phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

anthropic prompt caching cost tracking (#5453)

Browse source 
* fix(utils.py): support 'drop_params' for embedding requests

Fixes https://github.com/BerriAI/litellm/issues/5444

* feat(anthropic/cost_calculation.py): Support calculating cost for prompt caching on anthropic

* feat(types/utils.py): allows us to migrate to openai's equivalent, once that comes out

* fix: fix linting errors

* test: mark flaky test
This commit is contained in:
Krish Dholakia 2024-08-31 14:09:35 -07:00 • committed by Ishaan Jaff
parent 6aaa7a75cd
commit aa9f1896c6
17 changed files with 432 additions and 84 deletions
Download patch file Download diff file Expand all files Collapse all files

13
litellm/llms/base.py
View file

@ -1,11 +1,14 @@
## This is a template base class to be used for adding new LLM providers via API calls
from typing import Any, Optional, Union
import httpx
import requests
import litellm
import httpx, requests
from typing import Optional, Union
from litellm.litellm_core_utils.litellm_logging import Logging
class BaseLLM:
_client_session: Optional[httpx.Client] = None
def process_response(
@ -14,7 +17,7 @@ class BaseLLM:
response: Union[requests.Response, httpx.Response],
model_response: litellm.utils.ModelResponse,
stream: bool,
logging_obj: Logging,
logging_obj: Any,
optional_params: dict,
api_key: str,
data: Union[dict, str],
@ -33,7 +36,7 @@ class BaseLLM:
response: Union[requests.Response, httpx.Response],
model_response: litellm.utils.TextCompletionResponse,
stream: bool,
logging_obj: Logging,
logging_obj: Any,
optional_params: dict,
api_key: str,
data: Union[dict, str],