Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-18 09:25:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Invoke callback prior to yielding token (#17348)

Browse Source 
**Description:** Invoke callback prior to yielding token in stream
method for Ollama.
**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 22:22:55 -05:00 committed by GitHub
parent ab025507bc
commit e135dc70c3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
libs/community/langchain_community/chat_models/ollama.py
View File

@ -313,12 +313,12 @@ class ChatOllama(BaseChatModel, _OllamaCommon):
for stream_resp in self._create_chat_stream(messages, stop, **kwargs): for stream_resp in self._create_chat_stream(messages, stop, **kwargs):
if stream_resp: if stream_resp:
chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp) chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp)
yield chunk
if run_manager: if run_manager:
run_manager.on_llm_new_token( run_manager.on_llm_new_token(
chunk.text, chunk.text,
verbose=self.verbose, verbose=self.verbose,
) )
yield chunk
except OllamaEndpointNotFoundError: except OllamaEndpointNotFoundError:
yield from self._legacy_stream(messages, stop, **kwargs) yield from self._legacy_stream(messages, stop, **kwargs)
@ -332,12 +332,12 @@ class ChatOllama(BaseChatModel, _OllamaCommon):
async for stream_resp in self._acreate_chat_stream(messages, stop, **kwargs): async for stream_resp in self._acreate_chat_stream(messages, stop, **kwargs):
if stream_resp: if stream_resp:
chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp) chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp)
yield chunk
if run_manager: if run_manager:
await run_manager.on_llm_new_token( await run_manager.on_llm_new_token(
chunk.text, chunk.text,
verbose=self.verbose, verbose=self.verbose,
) )
yield chunk
@deprecated("0.0.3", alternative="_stream") @deprecated("0.0.3", alternative="_stream")
def _legacy_stream( def _legacy_stream(
@ -351,9 +351,9 @@ class ChatOllama(BaseChatModel, _OllamaCommon):
for stream_resp in self._create_generate_stream(prompt, stop, **kwargs): for stream_resp in self._create_generate_stream(prompt, stop, **kwargs):
if stream_resp: if stream_resp:
chunk = _stream_response_to_chat_generation_chunk(stream_resp) chunk = _stream_response_to_chat_generation_chunk(stream_resp)
yield chunk
if run_manager: if run_manager:
run_manager.on_llm_new_token( run_manager.on_llm_new_token(
chunk.text, chunk.text,
verbose=self.verbose, verbose=self.verbose,
) )
yield chunk