mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 11:14:04 +00:00
71f659d26b
* refactor: initial commit moving watsonx_text to base_llm_http_handler + clarifying new provider directory structure * refactor(watsonx/completion/handler.py): move to using base llm http handler removes 'requests' library usage * fix(watsonx_text/transformation.py): fix result transformation migrates to transformation.py, for usage with base llm http handler * fix(streaming_handler.py): migrate watsonx streaming to transformation.py ensures streaming works with base llm http handler * fix(streaming_handler.py): fix streaming linting errors and remove watsonx conditional logic * fix(watsonx/): fix chat route post completion route refactor * refactor(watsonx/embed): refactor watsonx to use base llm http handler for embedding calls as well * refactor(base.py): remove requests library usage from litellm * build(pyproject.toml): remove requests library usage * fix: fix linting errors * fix: fix linting errors * fix(types/utils.py): fix validation errors for modelresponsestream * fix(replicate/handler.py): fix linting errors * fix(litellm_logging.py): handle modelresponsestream object * fix(streaming_handler.py): fix modelresponsestream args * fix: remove unused imports * test: fix test * fix: fix test * test: fix test * test: fix tests * test: fix test * test: fix patch target * test: fix test
87 lines
2.4 KiB
Python
87 lines
2.4 KiB
Python
from abc import ABC, abstractmethod
|
|
from typing import TYPE_CHECKING, Any, List, Optional
|
|
|
|
import httpx
|
|
|
|
from litellm.llms.base_llm.chat.transformation import BaseConfig
|
|
from litellm.types.llms.openai import AllEmbeddingInputValues, AllMessageValues
|
|
from litellm.types.utils import EmbeddingResponse, ModelResponse
|
|
|
|
if TYPE_CHECKING:
|
|
from litellm.litellm_core_utils.litellm_logging import Logging as _LiteLLMLoggingObj
|
|
|
|
LiteLLMLoggingObj = _LiteLLMLoggingObj
|
|
else:
|
|
LiteLLMLoggingObj = Any
|
|
|
|
|
|
class BaseEmbeddingConfig(BaseConfig, ABC):
|
|
@abstractmethod
|
|
def transform_embedding_request(
|
|
self,
|
|
model: str,
|
|
input: AllEmbeddingInputValues,
|
|
optional_params: dict,
|
|
headers: dict,
|
|
) -> dict:
|
|
return {}
|
|
|
|
@abstractmethod
|
|
def transform_embedding_response(
|
|
self,
|
|
model: str,
|
|
raw_response: httpx.Response,
|
|
model_response: EmbeddingResponse,
|
|
logging_obj: LiteLLMLoggingObj,
|
|
api_key: Optional[str],
|
|
request_data: dict,
|
|
optional_params: dict,
|
|
litellm_params: dict,
|
|
) -> EmbeddingResponse:
|
|
return model_response
|
|
|
|
def get_complete_url(
|
|
self,
|
|
api_base: Optional[str],
|
|
model: str,
|
|
optional_params: dict,
|
|
stream: Optional[bool] = None,
|
|
) -> str:
|
|
"""
|
|
OPTIONAL
|
|
|
|
Get the complete url for the request
|
|
|
|
Some providers need `model` in `api_base`
|
|
"""
|
|
return api_base or ""
|
|
|
|
def transform_request(
|
|
self,
|
|
model: str,
|
|
messages: List[AllMessageValues],
|
|
optional_params: dict,
|
|
litellm_params: dict,
|
|
headers: dict,
|
|
) -> dict:
|
|
raise NotImplementedError(
|
|
"EmbeddingConfig does not need a request transformation for chat models"
|
|
)
|
|
|
|
def transform_response(
|
|
self,
|
|
model: str,
|
|
raw_response: httpx.Response,
|
|
model_response: ModelResponse,
|
|
logging_obj: LiteLLMLoggingObj,
|
|
request_data: dict,
|
|
messages: List[AllMessageValues],
|
|
optional_params: dict,
|
|
litellm_params: dict,
|
|
encoding: Any,
|
|
api_key: Optional[str] = None,
|
|
json_mode: Optional[bool] = None,
|
|
) -> ModelResponse:
|
|
raise NotImplementedError(
|
|
"EmbeddingConfig does not need a response transformation for chat models"
|
|
)
|