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

use route_request for making llm call

Browse source
This commit is contained in:
Ishaan Jaff 2024-08-15 08:16:44 -07:00
parent eb6a0a32f1
commit fdd6664420
3 changed files with 117 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

70
litellm/proxy/proxy_server.py
View file

@ -187,6 +187,7 @@ from litellm.proxy.openai_files_endpoints.files_endpoints import set_files_confi
from litellm.proxy.pass_through_endpoints.pass_through_endpoints import (
initialize_pass_through_endpoints,
)
from litellm.proxy.route_llm_request import route_request
from litellm.proxy.secret_managers.aws_secret_manager import (
load_aws_kms,
load_aws_secret_manager,
@ -3006,68 +3007,13 @@ async def chat_completion(
### ROUTE THE REQUEST ###
# Do not change this - it should be a constant time fetch - ALWAYS
router_model_names = llm_router.model_names if llm_router is not None else []
# skip router if user passed their key
if "api_key" in data:
tasks.append(litellm.acompletion(**data))
elif "," in data["model"] and llm_router is not None:
if (
data.get("fastest_response", None) is not None
and data["fastest_response"] == True
):
tasks.append(llm_router.abatch_completion_fastest_response(**data))
else:
_models_csv_string = data.pop("model")
_models = [model.strip() for model in _models_csv_string.split(",")]
tasks.append(llm_router.abatch_completion(models=_models, **data))
elif "user_config" in data:
# initialize a new router instance. make request using this Router
router_config = data.pop("user_config")
user_router = litellm.Router(**router_config)
tasks.append(user_router.acompletion(**data))
elif (
llm_router is not None and data["model"] in router_model_names
): # model in router model list
tasks.append(llm_router.acompletion(**data))
elif (
llm_router is not None and data["model"] in llm_router.get_model_ids()
): # model in router model list
tasks.append(llm_router.acompletion(**data))
elif (
llm_router is not None
and llm_router.model_group_alias is not None
and data["model"] in llm_router.model_group_alias
): # model set in model_group_alias
tasks.append(llm_router.acompletion(**data))
elif (
llm_router is not None and data["model"] in llm_router.deployment_names
): # model in router deployments, calling a specific deployment on the router
tasks.append(llm_router.acompletion(**data, specific_deployment=True))
elif (
llm_router is not None
and data["model"] not in router_model_names
and llm_router.router_general_settings.pass_through_all_models is True
):
tasks.append(litellm.acompletion(**data))
elif (
llm_router is not None
and data["model"] not in router_model_names
and (
llm_router.default_deployment is not None
or len(llm_router.provider_default_deployments) > 0
)
): # model in router deployments, calling a specific deployment on the router
tasks.append(llm_router.acompletion(**data))
elif user_model is not None: # `litellm --model <your-model-name>`
tasks.append(litellm.acompletion(**data))
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail={
"error": "chat_completion: Invalid model name passed in model="
+ data.get("model", "")
},
)
llm_call = await route_request(
data=data,
route_type="acompletion",
llm_router=llm_router,
user_model=user_model,
)
tasks.append(llm_call)
# wait for call to end
llm_responses = asyncio.gather(