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

return cache key in streming responses

Browse source
This commit is contained in:
Ishaan Jaff 2024-04-04 11:00:00 -07:00
parent c4cb0afa98
commit 7e1d5c81b4
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
litellm/proxy/proxy_server.py
View file

@ -3440,7 +3440,10 @@ async def chat_completion(
if (
"stream" in data and data["stream"] == True
): # use generate_responses to stream responses
custom_headers = {"x-litellm-model-id": model_id}
custom_headers = {
"x-litellm-model-id": model_id,
"x-litellm-cache-key": cache_key,
}
selected_data_generator = select_data_generator(
response=response, user_api_key_dict=user_api_key_dict
)