PR #35543: fix(openai): avoid PydanticSerializationUnexpectedValue for structured output

• Repository: langchain-ai/langchain
• Author: JasonCZMeng
• State: closed | merged: True
• Link: https://github.com/langchain-ai/langchain/pull/35543

Description (problem / solution / changelog)

Summary

Exclude the parsed field from model_dump() in _create_chat_result() to prevent PydanticSerializationUnexpectedValue warnings when using structured output.

Fixes #35538

Root Cause

When OpenAI returns a parsed completion, message.parsed holds an arbitrary Pydantic BaseModel instance (the user's structured output schema). The existing code calls response.model_dump() which tries to serialize this into a dict — but the OpenAI SDK's ParsedChatCompletion types the parsed field as None, so Pydantic emits a serialization warning when it encounters a real model there.

Fix

Exclude parsed from the model_dump() call since it's already copied separately into additional_kwargs["parsed"] from the typed response object (at ~L1602). No data is lost.

Changes

libs/partners/openai/langchain_openai/chat_models/base.py

• Added exclude={"choices": {"__all__": {"message": {"parsed"}}}} to the model_dump() call in _create_chat_result()

libs/partners/openai/tests/unit_tests/chat_models/test_base.py

• Added test_create_chat_result_avoids_parsed_model_dump_warning() — mocks an OpenAI completion with a BaseModel in parsed and asserts no serialization warning is emitted

Changed files

• libs/partners/openai/langchain_openai/chat_models/base.py (modified, +7/-1)
• libs/partners/openai/tests/unit_tests/chat_models/test_base.py (modified, +43/-0)

PR #136: Update for notebooks in python-recipes

• Repository: redis-developer/redis-ai-resources
• Author: limjoobin
• State: closed | merged: True
• Link: https://github.com/redis-developer/redis-ai-resources/pull/136

Description (problem / solution / changelog)

This PR is a follow-up to previously merged PR #133 — finishing remaining notebook updates to resolve failed CI/CD tests.

Updates in this PR include:

• python-recipes/RAG/01_redisvl.ipynb - Updated dependencies related to langchain-text-splitters, migrated from the OpenAI Chat Completions API to the OpenAI Responses API, and did some minor refactors to the answer_question function for DRY-ness and to ensure consistent behaviour.

• python-recipes/RAG/02_langchain.ipynb - Very minor update to the documentation, fixed an outdated link.

• python-recipes/RAG/04_advanced_redisvl.ipynb - Updated dependencies related to langchain-text-spliiters and migrated from the OpenAI Chat Completions API to the Responses API.

• python-recipes/RAG/07_user_role_based_rag.ipynb - Updated dependencies related to langchain-text-splitters. Also wrapped some notebook cells in try-except blocks for clarity and to reduce confusion.

• python-recipes/vector-search/02_hybrid_search.ipynb - Updated versioning for redis-py dependencies and resolved error pertaining to unclear dtypes when using pandas DataFrames.

• python-recipes/vector-search/05_multivector_search.ipynb - Resolved error with redisvl import and included sentence-transformer import.

• python-recipes/agents/00_langgraph_redis_agentic_rag.ipynb - Updated dependencies related to langchain-core.tools.retriever and added Literal construct to specify exact outputs for agent.

Changed files

• python-recipes/RAG/01_redisvl.ipynb (modified, +202/-214)
• python-recipes/RAG/02_langchain.ipynb (modified, +4/-4)
• python-recipes/RAG/04_advanced_redisvl.ipynb (modified, +174/-148)
• python-recipes/RAG/07_user_role_based_rag.ipynb (modified, +136/-388)
• python-recipes/agents/00_langgraph_redis_agentic_rag.ipynb (modified, +47/-53)
• python-recipes/vector-search/02_hybrid_search.ipynb (modified, +799/-120)
• python-recipes/vector-search/05_multivector_search.ipynb (modified, +99/-53)