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

Proxy: Add x-litellm-call-id response header

Browse source 
This gives the value of `logging_obj.litellm_call_id` and one particular use of
this is to correlate the HTTP response from a request with a trace in an LLM
logging tool like Langfuse, Langsmith, etc.

For example, if a user in my environment (w/ Langfuse) gets back this in the
response headers:

```
x-litellm-call-id: ffcb49e7-bd6e-4e56-9c08-a7243802b26e
```

then they know that they can see the trace for this request in Langfuse by
visiting https://langfuse.domain.com/trace/ffcb49e7-bd6e-4e56-9c08-a7243802b26e

They can also use this ID to submit scores for this request to the Langfuse
scoring API.
This commit is contained in:
Marc Abramowitz 2024-07-10 16:05:37 -07:00
parent aace0b22a3
commit 3a2cb151aa
1 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/proxy/proxy_server.py
View file

@ -444,6 +444,7 @@ def _get_pydantic_json_dict(pydantic_obj: BaseModel) -> dict:
def get_custom_headers(
*,
user_api_key_dict: UserAPIKeyAuth,
call_id: Optional[str] = None,
model_id: Optional[str] = None,
cache_key: Optional[str] = None,
api_base: Optional[str] = None,
@ -455,6 +456,7 @@ def get_custom_headers(
) -> dict:
exclude_values = {"", None}
headers = {
"x-litellm-call-id": call_id,
"x-litellm-model-id": model_id,
"x-litellm-cache-key": cache_key,
"x-litellm-model-api-base": api_base,
@ -2895,6 +2897,7 @@ async def chat_completion(
): # use generate_responses to stream responses
custom_headers = get_custom_headers(
user_api_key_dict=user_api_key_dict,
call_id=logging_obj.litellm_call_id,
model_id=model_id,
cache_key=cache_key,
api_base=api_base,
@ -2925,6 +2928,7 @@ async def chat_completion(
fastapi_response.headers.update(
get_custom_headers(
user_api_key_dict=user_api_key_dict,
call_id=logging_obj.litellm_call_id,
model_id=model_id,
cache_key=cache_key,
api_base=api_base,
@ -3138,6 +3142,7 @@ async def completion(
): # use generate_responses to stream responses
custom_headers = get_custom_headers(
user_api_key_dict=user_api_key_dict,
call_id=logging_obj.litellm_call_id,
model_id=model_id,
cache_key=cache_key,
api_base=api_base,
@ -3158,6 +3163,7 @@ async def completion(
fastapi_response.headers.update(
get_custom_headers(
user_api_key_dict=user_api_key_dict,
call_id=logging_obj.litellm_call_id,
model_id=model_id,
cache_key=cache_key,
api_base=api_base,