phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(proxy_server.py): return original model response via response headers - /v1/completions

Browse source 
to help devs with debugging
This commit is contained in:
Krrish Dholakia 2024-04-03 13:05:43 -07:00
parent f17dd68df3
commit 15e0099948
4 changed files with 44 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/proxy/proxy_server.py
View file

@ -3126,14 +3126,21 @@ async def completion(
if hasattr(response, "_hidden_params"):
model_id = response._hidden_params.get("model_id", None) or ""
original_response = (
response._hidden_params.get("original_response", None) or ""
)
else:
model_id = ""
original_response = ""
verbose_proxy_logger.debug("final response: %s", response)
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-original-response": original_response,
}
selected_data_generator = select_data_generator(
response=response, user_api_key_dict=user_api_key_dict
)
@ -3145,6 +3152,7 @@ async def completion(
)
fastapi_response.headers["x-litellm-model-id"] = model_id
fastapi_response.headers["x-litellm-original-response"] = original_response
return response
except Exception as e:
verbose_proxy_logger.debug("EXCEPTION RAISED IN PROXY MAIN.PY")