Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.
Fix Quick Start CLI commands: add required bundle subcommand and path
Louis Choquel2a4a40b9f7ec
diff --git a/README.md b/README.mdindex bace37b3c..d455f75b0 100644--- a/README.md+++ b/README.md@@ -75,8 +75,8 @@ Then:1. Install the [VS Code extension](https://go.pipelex.com/vscode) for `.mthds` syntax highlighting2. Browse methods on the [MTHDS Hub](https://mthds.sh) for inspiration3. Author your own `.mthds` methods based on these examples-4. Validate with `pipelex validate`-5. Run them with `pipelex run`+4. Validate with `pipelex validate bundle your_method.mthds`+5. Run them with `pipelex run bundle your_method.mthds`6. View the flowchart in VS Code thanks to the extension7. Use the [`mthds` npm package](https://github.com/mthds-ai/mthds-js) to package and publish methods on the hub@@ -369,10 +369,10 @@ Create an `inputs.json` file with your PDF URLs:```pythonimport asyncio-from pipelex.pipeline.runner import PipelexRunner+from pipelex.core.stuffs.document_content import DocumentContentfrom pipelex.pipelex import Pipelex-from pipelex.content import DocumentContent-# Generated by: pipelex generate structures cv_batch_screening.mthds+from pipelex.pipeline.runner import PipelexRunner+# Generated by: `pipelex build structures bundle cv_batch_screening.mthds`from structures.cv_batch_screening__candidate_match import CandidateMatchasync def run_pipeline() -> list[CandidateMatch]:@@ -381,7 +381,7 @@ async def run_pipeline() -> list[CandidateMatch]:pipe_code="batch_analyze_cvs_for_job_offer",inputs={"cvs": {- "concept": "native.Document",+ "concept": "Document","content": [DocumentContent(url="https://pipelex-web.s3.amazonaws.com/demo/John-Doe-CV.pdf"),DocumentContent(path="inputs/Jane-Smith-CV.pdf"),