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

(feat) pass model_info, proxy_server_request to callback

Browse source
This commit is contained in:
ishaan-jaff 2023-12-08 14:06:38 -08:00
parent 72cca2e5a7
commit be94a8c478
2 changed files with 22 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/main.py
View file

@ -327,6 +327,8 @@ def completion(
litellm_logging_obj = kwargs.get('litellm_logging_obj', None)
id = kwargs.get('id', None)
metadata = kwargs.get('metadata', None)
model_info = kwargs.get('model_info', None)
proxy_server_request = kwargs.get('proxy_server_request', None)
fallbacks = kwargs.get('fallbacks', None)
headers = kwargs.get("headers", None)
num_retries = kwargs.get("num_retries", None) ## deprecated
@ -347,7 +349,7 @@ def completion(
client = kwargs.get("client", None)
######## end of unpacking kwargs ###########
openai_params = ["functions", "function_call", "temperature", "temperature", "top_p", "n", "stream", "stop", "max_tokens", "presence_penalty", "frequency_penalty", "logit_bias", "user", "request_timeout", "api_base", "api_version", "api_key", "deployment_id", "organization", "base_url", "default_headers", "timeout", "response_format", "seed", "tools", "tool_choice", "max_retries"]
litellm_params = ["metadata", "acompletion", "caching", "return_async", "mock_response", "api_key", "api_version", "api_base", "force_timeout", "logger_fn", "verbose", "custom_llm_provider", "litellm_logging_obj", "litellm_call_id", "use_client", "id", "fallbacks", "azure", "headers", "model_list", "num_retries", "context_window_fallback_dict", "roles", "final_prompt_value", "bos_token", "eos_token", "request_timeout", "complete_response", "self", "client", "rpm", "tpm", "input_cost_per_token", "output_cost_per_token", "hf_model_name"]
litellm_params = ["metadata", "acompletion", "caching", "return_async", "mock_response", "api_key", "api_version", "api_base", "force_timeout", "logger_fn", "verbose", "custom_llm_provider", "litellm_logging_obj", "litellm_call_id", "use_client", "id", "fallbacks", "azure", "headers", "model_list", "num_retries", "context_window_fallback_dict", "roles", "final_prompt_value", "bos_token", "eos_token", "request_timeout", "complete_response", "self", "client", "rpm", "tpm", "input_cost_per_token", "output_cost_per_token", "hf_model_name", "model_info", "proxy_server_request"]
default_params = openai_params + litellm_params
non_default_params = {k: v for k,v in kwargs.items() if k not in default_params} # model-specific params - pass them straight to the model/provider
if mock_response:
@ -454,7 +456,9 @@ def completion(
litellm_call_id=kwargs.get('litellm_call_id', None),
model_alias_map=litellm.model_alias_map,
completion_call_id=id,
metadata=metadata
metadata=metadata,
model_info=model_info,
proxy_server_request=proxy_server_request
)
logging.update_environment_variables(model=model, user=user, optional_params=optional_params, litellm_params=litellm_params)
if custom_llm_provider == "azure":

15
litellm/proxy/proxy_server.py
View file

@ -967,6 +967,14 @@ async def chat_completion(request: Request, model: Optional[str] = None, user_ap
data = {}
data = await request.json() # type: ignore
# Include original request and headers in the data
data["proxy_server_request"] = {
"url": str(request.url),
"method": request.method,
"headers": dict(request.headers),
"body": copy.copy(data) # use copy instead of deepcopy
}
print_verbose(f"receiving data: {data}")
data["model"] = (
general_settings.get("completion_model", None) # server default
@ -1059,6 +1067,13 @@ async def embeddings(request: Request, user_api_key_dict: UserAPIKeyAuth = Depen
body = await request.body()
data = orjson.loads(body)
# Include original request and headers in the data
data["proxy_server_request"] = {
"url": str(request.url),
"method": request.method,
"headers": dict(request.headers),
"body": copy.copy(data) # use copy instead of deepcopy
}
data["user"] = user_api_key_dict.user_id
data["model"] = (