: [Models](https://weknora.weixin.qq.com/docs/03-features/06-models) · [MCP](https://weknora.weixin.qq.com/docs/03-features/08-mcp) · [Web search](https://weknora.weixin.qq.com/docs/03-features/11-web-search) · [IM](https://weknora.weixin.qq.com/docs/03-features/12-im-integration) · [Embed](https://weknora.weixin.qq.com/docs/03-features/13-embed-channel) · [Storage](https://weknora.weixin.qq.com/docs/03-features/19-storage-backends)</sub>| Capability | Details ||------------|---------|| LLMs | OpenAI / Azure OpenAI / Anthropic (Claude) / DeepSeek / Qwen (Alibaba Cloud) / Zhipu / Hunyuan / Doubao (Volcengine) / Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Requesty / LiteLLM / Ollama || Embeddings | Ollama / BGE / GTE / Zhipu / OpenAI-compatible APIs || Vector DBs | PostgreSQL (pgvector) / Elasticsearch / OpenSearch / Milvus / Weaviate / Qdrant / Apache Doris / Tencent VectorDB |-| Object Storage | Local / MinIO / AWS S3 (IAM Role / IRSA default credential chain) / Volcengine TOS / Alibaba Cloud OSS / Kingsoft Cloud KS3 / Huawei Cloud OBS; **multiple storage instances per workspace** with per-KB binding and a default instance |+| Object Storage | Local / Tencent Cloud COS / MinIO / AWS S3 (IAM Role / IRSA default credential chain) / Volcengine TOS / Alibaba Cloud OSS / Kingsoft Cloud KS3 / Huawei Cloud OBS · **multiple storage instances per workspace** with per-KB binding and a default instance || IM Channels | WeCom / Feishu / Lark (Feishu International) / QQBot / Slack / Telegram / DingTalk / Mattermost / WeChat / Yunzhijia || Website Embed | Publish agents via embed widget with domain allowlists, rate limits, and secure-mode token exchange || Web Search | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG / Keenable / Zhipu AI / Exa / Metaso / Bocha / Serply |-| API Integration | Scoped API keys (capability-level grants + per-KB restriction + throttled last-used tracking) with an API integration playground; MCP OAuth and embed sessions isolated per principal; `resource_urls=public` returns directly loadable file/image URLs, removing the second authenticated proxy call |+| API Integration | Scoped API keys (capability-level grants + per-KB restriction + throttled last-used tracking) with an API integration playground · MCP OAuth and embed sessions isolated per principal · `resource_urls=public` returns directly loadable file/image URLs, removing the second authenticated proxy call || MCP Server | Built in: publish per-workspace endpoints at `/mcp/<endpoint_id>` (Streamable HTTP), each with its own token, knowledge-base scope, rate limit and tool groups (retrieval, `ask`, Wiki, opt-in write tools); the Python `tencent-weknora-mcp` package is deprecated |-**Platform**+### Platform++<sub>Docs: [Tenants & auth](https://weknora.weixin.qq.com/docs/03-features/01-tenant-auth) · [Observability](https://weknora.weixin.qq.com/docs/03-features/16-observability) · [Platform admin](https://weknora.weixin.qq.com/docs/03-features/20-platform-admin) · [Async tasks](https://weknora.weixin.qq.com/docs/02-architecture/05-async-tasks)</sub>| Capability | Details ||------------|---------|| Deployment | Local / Docker / Kubernetes (Helm) with private and offline support |-| UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / Website Embed Widget / WeChat Mini Program; UI in Chinese / English / Japanese / Korean / Russian |+| UI | Web UI / RESTful API / CLI (`weknora`) / Chrome Extension / Website Embed Widget / WeChat Mini Program · UI in Chinese / English / Japanese / Korean / Russian || Access Control | Workspace RBAC with 4-tier role matrix (Owner / Admin / Contributor / Viewer), per-KB resource ownership, per-workspace audit log, invite-only workspaces, tenantless provisioning & gated self-service workspace creation, admin password reset (session revocation), cross-workspace superuser, scoped API keys |-| Security | AES-256-GCM at-rest encryption for API keys and MCP / data-source credentials with graceful key rotation; gRPC TLS + Token between app and docreader; Redis TLS; SSRF-safe HTTP client (data sources, URL import, redirect chains); secret redaction in responses; skill sandbox isolation (Docker opt-in / E2B / Cube) with per-config network policy; OIDC ID-token JWKS verification; optional complex-password policy; whitelist-only outbound mode (`SSRF_DNS_WHITELIST_ONLY`) |-| Observability | Integrated Langfuse (sole tracing backend) for ReAct loops, token tracking, tool calls, and pipeline tracing; built-in Langfuse-style document parsing trace timeline with stage-by-stage progress; system-admin runtime task-queue dashboard (queue depth, per-model concurrency, failed-task inspection & manual retry) |-| Task Management | MQ async tasks with per-stage worker-pool governance (core / post-process / enrichment / maintenance + elastic shared pool, plus an independent Wiki pool) and per-model background concurrency governors; automatic database migration on version upgrade |-| Model Management | Centralized config, declarative built-in models via YAML, per-knowledge-base model selection, per-model thinking-mode and embedding-dimension overrides, interactive model test debugger, multi-workspace built-in model sharing, WeKnora Cloud hosted models and parsing; a generated model catalog fills context window, max output, reasoning levels and vision support, with a resolved-call preview and per-model protocol override |--## 🧩 Chrome Extension--[**WeKnora Chrome Extension**](https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd) lets you capture web content directly into your WeKnora knowledge base. Select text, images, or entire pages in the browser and save them as knowledge entries with one click — no copy-paste or file upload needed.---## 📱 WeChat Mini Program--The [WeKnora Mini Program](./miniprogram/README.md) provides a lightweight mobile client for configuring WeKnora API access, selecting knowledge bases, importing URLs, and asking knowledge chat from WeChat.---## 🦞 ClawHub Skill--[**WeKnora ClawHub Skill**](https://clawhub.ai/lyingbug/weknora) is a WeKnora skill published on the ClawHub platform. Once installed, it enables document import (file / URL / Markdown), hybrid search (vector + keyword) across knowledge bases, and knowledge entry management — all through the WeKnora REST API.--- **Document Import** — Upload files, import web pages, or write Markdown knowledge via the agent-- **Hybrid Search** — Search within or across knowledge bases with vector + keyword retrieval-- **Knowledge Management** — List, browse, edit, and delete knowledge entries programmatically--## 🐋 DeepSeek Harness Plugin--[**`@wxg-prc-cpg/dsh-weknora`**](https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora) is the official [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (`dsh`) plugin ([docs](./packages/dsh-weknora/README.md)). The harness ships no retrieval, embedding or knowledge-base capability of its own, so the plugin gives a coding agent your documents: `dsh plugin --profile web add @wxg-prc-cpg/dsh-weknora`, point it at a deployment, and four read-only tools appear in the agent's tool set.--- **`weknora_search`** — hybrid retrieval returning source passages verbatim, each with a reusable `knowledge_id`-- **`weknora_read_document`** — one document's passages reassembled in order, with paging-- **`weknora_ask`** — WeKnora's own composed answer with citations, over the RAG or the ReAct pipeline-- **`weknora_list_knowledge_bases`** — knowledge base names and ids, so the agent can scope its own search--## ⌨️ Command-Line Interface--`weknora` is the official CLI for driving the API from a terminal or an AI-agent. It is **agent-first**: every command emits a stable JSON envelope by-default (with typed error codes mapped to exit codes), and `--format text`-renders for humans. It also serves a curated MCP tool surface-(`weknora mcp serve`) and ships bundled Agent Skills.+| Security | AES-256-GCM at-rest encryption for API keys and MCP / data-source credentials with graceful key rotation · gRPC TLS + Token between app and docreader · Redis TLS · SSRF-safe HTTP client (data sources, URL import, redirect chains) · secret redaction in responses · skill sandbox isolation (Docker opt-in / E2B / Cube) with per-config network policy · OIDC ID-token JWKS verification · optional complex-password policy · whitelist-only outbound mode (`SSRF_DNS_WHITELIST_ONLY`) |+| Observability | Integrated Langfuse (sole tracing backend) for ReAct loops, token tracking, tool calls, and pipeline tracing · built-in Langfuse-style document parsing trace timeline with stage-by-stage progress · system-admin runtime task-queue dashboard (queue depth, per-model concurrency, failed-task inspection & manual retry) |+| Task Management | MQ async tasks with per-stage worker-pool governance (core / post-process / enrichment / maintenance + elastic shared pool, plus an independent Wiki pool) and per-model background concurrency governors · automatic database migration on version upgrade |+| Model Management | Centralized config, declarative built-in models via YAML, per-knowledge-base model selection, per-model thinking-mode and embedding-dimension overrides, interactive model test debugger, multi-workspace built-in model sharing, WeKnora Cloud hosted models and parsing · a generated model catalog fills context window, max output, reasoning levels and vision support, with a resolved-call preview and per-model protocol override |++## 🔌 Clients and Integrations++| | Client | What it does |+|:-:|--------|--------------|+| ⌨️ | [**CLI `weknora`**](./cli/README.md) | Agent-first command line for the full API, with a curated MCP tool surface and bundled Agent Skills |+| 🔌 | [**Built-in MCP Server**](https://weknora.weixin.qq.com/docs/03-features/08-mcp) | Publishes knowledge bases to Cursor, Claude and other MCP clients |+| 🌐 | [**Local Browser (BrowserSkill)**](https://weknora.weixin.qq.com/docs/05-clients/09-local-browser) | Lets agents operate the user's own Chrome / Edge |+| 🧩 | [**Chrome Extension**](https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd) | Select text, images, or entire pages in the browser and save them as knowledge entries with one click — no copy-paste or file upload needed |+| 📱 | [**WeChat Mini Program**](./miniprogram/README.md) | Lightweight mobile client: configure API access, select knowledge bases, import URLs, and ask knowledge chat from WeChat |+| 🦞 | [**ClawHub Skill**](https://clawhub.ai/lyingbug/weknora) | A WeKnora skill on ClawHub for document import, hybrid search and knowledge management via the REST API |+| 🐋 | [**DeepSeek Harness plugin**](https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora) | Gives `dsh` coding agents read-only access to your documents |+| 🪟 | [**Website Embed Widget**](https://weknora.weixin.qq.com/docs/03-features/13-embed-channel) | Publishes agents on external sites |+| 🐹 | [**Go SDK**](https://weknora.weixin.qq.com/docs/05-clients/03-go-sdk) | CRUD for knowledge bases, documents and sessions, plus SSE streaming Q&A |+| 💬 | [**WeChat Dialog Open Platform**](https://chatbot.weixin.qq.com) | Zero-code hosted Q&A inside the WeChat ecosystem, powered by WeKnora |++### ⌨️ Command-Line Interface++`weknora` is the official CLI for driving the API from a terminal or an AI agent. It is **agent-first**: every command emits a stable JSON envelope by default (with typed error codes mapped to exit codes), and `--format text` renders for humans. It also serves a curated MCP tool surface (`weknora mcp serve`) and ships bundled Agent Skills.```bashweknora profile add prod --host https://kb.example.com --use@@ -226,130 +332,95 @@ weknora doc upload notes.mdweknora chat "summarise the design doc"```-For headless / CI use, set `WEKNORA_API_KEY` + `WEKNORA_HOST` and skip-`auth login` entirely — no credentials written to disk.--See [`cli/README.md`](./cli/README.md) for install + 5-minute quickstart and-[`cli/AGENTS.md`](./cli/AGENTS.md) for the operational contract AI agents rely on.--## 🚀 Getting Started--### 🛠 Prerequisites--- [Docker](https://www.docker.com/) & [Docker Compose](https://docs.docker.com/compose/)-- [Git](https://git-scm.com/)--### 📦 Installation & Launch--```bash-git clone https://github.com/Tencent/WeKnora.git-cd WeKnora-cp .env.example .env # Edit .env as needed, see comments in the file-docker compose pull # Pull the latest images-docker compose up -d # Start core services-```+For headless / CI use, set `WEKNORA_API_KEY` + `WEKNORA_HOST` and skip `auth login` entirely — no credentials written to disk. See [`cli/README.md`](./cli/README.md) for install + 5-minute quickstart and [`cli/AGENTS.md`](./cli/AGENTS.md) for the operational contract AI agents rely on.-Once started, visit **http://localhost** to get started.+### 🔌 MCP Server-> To use a local Ollama model, run `ollama serve > /dev/null 2>&1 &` first.+WeKnora has a built-in MCP Server: create an endpoint under **Settings → Publish & Integrations → MCP Server** and connect clients over Streamable HTTP at `/mcp/<endpoint_id>`. See the [MCP guide](https://weknora.weixin.qq.com/docs/03-features/08-mcp). The standalone Python server in [`mcp-server/`](./mcp-server/MCP_CONFIG.md) is deprecated and kept only for existing deployments.-For Ollama embedding model name, `OLLAMA_BASE_URL`, and RAM notes, see [configuration](./website-docs/01-getting-started/04-configuration.md).+<details>+<summary><b>🦞 ClawHub Skill</b></summary>-### 🔄 Upgrading+<br/>-If you already have WeKnora running and downloaded a newer release:--```bash-# Set WEKNORA_VERSION in .env to the target release (e.g. 0.7.0), or keep latest-docker compose pull # Pull images matching WEKNORA_VERSION-docker compose up -d # Recreate containers with new images-```--> `docker compose up -d` alone reuses locally cached images and may leave the UI version out of sync with the release you downloaded.--### 🔧 Optional Services (Docker Compose Profiles)+[**WeKnora ClawHub Skill**](https://clawhub.ai/lyingbug/weknora) is a WeKnora skill published on the ClawHub platform. Once installed, it enables document import (file / URL / Markdown), hybrid search (vector + keyword) across knowledge bases, and knowledge entry management — all through the WeKnora REST API.-Add `--profile` flags to enable additional components. Multiple profiles can be combined:+- **Document Import** — Upload files, import web pages, or write Markdown knowledge via the agent+- **Hybrid Search** — Search within or across knowledge bases with vector + keyword retrieval+- **Knowledge Management** — List, browse, edit, and delete knowledge entries programmatically-| Profile | Description | Command |-|---------|-------------|---------|-| _(default)_ | Core services | `docker compose pull && docker compose up -d` |-| `full` | All features | `docker compose --profile full pull && docker compose --profile full up -d` |-| `neo4j` | Knowledge Graph (Neo4j) | `docker compose --profile neo4j pull && docker compose --profile neo4j up -d` |-| `minio` | Object Storage (MinIO) | `docker compose --profile minio pull && docker compose --profile minio up -d` |-| `langfuse` | Tracing (Langfuse) | `docker compose --profile langfuse pull && docker compose --profile langfuse up -d` |+</details>-Combine profiles: `docker compose --profile neo4j --profile minio pull && docker compose --profile neo4j --profile minio up -d`+<details>+<summary><b>🐋 DeepSeek Harness Plugin</b></summary>-Stop services: `docker compose down`+<br/>-### 🌐 Service URLs+[**`@wxg-prc-cpg/dsh-weknora`**](https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora) is the official [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (`dsh`) plugin ([docs](./packages/dsh-weknora/README.md)). The harness ships no retrieval, embedding or knowledge-base capability of its own, so the plugin gives a coding agent your documents: `dsh plugin --profile web add @wxg-prc-cpg/dsh-weknora`, point it at a deployment, and four read-only tools appear in the agent's tool set.-| Service | URL |-|---------|-----|-| Web UI | `http://localhost` |-| Backend API | `http://localhost:8080` |-| Langfuse Tracing | `http://localhost:3000` |+- **`weknora_search`** — hybrid retrieval returning source passages verbatim, each with a reusable `knowledge_id`+- **`weknora_read_document`** — one document's passages reassembled in order, with paging+- **`weknora_ask`** — WeKnora's own composed answer with citations, over the RAG or the ReAct pipeline+- **`weknora_list_knowledge_bases`** — knowledge base names and ids, so the agent can scope its own search-## MCP Server+</details>-WeKnora has a built-in MCP Server: create an endpoint under Settings → Publish & Integrations → MCP Server and connect clients over Streamable HTTP at `/mcp/<endpoint_id>`. See the [MCP guide](./website-docs/03-features/08-mcp.md). The standalone Python server in [`mcp-server/`](./mcp-server/MCP_CONFIG.md) is deprecated and kept only for existing deployments.+<details>+<summary><b>💬 WeChat Dialog Open Platform</b></summary>-## 🔌 Using WeChat Dialog Open Platform+<br/>WeKnora serves as the core technology framework for the [WeChat Dialog Open Platform](https://chatbot.weixin.qq.com), providing a more convenient usage approach:-- **Zero-code Deployment**: Simply upload knowledge to quickly deploy intelligent Q&A services within the WeChat ecosystem, achieving an "ask and answer" experience-- **Efficient Question Management**: Support for categorized management of high-frequency questions, with rich data tools to ensure accurate, reliable, and easily maintainable answers-- **WeChat Ecosystem Integration**: Through the WeChat Dialog Open Platform, WeKnora's intelligent Q&A capabilities can be seamlessly integrated into WeChat Official Accounts, Mini Programs, and other WeChat scenarios, enhancing user interaction experiences-+- **Zero-code Deployment** — Simply upload knowledge to quickly deploy intelligent Q&A services within the WeChat ecosystem, achieving an "ask and answer" experience+- **Efficient Question Management** — Categorized management of high-frequency questions, with rich data tools to ensure accurate, reliable, and easily maintainable answers+- **WeChat Ecosystem Integration** — WeKnora's intelligent Q&A capabilities can be seamlessly integrated into WeChat Official Accounts, Mini Programs, and other WeChat scenarios+</details>-## 📘 API Reference+## 📚 Documentation-**Official website and product documentation**: [`website-docs/`](./website-docs/README.md) contains the product homepage and the complete documentation set organized as Getting Started → Architecture → Features → API → Clients → Development. With Node.js 24, run `cd website-docs && npm run setup && npm run build && npm run preview` to preview both together. The unified static output serves the homepage at `/` and documentation at `/docs/`; see the directory's README for Nginx and Docker deployment.+The full product documentation lives at **[weknora.weixin.qq.com/docs](https://weknora.weixin.qq.com/docs/)** (in Chinese), organized as Getting Started → Architecture → Features → API → Clients → Development and covering ~360 API endpoints and ~150 environment variables.-Troubleshooting FAQ: [Troubleshooting FAQ](./website-docs/01-getting-started/05-troubleshooting.md)+| Start here | |+|------------|---|+| 👋 [Introduction](https://weknora.weixin.qq.com/docs/01-getting-started/01-introduction) | What WeKnora can do |+| 📦 [Installation](https://weknora.weixin.qq.com/docs/01-getting-started/02-installation) | Docker Compose, Helm, Lite and desktop |+| ⚙️ [Configuration](https://weknora.weixin.qq.com/docs/01-getting-started/04-configuration) | Environment variables and models |+| 🩺 [Troubleshooting FAQ](https://weknora.weixin.qq.com/docs/01-getting-started/05-troubleshooting) | Common problems and fixes |+| 📘 [API reference](https://weknora.weixin.qq.com/docs/04-api/01-api-overview) | REST API overview |+| 🗒️ [Release notes](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2) | What changed in each release |-Detailed API documentation is available at: [API Docs](./website-docs/04-api/01-api-overview.md)+## 🛠️ Development-Product capabilities: [Introduction](./website-docs/01-getting-started/01-introduction.md)--## 🧭 Developer Guide--### ⚡ Fast Development Mode (Recommended)--If you need to frequently modify code, **you don't need to rebuild Docker images every time**! Use fast development mode:+If you need to frequently modify code, **you don't need to rebuild Docker images every time** — use fast development mode:```bash-# Start infrastructure-make dev-start--# Start backend (new terminal)-make dev-app--# Start frontend (new terminal)-make dev-frontend+make dev-start # Start infrastructure+make dev-app # Start backend (new terminal)+make dev-frontend # Start frontend (new terminal)```-**Development Advantages:**- ✅ Frontend modifications auto hot-reload (no restart needed)- ✅ Backend modifications quick restart (5-10 seconds, supports Air hot-reload)- ✅ No need to rebuild Docker images-- ✅ Support IDE breakpoint debugging+- ✅ Supports IDE breakpoint debugging-**Detailed Documentation:** [Development Environment Quick Start](./website-docs/06-development/01-dev-guide.md)+See the [Development guide](https://weknora.weixin.qq.com/docs/06-development/01-dev-guide) for details.+The documentation site and product homepage are built from [`website-docs/`](./website-docs/README.md). With Node.js 24, run `cd website-docs && npm run setup && npm run build && npm run preview` to preview both together; the unified static output serves the homepage at `/` and documentation at `/docs/`. See the directory's README for Nginx and Docker deployment.## 🤝 ContributingWelcome to submit [Issues](https://github.com/Tencent/WeKnora/issues) or Pull Requests.-**Process:** Fork → Create branch → Commit changes → Open PR+- **Process:** Fork → Create branch → Commit changes → Open PR+- **Standards:** Format code with `gofmt`, follow [Conventional Commits](https://www.conventionalcommits.org/) (`feat:` / `fix:` / `docs:` / `test:` / `refactor:`)-**Standards:** Format code with `gofmt`, follow [Conventional Commits](https://www.conventionalcommits.org/) (`feat:` / `fix:` / `docs:` / `test:` / `refactor:`)+<details>+<summary><b>Validating your change</b></summary>-### Validation+<br/>For a focused PR, validate the changed scope first:@@ -372,16 +443,9 @@ make test`make fmt` formats the entire Go repository, so run it only with a clean worktree and review the resulting diff. Some full-suite tests require local infrastructure or service configuration. If a full check fails for an unrelated baseline or environment reason, include the exact command and failure in the PR while still providing passing targeted tests for your change.-## 🔒 Security Notice--**Important:** Starting from v0.1.3, WeKnora includes login authentication functionality to enhance system security. For production deployments, we strongly recommend:--- Deploy WeKnora services in internal/private network environments rather than public internet-- Avoid exposing the service directly to public networks to prevent potential information leakage-- Configure proper firewall rules and access controls for your deployment environment-- Regularly update to the latest version for security patches and improvements+</details>-## 👥 Contributors+### 👥 ContributorsThanks to these excellent contributors:@@ -389,5 +453,4 @@ Thanks to these excellent contributors:## 📄 License-This project is licensed under the [MIT License](./LICENSE).-You are free to use, modify, and distribute the code with proper attribution.+This project is licensed under the [MIT License](./LICENSE). You are free to use, modify, and distribute the code with proper attribution.diff --git a/README_CN.md b/README_CN.mdindex 40ce52aa7..b404815da 100644--- a/README_CN.md+++ b/README_CN.md@@ -1,77 +1,188 @@<p align="center">- <picture>- <img src="./docs/images/logo.png" alt="WeKnora Logo" height="120"/>- </picture>+ <img src="./docs/images/logo.png" alt="WeKnora Logo" height="120"/></p>+<h3 align="center">让文档活起来 —— RAG 问答、Agent 推理与自动 Wiki 一体化、可完全私有化部署的知识框架</h3>+<p align="center">- <picture>- <a href="https://trendshift.io/repositories/15289" target="_blank">- <img src="https://trendshift.io/api/badge/repositories/15289" alt="Tencent/WeKnora | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>- </a>- </picture>+ <a href="https://trendshift.io/repositories/15289" target="_blank">+ <img src="https://trendshift.io/api/badge/repositories/15289" alt="Tencent/WeKnora | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>+ </a></p>+<p align="center">- <a href="https://weknora.weixin.qq.com" target="_blank">- <img alt="官方网站" src="https://img.shields.io/badge/官方网站-WeKnora-4e6b99">- </a>- <a href="https://chatbot.weixin.qq.com" target="_blank">- <img alt="微信对话开放平台" src="https://img.shields.io/badge/微信对话开放平台-5ac725">- </a>- <a href="https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd" target="_blank">- <img alt="Chrome 插件" src="https://img.shields.io/badge/Chrome 插件-WeKnora-4285F4">- </a>- <a href="https://clawhub.ai/lyingbug/weknora" target="_blank">- <img alt="ClawHub Skill" src="https://img.shields.io/badge/ClawHub Skill-WeKnora-ff6b35">- </a>- <a href="https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora" target="_blank">- <img alt="npm @wxg-prc-cpg/dsh-weknora" src="https://img.shields.io/npm/v/@wxg-prc-cpg/dsh-weknora?label=dsh-weknora">- </a>- <a href="https://github.com/Tencent/WeKnora/blob/main/LICENSE">- <img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License">- </a>- <a href="./CHANGELOG.md">- <img alt="版本" src="https://img.shields.io/badge/version-0.8.2-2e6cc4?labelColor=d4eaf7">- </a>+ <a href="https://weknora.weixin.qq.com" target="_blank"><img alt="官方网站" src="https://img.shields.io/badge/官方网站-WeKnora-4e6b99"></a>+ <a href="https://weknora.weixin.qq.com/docs/" target="_blank"><img alt="产品文档" src="https://img.shields.io/badge/产品文档-weknora.weixin.qq.com-2e6cc4"></a>+ <a href="https://chatbot.weixin.qq.com" target="_blank"><img alt="微信对话开放平台" src="https://img.shields.io/badge/微信对话开放平台-5ac725"></a>+ <a href="https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd" target="_blank"><img alt="Chrome 插件" src="https://img.shields.io/badge/Chrome 插件-WeKnora-4285F4"></a>+ <a href="https://clawhub.ai/lyingbug/weknora" target="_blank"><img alt="ClawHub Skill" src="https://img.shields.io/badge/ClawHub Skill-WeKnora-ff6b35"></a>+ <a href="https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora" target="_blank"><img alt="npm @wxg-prc-cpg/dsh-weknora" src="https://img.shields.io/npm/v/@wxg-prc-cpg/dsh-weknora?label=dsh-weknora"></a>+ <a href="https://github.com/Tencent/WeKnora/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="License"></a>+ <a href="./CHANGELOG.md"><img alt="版本" src="https://img.shields.io/badge/version-0.8.2-2e6cc4?labelColor=d4eaf7"></a></p><p align="center">-| <a href="./README.md"><b>English</b></a> | <b>简体中文</b> | <a href="./README_JA.md"><b>日本語</b></a> | <a href="./README_KO.md"><b>한국어</b></a> |+ <a href="./README.md">English</a> | <b>简体中文</b> | <a href="./README_JA.md">日本語</a> | <a href="./README_KO.md">한국어</a></p><p align="center">- <h4 align="center">-- [项目介绍](#-项目介绍) • [架构设计](#-架构设计) • [核心特性](#-核心特性) • [快速开始](#-快速开始) • [文档](#-文档) • [开发指南](#-开发指南)-- </h4>+ <a href="#-项目介绍">项目介绍</a> •+ <a href="#-快速开始">快速开始</a> •+ <a href="#-最新更新">最新更新</a> •+ <a href="#-功能概览">功能概览</a> •+ <a href="#-客户端与生态">客户端与生态</a> •+ <a href="#-文档">文档</a> •+ <a href="#-开发指南">开发指南</a></p>-# 💡 WeKnora — 让文档活起来:RAG、Agent 推理与自动 Wiki 一体化的知识框架+---## 📌 项目介绍-**[WeKnora(维娜拉)](https://weknora.weixin.qq.com)** 是一款开源的、基于大语言模型(LLM)的知识管理框架,专为企业级文档理解、语义检索与智能推理场景打造。+**[WeKnora(维娜拉)](https://weknora.weixin.qq.com)** 是一款开源的、基于大语言模型(LLM)的知识管理框架,专为企业级文档理解、语义检索与智能推理场景打造。它帮助团队把分散的文档沉淀为可查询、可推理、可持续演进的专属知识资产,并且完全运行在你自己的基础设施上。https://github.com/user-attachments/assets/2819598d-3140-4623-814a-8162a22b653c-*2 分 25 秒 · 1080p · 英文旁白,中英字幕。*+<p align="center"><sub>2 分 25 秒 · 1080p · 英文旁白,中英字幕</sub></p>++框架围绕三大核心能力构建:++<table>+ <tr>+ <td width="33%" valign="top">+ <h4>💬 RAG 快速问答</h4>+ 基于知识库快速、准确地回答日常问题,附带内联引用与 RAG 流水线分阶段进度。+ </td>+ <td width="33%" valign="top">+ <h4>🤖 ReAct Agent 智能推理</h4>+ 自主编排知识检索、MCP 工具、<b>技能目录</b>、会话级 <b>Docker / E2B / Cube 沙箱</b>、通过 <b>BrowserSkill</b> 操作用户本机浏览器以及网络搜索,完成复杂多步任务。+ </td>+ <td width="33%" valign="top">+ <h4>📖 Wiki 模式</h4>+ Agent 从原始文档中自治生成相互链接的 Markdown 知识库与可视化知识图谱,并支持人工编辑、版本历史与一键回滚。+ </td>+ </tr>+</table>++在此之上:++- **记得住,也管得细** —— **跨会话长期记忆**会记住你是谁、你常问什么;**树形文件夹**保留上传目录结构;**分块编辑与版本历史**让检索片段可以像文档一样被修改、比对与回滚。+- **多源接入** —— 飞书知识库 / 飞书云盘 / Confluence / GitLab / 腾讯 IMA / Notion / 语雀 / 钉钉文档 / RSS 自动同步(更多持续接入中);覆盖 PDF、Word、图片、Excel、XMind 等十余种文档格式;Office 文档由 **anydoc** 在 Go 进程内解析。+- **随处可问** —— 通过企业微信、飞书、Slack、Telegram 等 IM 频道直接提供问答;**网站嵌入 Widget** 将智能体发布到外部站点;**内置 MCP Server** 把知识库开放给 Cursor、Claude 等 AI 工具;**权限范围 API Key 与 Principal 模型**面向程序化集成。+- **模型自由** —— 27 家内置模型厂商与自动生成的模型目录,兼容 OpenAI、DeepSeek、Qwen(阿里云)、智谱、混元、Gemini、MiniMax、NVIDIA、LiteLLM、Ollama 等主流厂商。+- **企业级** —— **多空间 RBAC**(四级角色矩阵 + 资源归属 + 空间审计日志)、**每空间多实例存储后端**、**运行时任务队列面板 + Worker 池治理**,并无缝集成 **Langfuse**,为 Agent 运行、Token 使用及任务流水线提供全链路可观测性。+- **完全私有化** —— 全流程模块化设计,大模型、向量数据库、存储等组件均可灵活替换,支持本地与私有云部署,数据完全自主可控。++## 🚀 快速开始++**环境要求:** [Docker](https://www.docker.com/)、[Docker Compose](https://docs.docker.com/compose/) 与 [Git](https://git-scm.com/)。++```bash+git clone https://github.com/Tencent/WeKnora.git+cd WeKnora+cp .env.example .env # 按需编辑 .env,详见文件内注释+docker compose pull # 拉取最新镜像+docker compose up -d # 启动核心服务+```++启动成功后访问 **[http://localhost](http://localhost)**,按新手引导完成配置即可使用。带样例数据的完整上手流程见[快速上手](https://weknora.weixin.qq.com/docs/01-getting-started/03-quickstart)。-框架围绕三大核心能力构建:**RAG 快速问答**适合日常知识查询,**ReAct Agent 智能推理**自主编排知识检索、MCP 工具、**技能目录**、会话级 **Docker / E2B / Cube 沙箱**、通过 **BrowserSkill** 操作用户本机浏览器与网络搜索完成复杂多步任务,全新的 **Wiki 模式**则让 Agent 从原始文档中自治生成相互链接的 Markdown 知识库与可视化知识图谱,并支持人工编辑、版本历史与一键回滚。**跨会话长期记忆**会记住你是谁、你常问什么。知识加工环节也完全可控:**树形文件夹**保留上传目录结构,**分块编辑与版本历史**让检索片段可以像文档一样被修改、比对与回滚。结合多源数据接入(飞书知识库 / 飞书云盘 / Confluence / GitLab / 腾讯 IMA / Notion / 语雀 / 钉钉文档 / RSS,更多持续接入中)、**网站嵌入 Widget** 将智能体发布到外部站点、**内置 MCP Server** 把知识库开放给 Cursor、Claude 等 AI 工具、**权限范围 API Key 与 Principal 模型**面向程序化集成、**每空间多实例存储后端**灵活编排数据落地、27 家内置模型厂商与自动生成的模型目录(含 LiteLLM)、Langfuse 全链路可观测性与**运行时任务队列面板 + Worker 池治理**、**企业级多空间 RBAC(四级角色矩阵 + 资源归属 + 空间审计日志)**,以及完全可私有化部署的模块化架构,WeKnora 帮助团队把分散文档沉淀为可查询、可推理、可持续演进的专属知识资产。+> [!TIP]+> 如需使用本地 Ollama 模型,请先运行 `ollama serve > /dev/null 2>&1 &`。Ollama 向量模型名、`OLLAMA_BASE_URL` 与内存说明见[配置文档](https://weknora.weixin.qq.com/docs/01-getting-started/04-configuration)。-框架支持从飞书、Confluence、钉钉文档、GitLab、腾讯 IMA、Notion 及语雀等外部平台自动同步知识(更多数据源持续接入中),覆盖 PDF、Word、图片、Excel、XMind 等十余种文档格式,并可通过企业微信、飞书、Slack、Telegram 等 IM 频道直接提供问答服务。模型层面兼容 OpenAI、DeepSeek、Qwen(阿里云)、智谱、混元、Gemini、MiniMax、NVIDIA、LiteLLM、Ollama 等主流厂商。Office 文档可由 **anydoc** 在 Go 进程内解析。全流程模块化设计,大模型、向量数据库、存储等组件均可灵活替换,支持本地与私有云部署,数据完全自主可控。WeKnora 还无缝集成了 **Langfuse**,为 Agent 运行、Token 使用及任务流水线提供了全面的可观测性追踪。+| 服务 | 地址 |+|------|------|+| Web UI | `http://localhost` |+| 后端 API | `http://localhost:8080` |+| 链路追踪 (Langfuse) | `http://localhost:3000` |++### 可选服务++按需添加 `--profile` 启动额外组件,多个 profile 可叠加使用:++| Profile | 说明 |+|---------|------|+| _(默认)_ | 核心服务 |+| `full` | 全部功能 |+| `neo4j` | 知识图谱 (Neo4j) |+| `minio` | 对象存储 (MinIO) |+| `langfuse` | 链路追踪 (Langfuse) |++```bash+docker compose --profile neo4j --profile minio pull+docker compose --profile neo4j --profile minio up -d+docker compose down # 停止服务+```++### 版本升级++若已有部署并下载了更新的 release:++```bash+# 在 .env 中将 WEKNORA_VERSION 设为目标版本(如 0.8.2),或保持 latest+docker compose pull # 拉取与 WEKNORA_VERSION 匹配的镜像+docker compose up -d # 用新镜像重建容器+```++> [!NOTE]+> 仅执行 `docker compose up -d` 会复用本地缓存镜像,可能导致 Web UI 显示版本与下载的 release 不一致。从 v0.8.0 升级前请先阅读[升级须知](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#upgrade-notes)。++### 其他部署方式++| 方式 | 适用场景 |+|------|----------|+| **Docker Compose** | 上面的标准部署,功能完整,多服务 |+| **Kubernetes (Helm)** | 生产集群;Chart 位于 [`helm/`](./helm) |+| **Lite 单二进制** | 本机或低资源环境,零外部依赖(SQLite + 内存队列);与标准版的差异见 [Lite 与标准版区别](./docs/LITE.md) |+| **桌面应用** | 带图形界面的 Lite 运行时,免登录启动,macOS 上提供本机沙箱;尚未提供安装包,需自行构建 |++全部部署形态、硬件要求与常见拓扑见[安装部署](https://weknora.weixin.qq.com/docs/01-getting-started/02-installation)。++> [!WARNING]+> WeKnora 已提供登录鉴权,但在生产环境部署时,我们强烈建议:+> - 将 WeKnora 服务部署在内网 / 私有网络环境中,而非公网环境;+> - 避免将服务直接暴露在公网上,以防止重要信息泄露风险;+> - 为部署环境配置适当的防火墙规则和访问控制;+> - 定期更新到最新版本以获取安全补丁和改进。## ✨ 最新更新-- **v0.8.2** —— **本地浏览器(BrowserSkill)**:智能体通过开源 BrowserSkill 扩展操作用户自己的 Chrome / Edge,支持实时任务预览、暂停 / 继续,登录和验证码交给用户处理;**内置 MCP Server**(按空间发布 `/mcp/<endpoint_id>` 端点,Streamable HTTP,每个端点独立令牌、知识库范围、限流与工具分组;Python 版 `mcp-server/` 已弃用);侧边栏**工具箱**集中管理技能、MCP 服务与浏览器连接;**对话控制**(运行中追加要求、从任意历史问题分叉、原地回滚并还原沙箱检查点、按会话选择思考强度);**产物库**;沙箱**交互终端**与**图形桌面**;macOS **Lite 宿主机沙箱**与项目文件夹;重构的**模型目录**(27 家内置厂商,自动补全上下文窗口、最大输出、思考档位与视觉能力);Agent 检索工具合并为 `search_knowledge` / `read_document` / `list_documents`;Confluence 与钉钉文档数据源;博查与 Serply 网络搜索;日语界面;IM 频道级回复语言;仅白名单出站模式。不兼容变更:钉钉频道仅支持 Stream 模式,沙箱命令默认以 `root` 执行。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.8.0** —— **技能沙箱运行时**(会话级常驻 Docker / E2B / Cube 后端,按空间配置网络策略;移除 Local 宿主机进程后端;Docker 需显式开启);**空间技能目录**(从 ClawHub / SkillHub / git / zip 安装,按沙箱快照、实时进度、文件浏览/编辑、个人与空间环境变量);**跨会话长期记忆**(profile / preference / fact / task / interest,自动抽取需确认,`search_memory`);进程内 **anydoc** Office 解析;官方 **DeepSeek Harness 插件** `@wxg-prc-cpg/dsh-weknora`;GitLab 与腾讯 IMA 数据源;LiteLLM;Exa 与 Metaso 网络搜索;XMind 解析;对话产物、问题大纲与时间戳;上下文压缩与供应商 Prompt Cache 标记。另有 OIDC JWKS 验签、可选复杂密码、文档自动打标签,以及大范围沙箱/安全加固。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.7.2** —— 上线**官方产品文档站**(VitePress,六大板块约 50 篇,覆盖约 360 个 API 端点与约 150 个环境变量,含独立 Docker/Nginx 部署、快速上手样例数据与本地 MCP demo);**知识库文件夹树**(文件夹路径独立入库,可像文件管理器一样浏览、重命名与重新归档);**分块编辑与版本历史**(可视化编辑检索分块、逐版本 diff 与回滚、自动重建索引、文档自定义元数据);**Wiki 页面版本历史**(快照 + 行级 diff + 一键回滚 + 浏览器内手动编辑);**API 文件直链模式** `resource_urls=public` / `RESOURCE_URL_MODE`(第三方 App 无需二次调用鉴权代理即可加载图片与文件);**飞书云盘数据源**与 docx blocks 逐类型下钻同步;文档批量打标签;**MCP Server 1.1.x**(迁移到 mcp 2.x 高级 API,官方 PyPI 包 `tencent-weknora-mcp`,新增 `create_knowledge_from_text` 与 `list_shared_knowledge_bases`,共 29 个工具);AWS S3 默认凭据链(IAM Role / IRSA);本地 HTML 上传解析;QQBot Markdown 回复;新增 app / frontend / docreader / mcp-server 的 PR CI 检查。另有 router 与 modelcontext 大规模重构、重排与分块质量优化,以及大量稳定性修复。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.7.1** —— 新增**云之家 IM 集成**(WebSocket + 图片消息 + Markdown 回复);**火山引擎 Rerank** 供应商(自动分批请求)与**智谱 AI 网络搜索**供应商;**平台级 API Key**,用于控制面自动化(空间管理、系统设置、运行时队列、审计日志);**按知识库的活动审计追踪**;FAQ 管理增强(筛选、打标签、导出、导入结果追踪);**Langfuse OTLP/OTel 追踪**迁移,支持 W3C traceparent 跨服务传播;对话头部操作栏,支持一键 **Markdown 导出**,并在引用抽屉中展示 Wiki 工具结果;Prompt 缓存可观测性;会话渠道治理(IM/嵌入/API 会话按管理员范围隔离);飞书大型 Wiki 同步韧性增强;移除旧版 Neo4j 会话记忆依赖。另有大范围的 slug 完整性、SSRF 传输与状态同步加固。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.7.0** —— 细粒度**权限范围 API Key 与 Principal 模型**(能力级授权 + 按 KB 限制 + API 集成调试台);**运行时任务队列可观测面板与 Worker 池治理**(分阶段独立池 + 按模型并发治理 + 失败任务排查/重试);**多实例存储后端**(每空间多存储实例、按 KB 绑定、默认实例);**会话级临时附件**(图片/文档异步解析 + 合并限额);推荐问题与追问;稳定资源注册表与 LLM 上下文别名压缩;`@Skill / @MCP` 提及范围化 Agent 运行时;会话内 MCP OAuth 授权;QQBot 与 Lark(飞书国际版)IM 集成;Redis TLS;Requesty 模型厂商 + Keenable 网络搜索;无空间预置与受控自助创建工作区;管理员密码重置;知识库复制流程;`weknora` CLI v0.10。同时完成大范围安全加固(SSRF、密钥脱敏、SQL 校验、越权)。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.6.3** —— 网站嵌入 Widget 与发布集成中心(安全模式 Token 交换 + 限流);对话体验全面革新(引用浮层、RAG 流水线进度、流式 Markdown);文档多标签与批量重新解析;Wiki 文件夹与层级导航;RSS 数据源;MCP OAuth2;EPUB / MHTML 解析;Agent 模型就绪校验;模型调试器;会话来源筛选;工作区删除 UI。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.6.2** —— 按批次解析配置(`process_config`)+ 上传确认对话框;文档重新解析(reparse)支持覆盖配置;`weknora` CLI v0.9(内置 Agent Skills、`session stop`、auth/profile 统一);知识库框选多选;pgvector 1024 维 HNSW 索引;对话资源 Store 重构;仅保留 Langfuse 追踪(移除 Jaeger)。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.6.1** —— 文档解析追踪时间线(Langfuse 风格 Span 树,逐阶段进度展示 + 解析中止);OpenSearch 向量库驱动;YAML 声明式内置模型配置;系统管理员与统一平台设置 + 审计日志;新用户引导;设置页 UI 重构;`weknora` CLI v0.7 / v0.8(Agent 优先线协议、NDJSON、`--dry-run`);OpenDataLoader 与 PaddleOCR-VL 解析引擎;MCP Server 多传输(stdio / SSE / HTTP);按模型的思考模式配置;腾讯云 LKEAP 重排 + 原生 Gemini Embedding + MiniMax-M3。详见 [`CHANGELOG.md`](./CHANGELOG.md)。-- **v0.6.0** —— 空间 RBAC(四级角色矩阵 `Owner` / `Admin` / `Contributor` / `Viewer` + 按 KB 归属 + 每空间审计日志)、空间成员管理与多工作区 UX、自助创建工作区;`weknora` CLI v0.4 正式版 + `mcp serve`;KB 检索跨向量库扇出;MCP / 数据源凭据 AES-256-GCM 加密 + docreader gRPC TLS + Token;新增智谱 Embedding 与华为云 OBS;服务端用户偏好;Go 1.26.0。详见 [`website-docs/03-features/01-tenant-auth.md`](./website-docs/03-features/01-tenant-auth.md) 与 [`CHANGELOG.md`](./CHANGELOG.md)。+### v0.8.2 <sub>· 2026-09-24 · [版本说明](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2)</sub>++智能体走出对话框:它可以操作你电脑上的浏览器;知识库可以作为 MCP Server 发布给其他 AI 工具;对话过程也更可控。++- 🌐 **[本地浏览器(BrowserSkill)](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#local-browser)** —— 智能体通过开源 BrowserSkill 扩展操作用户自己的 Chrome / Edge,支持实时任务预览、暂停 / 继续,登录和验证码交给用户处理。+- 🔌 **[内置 MCP Server](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#mcp-server)** —— 按空间发布 `/mcp/<endpoint_id>` 端点,Streamable HTTP,每个端点独立令牌、知识库范围、限流与工具分组;Python 版 `mcp-server/` 已弃用。+- 🧭 **[对话控制](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#conversation-control)** —— 运行中追加要求、从任意历史问题分叉、原地回滚并还原沙箱检查点、按会话选择思考强度;新增**产物库**。+- 🖥️ **[沙箱](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#sandbox)** —— 沙箱**交互终端**与**图形桌面**;macOS **Lite 宿主机沙箱**与项目文件夹;侧边栏**工具箱**集中管理技能、MCP 服务与浏览器连接。+- 🧠 **[模型接入](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#models)** —— 重构的**模型目录**(27 家内置厂商,自动补全上下文窗口、最大输出、思考档位与视觉能力);Agent 检索工具合并为 `search_knowledge` / `read_document` / `list_documents`。+- 📚 **[知识库与平台](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#knowledge)** —— Confluence 与钉钉文档数据源;博查与 Serply 网络搜索;日语界面;IM 频道级回复语言;仅白名单出站模式。++> [!IMPORTANT]+> **不兼容变更:** 钉钉频道仅支持 Stream 模式,沙箱命令默认以 `root` 执行。详见[升级须知](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2#upgrade-notes)。++### v0.8.0 <sub>· [版本说明](https://weknora.weixin.qq.com/docs/07-releases/v0.8.0)</sub>++- 🧪 **技能沙箱运行时** —— 会话级常驻 Docker / E2B / Cube 后端,按空间配置网络策略;移除 Local 宿主机进程后端;Docker 需显式开启。+- 📦 **空间技能目录** —— 从 ClawHub / SkillHub / git / zip 安装,按沙箱快照、实时进度、文件浏览/编辑、个人与空间环境变量。+- 🧠 **跨会话长期记忆** —— profile / preference / fact / task / interest,自动抽取需确认,`search_memory`。+- 📄 **解析与数据源** —— 进程内 **anydoc** Office 解析;GitLab 与腾讯 IMA 数据源;XMind 解析。+- 🧩 **生态** —— 官方 **DeepSeek Harness 插件** `@wxg-prc-cpg/dsh-weknora`;LiteLLM;Exa 与 Metaso 网络搜索。+- 💬 **对话** —— 对话产物、问题大纲与时间戳;上下文压缩与供应商 Prompt Cache 标记。+- 🔒 **安全** —— OIDC JWKS 验签、可选复杂密码、文档自动打标签,以及大范围沙箱/安全加固。++<details>+<summary><b>更早版本(v0.2.0 – v0.7.2)</b></summary>++<br/>++- **v0.7.2** —— 上线**官方产品文档站**(VitePress,六大板块约 50 篇,覆盖约 360 个 API 端点与约 150 个环境变量,含独立 Docker/Nginx 部署、快速上手样例数据与本地 MCP demo);**知识库文件夹树**(文件夹路径独立入库,可像文件管理器一样浏览、重命名与重新归档);**分块编辑与版本历史**(可视化编辑检索分块、逐版本 diff 与回滚、自动重建索引、文档自定义元数据);**Wiki 页面版本历史**(快照 + 行级 diff + 一键回滚 + 浏览器内手动编辑);**API 文件直链模式** `resource_urls=public` / `RESOURCE_URL_MODE`(第三方 App 无需二次调用鉴权代理即可加载图片与文件);**飞书云盘数据源**与 docx blocks 逐类型下钻同步;文档批量打标签;**MCP Server 1.1.x**(迁移到 mcp 2.x 高级 API,官方 PyPI 包 `tencent-weknora-mcp`,新增 `create_knowledge_from_text` 与 `list_shared_knowledge_bases`,共 29 个工具);AWS S3 默认凭据链(IAM Role / IRSA);本地 HTML 上传解析;QQBot Markdown 回复;新增 app / frontend / docreader / mcp-server 的 PR CI 检查。另有 router 与 modelcontext 大规模重构、重排与分块质量优化,以及大量稳定性修复。+- **v0.7.1** —— 新增**云之家 IM 集成**(WebSocket + 图片消息 + Markdown 回复);**火山引擎 Rerank** 供应商(自动分批请求)与**智谱 AI 网络搜索**供应商;**平台级 API Key**,用于控制面自动化(空间管理、系统设置、运行时队列、审计日志);**按知识库的活动审计追踪**;FAQ 管理增强(筛选、打标签、导出、导入结果追踪);**Langfuse OTLP/OTel 追踪**迁移,支持 W3C traceparent 跨服务传播;对话头部操作栏,支持一键 **Markdown 导出**,并在引用抽屉中展示 Wiki 工具结果;Prompt 缓存可观测性;会话渠道治理(IM/嵌入/API 会话按管理员范围隔离);飞书大型 Wiki 同步韧性增强;移除旧版 Neo4j 会话记忆依赖。另有大范围的 slug 完整性、SSRF 传输与状态同步加固。+- **v0.7.0** —— 细粒度**权限范围 API Key 与 Principal 模型**(能力级授权 + 按 KB 限制 + API 集成调试台);**运行时任务队列可观测面板与 Worker 池治理**(分阶段独立池 + 按模型并发治理 + 失败任务排查/重试);**多实例存储后端**(每空间多存储实例、按 KB 绑定、默认实例);**会话级临时附件**(图片/文档异步解析 + 合并限额);推荐问题与追问;稳定资源注册表与 LLM 上下文别名压缩;`@Skill / @MCP` 提及范围化 Agent 运行时;会话内 MCP OAuth 授权;QQBot 与 Lark(飞书国际版)IM 集成;Redis TLS;Requesty 模型厂商 + Keenable 网络搜索;无空间预置与受控自助创建工作区;管理员密码重置;知识库复制流程;`weknora` CLI v0.10。同时完成大范围安全加固(SSRF、密钥脱敏、SQL 校验、越权)。+- **v0.6.3** —— 网站嵌入 Widget 与发布集成中心(安全模式 Token 交换 + 限流);对话体验全面革新(引用浮层、RAG 流水线进度、流式 Markdown);文档多标签与批量重新解析;Wiki 文件夹与层级导航;RSS 数据源;MCP OAuth2;EPUB / MHTML 解析;Agent 模型就绪校验;模型调试器;会话来源筛选;工作区删除 UI。+- **v0.6.2** —— 按批次解析配置(`process_config`)+ 上传确认对话框;文档重新解析(reparse)支持覆盖配置;`weknora` CLI v0.9(内置 Agent Skills、`session stop`、auth/profile 统一);知识库框选多选;pgvector 1024 维 HNSW 索引;对话资源 Store 重构;仅保留 Langfuse 追踪(移除 Jaeger)。+- **v0.6.1** —— 文档解析追踪时间线(Langfuse 风格 Span 树,逐阶段进度展示 + 解析中止);OpenSearch 向量库驱动;YAML 声明式内置模型配置;系统管理员与统一平台设置 + 审计日志;新用户引导;设置页 UI 重构;`weknora` CLI v0.7 / v0.8(Agent 优先线协议、NDJSON、`--dry-run`);OpenDataLoader 与 PaddleOCR-VL 解析引擎;MCP Server 多传输(stdio / SSE / HTTP);按模型的思考模式配置;腾讯云 LKEAP 重排 + 原生 Gemini Embedding + MiniMax-M3。+- **v0.6.0** —— 空间 RBAC(四级角色矩阵 `Owner` / `Admin` / `Contributor` / `Viewer` + 按 KB 归属 + 每空间审计日志)、空间成员管理与多工作区 UX、自助创建工作区;`weknora` CLI v0.4 正式版 + `mcp serve`;KB 检索跨向量库扇出;MCP / 数据源凭据 AES-256-GCM 加密 + docreader gRPC TLS + Token;新增智谱 Embedding 与华为云 OBS;服务端用户偏好;Go 1.26.0。详见[多租户与认证](https://weknora.weixin.qq.com/docs/03-features/01-tenant-auth)。- **v0.5.2** —— Wiki 入库支撑万级文档知识库(任务队列 + 死信队列);MCP 工具人机审批;Anthropic / Apache Doris / 腾讯云 VectorDB / 金山云 KS3 / SearXNG 后端;自适应三层分块 + 实时调试面板;全局 ⌘K 命令面板;语雀连接器 + 微信小程序;`weknora` CLI 早期版本。- **v0.5.1** —— 知识库批量管理;空间级 IM 频道总览;会话搜索 + 用户级置顶;模型 / 网页搜索 / MCP 统一卡片化设置;按 Agent LLM 调用超时;桌面端空间切换。- **v0.5.0** —— Wiki 模式正式版 —— Agent 从原始文档自治生成结构化、相互链接的 Markdown Wiki 页面及知识图谱;Wiki 浏览器 + 可视化图谱。@@ -84,8 +195,11 @@ https://github.com/user-attachments/assets/2819598d-3140-4623-814a-8162a22b653c- **v0.3.0** —— 共享空间;Agent Skills + 沙盒执行;自定义 Agent;数据分析 Agent;思考模式;Bing / Google 搜索;API Key 认证;Helm Chart;韩语 i18n;Qdrant。- **v0.2.0** —— Agent 模式(ReACT);多类型知识库(FAQ + 文档);对话策略配置;DuckDuckGo 网页搜索;MCP 工具集成;全新 UI + Agent 模式切换;MQ 异步任务管理。+完整变更记录见 [`CHANGELOG.md`](./CHANGELOG.md)。++</details>-## 📱 功能展示+## 📸 功能展示<table><tr>@@ -114,225 +228,199 @@ https://github.com/user-attachments/assets/2819598d-3140-4623-814a-8162a22b653c## 🏗️ 架构设计-+-从文档解析、向量化、检索到大模型推理,全流程模块化解耦,组件可灵活替换与扩展。支持本地 / 私有云部署,数据完全自主可控,零门槛 Web UI 快速上手。+从文档解析、向量化、检索到大模型推理,全流程模块化解耦,组件可灵活替换与扩展。支持本地 / 私有云部署,数据完全自主可控,零门槛 Web UI 快速上手。深入了解:[架构总览](https://weknora.weixin.qq.com/docs/02-architecture/01-overview) · [RAG 流水线](https://weknora.weixin.qq.com/docs/02-architecture/04-rag-pipeline) · [扩展点](https://weknora.weixin.qq.com/docs/06-development/03-extension-points)。## 🧩 功能概览-**智能对话**+### 智能对话++<sub>文档:[Agent](https://weknora.weixin.qq.com/docs/03-features/07-agent) · [Wiki](https://weknora.weixin.qq.com/docs/03-features/14-wiki) · [技能与沙箱](https://weknora.weixin.qq.com/docs/03-features/22-skills-sandbox) · [长期记忆](https://weknora.weixin.qq.com/docs/03-features/23-memory) · [对话体验](https://weknora.weixin.qq.com/docs/03-features/18-chat-experience)</sub>| 能力 | 详情 ||------|------|| 智能推理 | ReACT 渐进式多步推理,自主编排知识检索、MCP 工具、技能沙箱、本地浏览器与网络搜索 || 快速问答 | 基于知识库的 RAG 问答,快速准确地回答问题 || Wiki 模式 | Agent 驱动从原始文档中自动生成并维护结构化、相互链接的 Markdown Wiki 知识页面;支持浏览器内人工编辑、页面版本历史、行级 diff 与一键回滚 |-| 技能目录与沙箱 | 空间技能目录(ClawHub / SkillHub / git / zip)安装到会话级 Docker / E2B / Cube 沙箱;`shell_exec`、文件工具、产物收集、按配置网络策略;已移除 Local 宿主机进程后端;对话旁提供交互终端与浏览器内图形桌面;macOS 桌面版把未固定沙箱的会话放在系统沙箱(Seatbelt)中运行,可绑定所选项目文件夹或使用按日期创建的临时工作区 |+| 技能目录与沙箱 | 空间技能目录(ClawHub / SkillHub / git / zip)安装到会话级 Docker / E2B / Cube 沙箱 · `shell_exec`、文件工具、产物收集、按配置网络策略 · 对话旁提供交互终端与浏览器内图形桌面 · macOS 桌面版把未固定沙箱的会话放在系统沙箱(Seatbelt)中运行,可绑定所选项目文件夹或使用按日期创建的临时工作区 · 已移除 Local 宿主机进程后端 || 本地浏览器 | 智能体通过开源 BrowserSkill 扩展在独立任务窗口中操作用户自己的 Chrome / Edge(打开页面、点击、填表、读取内容),支持实时预览、暂停 / 继续 / 结束,登录与验证码交由用户处理 || 对话控制 | 运行中追加要求、从任意历史问题分叉对话、原地回滚(沙箱工作区同步还原到对应检查点),按会话选择思考强度 || 产物库 | 侧边栏集中列出所有对话生成的文件,支持类型筛选、搜索、按日期分组与版本历史 || 长期记忆 | 跨会话记忆(profile / preference / fact / task / interest),支持自动抽取、用户确认与按需 `search_memory` |-| 工具调用 | 内置工具、MCP 工具(含 OAuth2 远程服务、会话内 OAuth 授权)、网络搜索;支持 `@Skill / @MCP` 提及以按轮次范围化 Agent 运行时;MCP 工具按需发现与调用,可逐个启用或停用 |+| 工具调用 | 内置工具、MCP 工具(含 OAuth2 远程服务、会话内 OAuth 授权)、网络搜索 · 支持 `@Skill / @MCP` 提及以按轮次范围化 Agent 运行时 · MCP 工具按需发现与调用,可逐个启用或停用 || 对话策略 | 在线 Prompt 编辑、检索阈值调节、多轮上下文感知、按 Agent 引用输出开关 || 推荐问题 | 基于知识库内容自动生成推荐问题与答后追问 || 临时附件 | 会话级临时上传图片 / 文档,异步解析后用于一次性问答,支持图片与附件合并限额 || 引用与 RAG 进度 | 对话内引用浮层与引用抽屉(区分网络 / 知识库来源)、统一 Markdown 渲染、RAG 流水线分阶段进度展示 || 会话管理 | 侧边栏按来源(Web / IM / 嵌入)筛选与分组会话,支持会话标题内联重命名 |-**知识管理**+### 知识管理++<sub>文档:[知识库](https://weknora.weixin.qq.com/docs/03-features/02-knowledge-base) · [文档解析](https://weknora.weixin.qq.com/docs/03-features/03-document-parsing) · [分块](https://weknora.weixin.qq.com/docs/03-features/04-chunking) · [检索引擎](https://weknora.weixin.qq.com/docs/03-features/05-retrieval-engines) · [知识图谱](https://weknora.weixin.qq.com/docs/03-features/09-knowledge-graph) · [数据源](https://weknora.weixin.qq.com/docs/03-features/10-datasource)</sub>| 能力 | 详情 ||------|------|| 知识库类型 | FAQ / 文档 / Wiki,支持文件夹导入、URL 导入、多标签管理、在线录入 || 文件夹树 | 文件夹上传保留原始目录结构,侧栏树形浏览、重命名文件夹、把文档重新归档到其他文件夹 |-| 分块编辑与版本历史 | 在界面直接编辑检索分块,保留逐版本快照,支持 diff 与一键回滚,编辑后自动重建索引;生成问题可增删改与重新生成;支持文档自定义元数据 |+| 分块编辑与版本历史 | 在界面直接编辑检索分块,保留逐版本快照,支持 diff 与一键回滚,编辑后自动重建索引 · 生成问题可增删改与重新生成 · 支持文档自定义元数据 || 按批次解析配置 | 上传确认对话框或 `process_config` API 覆盖解析引擎、分块、多模态(VLM / ASR)、图谱抽取与问题生成;支持 reparse 时调整配置 || 批量重新解析 | 一次为多篇文档重新排队解析,可携带批次级 `process_config` || 数据源导入 | 飞书知识库 / 飞书云盘 / Lark / Confluence / GitLab / 腾讯 IMA / Notion / 语雀 / 钉钉文档 / RSS 订阅自动同步(更多数据源开发中),支持增量与全量同步 || 文档格式 | PDF / Word / Txt / Markdown / HTML / EPUB / MHTML / 图片 / CSV / Excel / PPT / JSON / XMind || 自动打标签 | 解析完成后从知识库已有标签中选择匹配项增量关联,不创建新标签、不覆盖人工标签 || 检索策略 | BM25 稀疏召回 / Dense 稠密召回 / GraphRAG 图谱增强 / 父子分块 / pgvector HNSW 加速(1024 维)/ 多维度索引 |+| 文档知识图谱 | 将文档转化为知识图谱,展示不同段落之间的关联关系,为索引和检索提供结构化支撑,提升检索结果的相关性和广度(需部署 Neo4j:启用 `neo4j` profile 并设置 `NEO4J_ENABLE=true`) || 批量选择与打标签 | 知识库文档列表支持框选(marquee)多选,可批量重新解析、批量打标签(自动预选公共标签) || 端到端测试 | 检索+生成全链路可视化,评估召回命中率、BLEU / ROUGE 等指标 |-**集成与扩展**+### 集成与扩展++<sub>文档:[模型](https://weknora.weixin.qq.com/docs/03-features/06-models) · [MCP](https://weknora.weixin.qq.com/docs/03-features/08-mcp) · [网络搜索](https://weknora.weixin.qq.com/docs/03-features/11-web-search) · [IM 集成](https://weknora.weixin.qq.com/docs/03-features/12-im-integration) · [网站嵌入](https://weknora.weixin.qq.com/docs/03-features/13-embed-channel) · [存储后端](https://weknora.weixin.qq.com/docs/03-features/19-storage-backends)</sub>| 能力 | 详情 ||------|------|| 模型厂商 | OpenAI / Azure OpenAI / Anthropic(Claude)/ DeepSeek / Qwen(阿里云)/ 智谱 / 混元 / 豆包(火山引擎)/ Gemini / MiniMax / NVIDIA / Novita AI / SiliconFlow / OpenRouter / Requesty / LiteLLM / Ollama || 向量数据库 | PostgreSQL (pgvector) / Elasticsearch / OpenSearch / Milvus / Weaviate / Qdrant / Apache Doris / 腾讯云 VectorDB || Embedding | Ollama / BGE / GTE / 智谱 / OpenAI 兼容接口 |-| 对象存储 | 本地 / 腾讯云COS / 火山引擎 TOS / MinIO / AWS S3(支持 IAM Role / IRSA 默认凭据链)/ 阿里云 OSS / 金山云 KS3 / 华为云 OBS;支持**每空间多实例存储后端**,不同知识库可绑定不同实例并设置默认实例 |+| 对象存储 | 本地 / 腾讯云 COS / 火山引擎 TOS / MinIO / AWS S3(支持 IAM Role / IRSA 默认凭据链)/ 阿里云 OSS / 金山云 KS3 / 华为云 OBS · 支持**每空间多实例存储后端**,不同知识库可绑定不同实例并设置默认实例 || IM 集成 | 企业微信 / 飞书 / Lark(飞书国际版)/ QQBot / Slack / Telegram / 钉钉 / Mattermost / 微信 / 云之家 || 网站嵌入 | 通过嵌入 Widget 发布智能体,支持域名白名单、限流与安全模式 Token 交换 || 网络搜索 | DuckDuckGo / Bing / Google / Tavily / Baidu / Ollama / SearXNG / Keenable / 智谱 AI / Exa / Metaso / 博查 / Serply |-| API 集成 | 权限范围 API Key(能力级授权 + 按 KB 限制 + 节流的 last_used 追踪)与 API 集成调试台;MCP OAuth 与嵌入会话按 Principal 隔离;`resource_urls=public` 直接返回可加载的文件/图片直链,免去二次鉴权代理调用 |+| API 集成 | 权限范围 API Key(能力级授权 + 按 KB 限制 + 节流的 last_used 追踪)与 API 集成调试台 · MCP OAuth 与嵌入会话按 Principal 隔离 · `resource_urls=public` 直接返回可加载的文件/图片直链,免去二次鉴权代理调用 || MCP Server | 内置:按空间发布 `/mcp/<endpoint_id>` 端点(Streamable HTTP),每个端点独立令牌、知识库范围、限流与工具分组(检索、`ask`、Wiki、需手动开启的写入工具);Python 包 `tencent-weknora-mcp` 已弃用 |+### 平台能力-**平台能力**+<sub>文档:[多租户与认证](https://weknora.weixin.qq.com/docs/03-features/01-tenant-auth) · [可观测性](https://weknora.weixin.qq.com/docs/03-features/16-observability) · [平台管理](https://weknora.weixin.qq.com/docs/03-features/20-platform-admin) · [异步任务](https://weknora.weixin.qq.com/docs/02-architecture/05-async-tasks)</sub>| 能力 | 详情 ||------|------|| 部署 | 本地 / Docker / Kubernetes (Helm),支持私有化离线部署 |-| 界面 | Web UI / RESTful API / 命令行(`weknora`)/ Chrome Extension / 网站嵌入 Widget / 微信小程序;界面支持中文 / 英文 / 日文 / 韩文 / 俄文 |+| 界面 | Web UI / RESTful API / 命令行(`weknora`)/ Chrome Extension / 网站嵌入 Widget / 微信小程序 · 界面支持中文 / 英文 / 日文 / 韩文 / 俄文 || 权限控制 | 空间 RBAC 四级角色矩阵(Owner / Admin / Contributor / Viewer),按知识库的资源归属,每空间审计日志,invite-only 准入,无空间预置与受控自助创建工作区,管理员密码重置(会话吊销),跨空间超级管理员,权限范围 API Key |-| 安全 | API Key 与 MCP / 数据源凭据 AES-256-GCM 静态加密、支持平滑密钥轮换;app ↔ docreader gRPC TLS + Token;Redis TLS;防 SSRF HTTP 客户端(覆盖数据源、URL 导入、重定向链等);密钥响应脱敏;技能沙箱隔离(Docker 需开启 / E2B / Cube)与按配置网络策略;OIDC ID Token JWKS 验签;可选复杂密码策略;仅白名单出站模式(`SSRF_DNS_WHITELIST_ONLY`) |-| 可观测性 | 集成 Langfuse(唯一追踪后端)以追踪 ReAct 循环、Token 消耗、工具调用和任务流水线;内置 Langfuse 风格的文档解析追踪时间线,逐阶段展示解析进度;系统管理员运行时任务队列面板(队列深度、按模型并发、失败任务排查与手动重试) |-| 任务管理 | MQ 异步任务,分阶段独立 Worker 池治理(core / 后处理 / enrichment / maintenance + 弹性共享池,Wiki 独立池)与按模型后台并发治理;版本升级自动数据库迁移 |-| 模型管理 | 集中配置,YAML 声明式内置模型配置,知识库级别模型选择,按模型思考模式与 Embedding 维度覆盖,交互式模型调试器,多空间共享内置模型,WeKnora Cloud 托管模型与文档解析;模型目录自动补全上下文窗口、最大输出、思考档位与视觉能力,提供实际调用预览与按模型协议覆盖 |--## 🧩 Chrome 插件--[**WeKnora Chrome 插件**](https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd)支持在浏览器中直接将网页内容采集到 WeKnora 知识库。选中文本、图片或整个页面,一键保存为知识条目,无需复制粘贴或手动上传文件。---## 📱 微信小程序--[**WeKnora 微信小程序**](./miniprogram/README.md) 提供轻量移动端客户端,支持配置 WeKnora API、选择知识库、导入 URL,并在微信内向知识库提问。---## 🦞 ClawHub Skill--[**WeKnora ClawHub Skill**](https://clawhub.ai/lyingbug/weknora) 是 WeKnora 发布在 ClawHub 平台上的技能。安装后,可通过 WeKnora REST API 上传文档(文件 / URL / Markdown)、执行混合检索(向量 + 关键词)以及管理知识条目。--- **文档导入** — 通过 Agent 上传文件、导入网页或写入 Markdown 知识-- **混合检索** — 在单个或多个知识库中进行向量 + 关键词混合搜索-- **知识管理** — 以编程方式浏览、编辑和删除知识条目--## 🐋 DeepSeek Harness 插件--[**`@wxg-prc-cpg/dsh-weknora`**](https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora) 是官方的 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)(`dsh`)插件([说明](./packages/dsh-weknora/README_CN.md))。harness 自身不带任何检索、向量或知识库能力,这个插件把你的文档接进编码 Agent:`dsh plugin --profile web add @wxg-prc-cpg/dsh-weknora`,指向一个部署,Agent 的工具集里就会出现四个只读工具。--- **`weknora_search`** — 混合检索,返回原文片段,每条都带可复用的 `knowledge_id`-- **`weknora_read_document`** — 把单个文档的分块按序拼回正文,支持翻页-- **`weknora_ask`** — WeKnora 自己带引用的成稿答案,走 RAG 或 ReAct 流水线-- **`weknora_list_knowledge_bases`** — 知识库名称与 id,便于 Agent 自己缩小检索范围--## 🚀 快速开始--### 🛠 环境要求--- [Docker](https://www.docker.com/) & [Docker Compose](https://docs.docker.com/compose/)-- [Git](https://git-scm.com/)--### 📦 安装与启动+| 安全 | API Key 与 MCP / 数据源凭据 AES-256-GCM 静态加密、支持平滑密钥轮换 · app ↔ docreader gRPC TLS + Token · Redis TLS · 防 SSRF HTTP 客户端(覆盖数据源、URL 导入、重定向链等)· 密钥响应脱敏 · 技能沙箱隔离(Docker 需开启 / E2B / Cube)与按配置网络策略 · OIDC ID Token JWKS 验签 · 可选复杂密码策略 · 仅白名单出站模式(`SSRF_DNS_WHITELIST_ONLY`) |+| 可观测性 | 集成 Langfuse(唯一追踪后端)以追踪 ReAct 循环、Token 消耗、工具调用和任务流水线 · 内置 Langfuse 风格的文档解析追踪时间线,逐阶段展示解析进度 · 系统管理员运行时任务队列面板(队列深度、按模型并发、失败任务排查与手动重试) |+| 任务管理 | MQ 异步任务,分阶段独立 Worker 池治理(core / 后处理 / enrichment / maintenance + 弹性共享池,Wiki 独立池)与按模型后台并发治理 · 版本升级自动数据库迁移 |+| 模型管理 | 集中配置,YAML 声明式内置模型配置,知识库级别模型选择,按模型思考模式与 Embedding 维度覆盖,交互式模型调试器,多空间共享内置模型,WeKnora Cloud 托管模型与文档解析 · 模型目录自动补全上下文窗口、最大输出、思考档位与视觉能力,提供实际调用预览与按模型协议覆盖 |++## 🔌 客户端与生态++| | 客户端 | 用途 |+|:-:|--------|------|+| ⌨️ | [**命令行 `weknora`**](./cli/README.md) | Agent 优先的命令行,覆盖完整 API,附带精选 MCP 工具面与内置 Agent Skills |+| 🔌 | [**内置 MCP Server**](https://weknora.weixin.qq.com/docs/03-features/08-mcp) | 把知识库开放给 Cursor、Claude 等 MCP 客户端 |+| 🌐 | [**本地浏览器(BrowserSkill)**](https://weknora.weixin.qq.com/docs/05-clients/09-local-browser) | 让智能体操作用户自己的 Chrome / Edge |+| 🧩 | [**Chrome 插件**](https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd) | 在浏览器中选中文本、图片或整个页面,一键保存为知识条目,无需复制粘贴或手动上传文件 |+| 📱 | [**微信小程序**](./miniprogram/README.md) | 轻量移动端:配置 WeKnora API、选择知识库、导入 URL,并在微信内向知识库提问 |+| 🦞 | [**ClawHub Skill**](https://clawhub.ai/lyingbug/weknora) | 发布在 ClawHub 上的 WeKnora 技能,通过 REST API 导入文档、混合检索与管理知识条目 |+| 🐋 | [**DeepSeek Harness 插件**](https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora) | 让 `dsh` 编码 Agent 只读访问你的文档 |+| 🪟 | [**网站嵌入 Widget**](https://weknora.weixin.qq.com/docs/03-features/13-embed-channel) | 将智能体发布到外部站点 |+| 🐹 | [**Go SDK**](https://weknora.weixin.qq.com/docs/05-clients/03-go-sdk) | 知识库、文档、会话等资源的 CRUD 与 SSE 流式问答 |+| 💬 | [**微信对话开放平台**](https://chatbot.weixin.qq.com) | 以 WeKnora 为核心的零代码托管问答,覆盖微信生态 |++### ⌨️ 命令行工具++`weknora` 是官方命令行工具,可在终端或 AI Agent 中驱动 API。它**以 Agent 为先**:每条命令默认输出稳定的 JSON 信封(带类型化错误码并映射到退出码),`--format text` 则面向人类阅读。它还提供精选的 MCP 工具面(`weknora mcp serve`),并内置 Agent Skills。```bash-git clone https://github.com/Tencent/WeKnora.git-cd WeKnora-cp .env.example .env # 按需编辑 .env,详见文件内注释-docker compose pull # 拉取最新镜像-docker compose up -d # 启动核心服务+weknora profile add prod --host https://kb.example.com --use+weknora auth login+weknora kb list+weknora link --kb my-knowledge-base # 绑定当前目录+weknora doc upload notes.md+weknora chat "总结一下设计文档"```-启动成功后访问 **http://localhost** 即可使用。--> 如需使用本地 Ollama 模型,请先运行 `ollama serve > /dev/null 2>&1 &`+在无界面 / CI 场景下,设置 `WEKNORA_API_KEY` 与 `WEKNORA_HOST` 即可跳过 `auth login`,不会有凭据写入磁盘。安装与 5 分钟上手见 [`cli/README.md`](./cli/README.md),AI Agent 依赖的操作约定见 [`cli/AGENTS.md`](./cli/AGENTS.md)。-Ollama 向量模型名、`OLLAMA_BASE_URL` 与内存说明见[配置文档](./website-docs/01-getting-started/04-configuration.md)。+### 🔌 MCP Server-### 🔄 版本升级--若已有部署并下载了更新的 release:--```bash-# 在 .env 中将 WEKNORA_VERSION 设为目标版本(如 0.7.0),或保持 latest-docker compose pull # 拉取与 WEKNORA_VERSION 匹配的镜像-docker compose up -d # 用新镜像重建容器-```+WeKnora 已内置 MCP Server:在「**设置 → 发布集成 → MCP Server**」新建端点,客户端通过 Streamable HTTP 连接 `/mcp/<endpoint_id>` 即可,详见 [MCP 文档](https://weknora.weixin.qq.com/docs/03-features/08-mcp)。[`mcp-server/`](./mcp-server/MCP_CONFIG.md) 下的独立 Python 服务已弃用,仅为兼容旧部署保留。-> 仅执行 `docker compose up -d` 会复用本地缓存镜像,可能导致 Web UI 显示版本与下载的 release 不一致。+<details>+<summary><b>🦞 ClawHub Skill</b></summary>-### 🔧 可选服务(Docker Compose Profile)+<br/>-按需添加 `--profile` 启动额外组件,多个 profile 可叠加使用:+[**WeKnora ClawHub Skill**](https://clawhub.ai/lyingbug/weknora) 是 WeKnora 发布在 ClawHub 平台上的技能。安装后,可通过 WeKnora REST API 上传文档(文件 / URL / Markdown)、执行混合检索(向量 + 关键词)以及管理知识条目。-| Profile | 说明 | 启动命令 |-|---------|------|----------|-| _(默认)_ | 核心服务 | `docker compose pull && docker compose up -d` |-| `full` | 全部功能 | `docker compose --profile full pull && docker compose --profile full up -d` |-| `neo4j` | 知识图谱 (Neo4j) | `docker compose --profile neo4j pull && docker compose --profile neo4j up -d` |-| `minio` | 对象存储 (MinIO) | `docker compose --profile minio pull && docker compose --profile minio up -d` |-| `langfuse` | 链路追踪 (Langfuse) | `docker compose --profile langfuse pull && docker compose --profile langfuse up -d` |+- **文档导入** —— 通过 Agent 上传文件、导入网页或写入 Markdown 知识+- **混合检索** —— 在单个或多个知识库中进行向量 + 关键词混合搜索+- **知识管理** —— 以编程方式浏览、编辑和删除知识条目-组合示例:`docker compose --profile neo4j --profile minio pull && docker compose --profile neo4j --profile minio up -d`+</details>-停止服务:`docker compose down`+<details>+<summary><b>🐋 DeepSeek Harness 插件</b></summary>-### 🌐 服务地址+<br/>-| 服务 | 地址 |-|------|------|-| Web UI | `http://localhost` |-| 后端 API | `http://localhost:8080` |-| 链路追踪 (Langfuse) | `http://localhost:3000` |--## 文档知识图谱--WeKnora 支持将文档转化为知识图谱,展示文档中不同段落之间的关联关系。开启知识图谱功能后,系统会分析并构建文档内部的语义关联网络,不仅帮助用户理解文档内容,还为索引和检索提供结构化支撑,提升检索结果的相关性和广度。+[**`@wxg-prc-cpg/dsh-weknora`**](https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora) 是官方的 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)(`dsh`)插件([说明](./packages/dsh-weknora/README_CN.md))。harness 自身不带任何检索、向量或知识库能力,这个插件把你的文档接进编码 Agent:`dsh plugin --profile web add @wxg-prc-cpg/dsh-weknora`,指向一个部署,Agent 的工具集里就会出现四个只读工具。-具体配置请参考 [知识图谱配置说明](./website-docs/03-features/09-knowledge-graph.md) 进行相关配置。+- **`weknora_search`** —— 混合检索,返回原文片段,每条都带可复用的 `knowledge_id`+- **`weknora_read_document`** —— 把单个文档的分块按序拼回正文,支持翻页+- **`weknora_ask`** —— WeKnora 自己带引用的成稿答案,走 RAG 或 ReAct 流水线+- **`weknora_list_knowledge_bases`** —— 知识库名称与 id,便于 Agent 自己缩小检索范围-## 配套MCP服务器+</details>-WeKnora 已内置 MCP Server:在「设置 → 发布集成 → MCP Server」新建端点,客户端通过 Streamable HTTP 连接 `/mcp/<endpoint_id>` 即可,详见 [MCP 文档](./website-docs/03-features/08-mcp.md)。[`mcp-server/`](./mcp-server/MCP_CONFIG.md) 下的独立 Python 服务已弃用,仅为兼容旧部署保留。+<details>+<summary><b>💬 微信对话开放平台</b></summary>-## 🔌 使用微信对话开放平台+<br/>WeKnora 作为[微信对话开放平台](https://chatbot.weixin.qq.com)的核心技术框架,提供更简便的使用方式:-- **零代码部署**:只需上传知识,即可在微信生态中快速部署智能问答服务,实现"即问即答"的体验-- **高效问题管理**:支持高频问题的独立分类管理,提供丰富的数据工具,确保回答精准可靠且易于维护-- **微信生态覆盖**:通过微信对话开放平台,WeKnora 的智能问答能力可无缝集成到公众号、小程序等微信场景中,提升用户交互体验---## 📘 文档+- **零代码部署** —— 只需上传知识,即可在微信生态中快速部署智能问答服务,实现"即问即答"的体验+- **高效问题管理** —— 支持高频问题的独立分类管理,提供丰富的数据工具,确保回答精准可靠且易于维护+- **微信生态覆盖** —— WeKnora 的智能问答能力可无缝集成到公众号、小程序等微信场景中,提升用户交互体验-**官方产品文档**:[`website-docs/`](./website-docs/README.md) —— 按「入门 → 架构 → 功能 → API → 客户端 → 开发」六个板块组织的完整文档,覆盖约 360 个 API 端点、约 150 个环境变量与 9 大扩展点。本目录同时是一个 VitePress 站点,`cd website-docs && npm install && npm run dev` 即可本地预览,也可用目录内的 `Dockerfile` 独立部署。+</details>-常见问题排查:[常见问题排查](./website-docs/01-getting-started/05-troubleshooting.md)+## 📚 文档-详细接口说明请参考:[API 文档](./website-docs/04-api/01-api-overview.md)+完整产品文档见 **[weknora.weixin.qq.com/docs](https://weknora.weixin.qq.com/docs/)**,按「入门 → 架构 → 功能 → API → 客户端 → 开发」六个板块组织,覆盖约 360 个 API 端点、约 150 个环境变量与 9 大扩展点。-产品能力:[产品介绍](./website-docs/01-getting-started/01-introduction.md)+| 从这里开始 | |+|------------|---|+| 👋 [产品介绍](https://weknora.weixin.qq.com/docs/01-getting-started/01-introduction) | WeKnora 能做什么 |+| 📦 [安装部署](https://weknora.weixin.qq.com/docs/01-getting-started/02-installation) | Docker Compose、Helm、Lite 与桌面端 |+| ⚙️ [配置说明](https://weknora.weixin.qq.com/docs/01-getting-started/04-configuration) | 环境变量与模型配置 |+| 🩺 [常见问题排查](https://weknora.weixin.qq.com/docs/01-getting-started/05-troubleshooting) | 常见问题与解决办法 |+| 📘 [API 文档](https://weknora.weixin.qq.com/docs/04-api/01-api-overview) | REST API 总览 |+| 🗒️ [版本说明](https://weknora.weixin.qq.com/docs/07-releases/v0.8.2) | 各版本变更详解 |-## 🧭 开发指南+## 🛠️ 开发指南-### ⚡ 快速开发模式(推荐)--如果你需要频繁修改代码,**不需要每次重新构建 Docker 镜像**!使用快速开发模式:+如果你需要频繁修改代码,**不需要每次重新构建 Docker 镜像**,使用快速开发模式即可:```bash-# 启动基础设施-make dev-start--# 启动后端(新终端)-make dev-app--# 启动前端(新终端)-make dev-frontend+make dev-start # 启动基础设施+make dev-app # 启动后端(新终端)+make dev-frontend # 启动前端(新终端)```-**开发优势:**-- ✅ 前端修改自动热重载(无需重启)-- ✅ 后端修改快速重启(5-10秒,支持 Air 热重载)+- ✅ 后端修改快速重启(5-10 秒,支持 Air 热重载)- ✅ 无需重新构建 Docker 镜像- ✅ 支持 IDE 断点调试-**详细文档:** [开发环境快速入门](./website-docs/06-development/01-dev-guide.md)+详细说明见[开发环境快速入门](https://weknora.weixin.qq.com/docs/06-development/01-dev-guide)。+文档站与产品主页的源码位于 [`website-docs/`](./website-docs/README.md)。使用 Node.js 24 运行 `cd website-docs && npm run setup && npm run build && npm run preview` 即可同时预览两者;统一的静态产物在 `/` 提供主页、在 `/docs/` 提供文档。Nginx 与 Docker 部署方式见该目录的 README。## 🤝 贡献指南欢迎通过 [Issue](https://github.com/Tencent/WeKnora/issues) 反馈问题或提交 Pull Request。-**流程:** Fork → 新建分支 → 提交更改 → 创建 PR+- **流程:** Fork → 新建分支 → 提交更改 → 创建 PR+- **规范:** 使用 `gofmt` 格式化代码,遵循 [Conventional Commits](https://www.conventionalcommits.org/) 提交(`feat:` / `fix:` / `docs:` / `test:` / `refactor:`)-**规范:** 使用 `gofmt` 格式化代码,遵循 [Conventional Commits](https://www.conventionalcommits.org/) 提交(`feat:` / `fix:` / `docs:` / `test:` / `refactor:`)+<details>+<summary><b>验证方式</b></summary>-### 验证方式+<br/>对于范围集中的 PR,优先验证本次改动涉及的文件和包:@@ -355,16 +443,9 @@ make test`make fmt` 会格式化整个 Go 仓库,因此请仅在工作区干净时运行,并检查产生的 diff。部分全量测试依赖本地基础设施或服务配置。如果全仓检查因无关的基线问题或环境依赖失败,请在 PR 中写明具体命令和错误,同时提供本次改动范围内通过的定向测试。-## 🔒 安全声明--**重要提示:** 从 v0.1.3 版本开始,WeKnora 提供了登录鉴权功能,以增强系统安全性。在生产环境部署时,我们强烈建议:--- 将 WeKnora 服务部署在内网/私有网络环境中,而非公网环境-- 避免将服务直接暴露在公网上,以防止重要信息泄露风险-- 为部署环境配置适当的防火墙规则和访问控制-- 定期更新到最新版本以获取安全补丁和改进+</details>-## 👥 贡献者+### 👥 贡献者感谢以下优秀的贡献者们:@@ -372,5 +453,4 @@ make test## 📄 许可证-本项目基于 [MIT](./LICENSE) 协议发布。-你可以自由使用、修改和分发本项目代码,但需保留原始版权声明。+本项目基于 [MIT](./LICENSE) 协议发布。你可以自由使用、修改和分发本项目代码,但需保留原始版权声明。