mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-11 05:45:01 +00:00
community[patch]: Invoke callback prior to yielding token fix for Llamafile (#20365)
- [x] **PR title**: community[patch]: Invoke callback prior to yielding token fix for Llamafile - [x] **PR message**: - **Description:** Invoke callback prior to yielding token in stream method in community llamafile.py - **Issue:** https://github.com/langchain-ai/langchain/issues/16913 - **Dependencies:** None - **Twitter handle:** @bolun_zhang If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.
This commit is contained in:
parent
1b272fa2f4
commit
e7b1a44c5b
@ -297,9 +297,10 @@ class Llamafile(LLM):
|
||||
for raw_chunk in response.iter_lines(decode_unicode=True):
|
||||
content = self._get_chunk_content(raw_chunk)
|
||||
chunk = GenerationChunk(text=content)
|
||||
yield chunk
|
||||
|
||||
if run_manager:
|
||||
run_manager.on_llm_new_token(token=chunk.text)
|
||||
yield chunk
|
||||
|
||||
def _get_chunk_content(self, chunk: str) -> str:
|
||||
"""When streaming is turned on, llamafile server returns lines like:
|
||||
|
Loading…
Reference in New Issue
Block a user