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

v0 return cache key in responses

Browse source
This commit is contained in:
Ishaan Jaff 2024-04-04 10:11:18 -07:00
parent 4b56f08cbe
commit 9dc4127576
2 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/proxy/proxy_server.py
View file

@ -3432,10 +3432,10 @@ async def chat_completion(
# Post Call Processing # Post Call Processing
data["litellm_status"] = "success" # used for alerting data["litellm_status"] = "success" # used for alerting
if hasattr(response, "_hidden_params"):
model_id = response._hidden_params.get("model_id", None) or "" hidden_params = getattr(response, "_hidden_params", {}) or {}
else: model_id = hidden_params.get("model_id", None) or ""
model_id = "" cache_key = hidden_params.get("cache_key", None) or ""
if ( if (
"stream" in data and data["stream"] == True "stream" in data and data["stream"] == True
@ -3451,6 +3451,7 @@ async def chat_completion(
) )
fastapi_response.headers["x-litellm-model-id"] = model_id fastapi_response.headers["x-litellm-model-id"] = model_id
fastapi_response.headers["x-litellm-cache-key"] = cache_key
### CALL HOOKS ### - modify outgoing data ### CALL HOOKS ### - modify outgoing data
response = await proxy_logging_obj.post_call_success_hook( response = await proxy_logging_obj.post_call_success_hook(

2
litellm/utils.py
View file

@ -3132,6 +3132,8 @@ def client(original_function):
target=logging_obj.success_handler, target=logging_obj.success_handler,
args=(cached_result, start_time, end_time, cache_hit), args=(cached_result, start_time, end_time, cache_hit),
).start() ).start()
cache_key = kwargs.get("preset_cache_key", None)
cached_result._hidden_params["cache_key"] = cache_key
return cached_result return cached_result
elif ( elif (
call_type == CallTypes.aembedding.value call_type == CallTypes.aembedding.value