github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-04 10:42:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Invoke callback prior to yielding token (#17346)

Browse Source 
**Description:** Invoke callback prior to yielding token in stream
method for watsonx.
**Issue:** [Callback for on_llm_new_token should be invoked before the
token is yielded by the model
#16913](https://github.com/langchain-ai/langchain/issues/16913)

Co-authored-by: Robby <h0rv@users.noreply.github.com>
This commit is contained in:
Robby 2024-02-12 19:36:33 -05:00 committed by GitHub
parent ce9a68791b
commit 0653aa469a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libs/community/langchain_community/llms/watsonxllm.py
View File

@ -397,7 +397,7 @@ class WatsonxLLM(BaseLLM):
prompt=prompt, raw_response=True, params=params prompt=prompt, raw_response=True, params=params
): ):
chunk = self._stream_response_to_generation_chunk(stream_resp) chunk = self._stream_response_to_generation_chunk(stream_resp)
yield chunk
if run_manager: if run_manager:
run_manager.on_llm_new_token(chunk.text, chunk=chunk) run_manager.on_llm_new_token(chunk.text, chunk=chunk)
yield chunk