Yassin NouhandGitHub
82905297fd
## Description This PR enhances the state-model documentation by adding comprehensive examples for advanced Pydantic usage in LangGraph. It addresses issue #2745 regarding the need for better documentation of Pydantic schema behavior. ### Changes - Added new section on Advanced Pydantic Model Usage - Added examples for serialization behavior with nested models - Added section on runtime type coercion with examples - Added documentation for proper message type handling (BaseMessage vs AnyMessage) - Updated Pydantic error URLs to latest version ### Related Issues Closes #2745 ### Testing - All notebook cells have been executed and outputs verified - Examples demonstrate proper usage patterns - Error cases are properly documented ### Documentation The changes are documentation-focused and include: - New examples for complex Pydantic models - Runtime coercion behavior examples - Message type handling best practices ### Reviewers @eyurtsev
Setup
To setup requirements for building docs you can run:
poetry install --with test
Serving documentation locally
To run the documentation server locally you can run:
make serve-docs
Execute notebooks
If you would like to automatically execute all of the notebooks, to mimic the "Run notebooks" GHA, you can run:
python _scripts/prepare_notebooks_for_ci.py
./_scripts/execute_notebooks.sh
Note: if you want to run the notebooks without %pip install cells, you can run:
python _scripts/prepare_notebooks_for_ci.py --comment-install-cells
./_scripts/execute_notebooks.sh
prepare_notebooks_for_ci.py script will add VCR cassette context manager for each cell in the notebook, so that:
- when the notebook is run for the first time, cells with network requests will be recorded to a VCR cassette file
- when the notebook is run subsequently, the cells with network requests will be replayed from the cassettes
Adding new notebooks
If you are adding a notebook with API requests, it's recommended to record network requests so that they can be subsequently replayed. If this is not done, the notebook runner will make API requests every time the notebook is run, which can be costly and slow.
To record network requests, please make sure to first run prepare_notebooks_for_ci.py script.
Then, run
jupyter execute <path_to_notebook>
Once the notebook is executed, you should see the new VCR cassettes recorded in cassettes directory and discard the updated notebook.
Updating existing notebooks
If you are updating an existing notebook, please make sure to remove any existing cassettes for the notebook in cassettes directory (each cassette is prefixed with the notebook name), and then run the steps from the "Adding new notebooks" section above.
To delete cassettes for a notebook, you can run:
rm cassettes/<notebook_name>*