phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(ollama.py): fix ollama async streaming for /completions calls

Browse source
This commit is contained in:
Krrish Dholakia 2023-12-15 09:28:18 -08:00
parent 04825115df
commit 3d6ade8f26
3 changed files with 70 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/main.py
View file

@ -209,7 +209,7 @@ async def _async_streaming(response, model, custom_llm_provider, args):
print_verbose(f"line in async streaming: {line}")
yield line
except Exception as e:
print_verbose(f"error raised _async_streaming: {str(e)}")
print_verbose(f"error raised _async_streaming: {traceback.format_exc()}")
raise exception_type(
model=model, custom_llm_provider=custom_llm_provider, original_exception=e, completion_kwargs=args,
)
@ -2378,6 +2378,8 @@ def stream_chunk_builder(chunks: list, messages: Optional[list]=None):
completion_output = combined_content
elif len(combined_arguments) > 0:
completion_output = combined_arguments
else:
completion_output = ""
# # Update usage information if needed
try:
response["usage"]["prompt_tokens"] = token_counter(model=model, messages=messages)