phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(utils.py): return finish reason for last vertex ai chunk

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-06 09:21:03 -08:00
parent f2ef32bcee
commit 3afa5230d6
2 changed files with 52 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

31
litellm/proxy/proxy_server.py
View file

@ -1746,7 +1746,33 @@ async def async_data_generator(response, user_api_key_dict):
done_message = "[DONE]"
yield f"data: {done_message}\n\n"
except Exception as e:
yield f"data: {str(e)}\n\n"
traceback.print_exc()
await proxy_logging_obj.post_call_failure_hook(
user_api_key_dict=user_api_key_dict, original_exception=e
)
verbose_proxy_logger.debug(
f"\033[1;31mAn error occurred: {e}\n\n Debug this by setting `--debug`, e.g. `litellm --model gpt-3.5-turbo --debug`"
)
router_model_names = (
[m["model_name"] for m in llm_model_list]
if llm_model_list is not None
else []
)
if user_debug:
traceback.print_exc()
if isinstance(e, HTTPException):
raise e
else:
error_traceback = traceback.format_exc()
error_msg = f"{str(e)}\n\n{error_traceback}"
raise ProxyException(
message=getattr(e, "message", error_msg),
type=getattr(e, "type", "None"),
param=getattr(e, "param", "None"),
code=getattr(e, "status_code", 500),
)
def select_data_generator(response, user_api_key_dict):
@ -1754,7 +1780,7 @@ def select_data_generator(response, user_api_key_dict):
# since boto3 - sagemaker does not support async calls, we should use a sync data_generator
if hasattr(
response, "custom_llm_provider"
) and response.custom_llm_provider in ["sagemaker", "together_ai"]:
) and response.custom_llm_provider in ["sagemaker"]:
return data_generator(
response=response,
)
@ -2239,7 +2265,6 @@ async def chat_completion(
selected_data_generator = select_data_generator(
response=response, user_api_key_dict=user_api_key_dict
)
return StreamingResponse(
selected_data_generator,
media_type="text/event-stream",