mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-27 21:45:08 +00:00
Following https://github.com/langchain-ai/langchain/pull/30909: need to retain "empty" reasoning output when streaming, e.g., ```python {'id': 'rs_...', 'summary': [], 'type': 'reasoning'} ``` Tested by existing integration tests, which are currently failing. |
||
---|---|---|
.. | ||
chat_models | ||
embeddings | ||
llms | ||
output_parsers | ||
__init__.py | ||
py.typed |