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

fix(utils.py): support raw response headers for streaming requests

Browse source
This commit is contained in:
Krrish Dholakia 2024-07-23 11:58:58 -07:00
parent d1ffb4de5f
commit f64a3309d1
5 changed files with 60 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/proxy/proxy_server.py
View file

@ -2909,6 +2909,7 @@ async def chat_completion(
fastest_response_batch_completion = hidden_params.get(
"fastest_response_batch_completion", None
)
additional_headers: dict = hidden_params.get("additional_headers", {}) or {}
# Post Call Processing
if llm_router is not None:
@ -2931,6 +2932,7 @@ async def chat_completion(
response_cost=response_cost,
model_region=getattr(user_api_key_dict, "allowed_model_region", ""),
fastest_response_batch_completion=fastest_response_batch_completion,
**additional_headers,
)
selected_data_generator = select_data_generator(
response=response,
@ -2948,8 +2950,10 @@ async def chat_completion(
user_api_key_dict=user_api_key_dict, response=response
)
hidden_params = getattr(response, "_hidden_params", {}) or {}
additional_headers: dict = hidden_params.get("additional_headers", {}) or {}
hidden_params = (
getattr(response, "_hidden_params", {}) or {}
) # get any updated response headers
additional_headers = hidden_params.get("additional_headers", {}) or {}
fastapi_response.headers.update(
get_custom_headers(