Eugene Yurtsev feb41c5e28 langchain[patch]: Improve stream_log with AgentExecutor and Runnable Agent (#15792) ...

This PR fixes an issue where AgentExecutor with RunnableAgent does not allow users to see individual llm tokens if streaming=True is not set explicitly on the underlying chat model.

The majority of this PR is testing code:

1. Create a test chat model that makes it easier to test streaming and
supports AIMessages that include function invocation information.
2. Tests for the chat model
3. Tests for RunnableAgent (previously untested)
4. Tests for openai agent (previously untested)

2024-01-10 10:53:01 -05:00

..

cli

Make packages optional (#15727)

2024-01-08 17:09:21 -08:00

community

community[patch]: more deprecations (#15782)

2024-01-09 20:36:16 -08:00

core

core[patch]: release 0.1.9 (#15794)

2024-01-09 19:27:19 -08:00

experimental

experimental[patch]: loosen core max version (#15763)

2024-01-09 12:10:14 -05:00

langchain

langchain[patch]: Improve stream_log with AgentExecutor and Runnable Agent (#15792)

2024-01-10 10:53:01 -05:00

partners

mistralai[patch]: warn on stop token, fix on_llm_new_token (#15787)

2024-01-09 16:27:20 -08:00