github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-22 23:00:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

langchain[patch]: Add warning in react agent (#26980)

Browse Source
This commit is contained in:
William FH 2024-10-31 15:29:34 -07:00 committed by GitHub
parent 2f6254605d
commit b4cb2089a2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
libs/core/langchain_core/callbacks/manager.py
View File

@ -2502,7 +2502,8 @@ async def adispatch_custom_event(
): ):
print(event) print(event)
.. warning: If using python <= 3.10 and async, you MUST .. warning::
If using python <= 3.10 and async, you MUST
specify the `config` parameter or the function will raise an error. specify the `config` parameter or the function will raise an error.
This is due to a limitation in asyncio for python <= 3.10 that prevents This is due to a limitation in asyncio for python <= 3.10 that prevents
LangChain from automatically propagating the config object on the user's LangChain from automatically propagating the config object on the user's

6
libs/langchain/langchain/agents/react/agent.py
View File

@ -27,6 +27,12 @@ def create_react_agent(
Based on paper "ReAct: Synergizing Reasoning and Acting in Language Models" Based on paper "ReAct: Synergizing Reasoning and Acting in Language Models"
(https://arxiv.org/abs/2210.03629) (https://arxiv.org/abs/2210.03629)
.. warning::
This implementation is based on the foundational ReAct paper but is older and not well-suited for production applications.
For a more robust and feature-rich implementation, we recommend using the `create_react_agent` function from the LangGraph library.
See the [reference doc](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent)
for more information.
Args: Args:
llm: LLM to use as the agent. llm: LLM to use as the agent.
tools: Tools this agent has access to. tools: Tools this agent has access to.