phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(fix) proxy - streaming sagemaker

Browse source
This commit is contained in:
ishaan-jaff 2024-01-23 11:12:16 -08:00
parent 01a2514b98
commit bd37a9cb5e
2 changed files with 19 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

26
litellm/proxy/proxy_server.py
View file

@ -1658,11 +1658,16 @@ async def completion(
"stream" in data and data["stream"] == True
): # use generate_responses to stream responses
custom_headers = {"x-litellm-model-id": model_id}
return StreamingResponse(
async_data_generator(
user_api_key_dict=user_api_key_dict,
stream_content = async_data_generator(
user_api_key_dict=user_api_key_dict,
response=response,
)
if response.custom_llm_provider == "sagemaker":
stream_content = data_generator(
response=response,
),
)
return StreamingResponse(
stream_content,
media_type="text/event-stream",
headers=custom_headers,
)
@ -1820,11 +1825,16 @@ async def chat_completion(
"stream" in data and data["stream"] == True
): # use generate_responses to stream responses
custom_headers = {"x-litellm-model-id": model_id}
return StreamingResponse(
async_data_generator(
user_api_key_dict=user_api_key_dict,
stream_content = async_data_generator(
user_api_key_dict=user_api_key_dict,
response=response,
)
if response.custom_llm_provider == "sagemaker":
stream_content = data_generator(
response=response,
),
)
return StreamingResponse(
stream_content,
media_type="text/event-stream",
headers=custom_headers,
)