phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[Feat] Support for all litellm providers on Responses API (works with Codex) - Anthropic, Bedrock API, VertexAI, Ollama (#10132)

Browse source 
* transform request

* basic handler for LiteLLMCompletionTransformationHandler

* complete transform litellm to responses api

* fixes to test

* fix stream=True

* fix streaming iterator

* fixes for transformation

* fixes for anthropic codex support

* fix pass response_api_optional_params

* test anthropic responses api tools

* update responses types

* working codex with litellm

* add session handler

* fixes streaming iterator

* fix handler

* add litellm codex example

* fix code quality

* test fix

* docs litellm codex

* litellm codexdoc

* docs openai codex with litellm

* docs litellm openai codex

* litellm codex

* linting fixes for transforming responses API

* fix import error

* fix responses api test

* add sync iterator support for responses api
This commit is contained in:
Ishaan Jaff 2025-04-18 19:53:59 -07:00 • committed by GitHub
parent 3e87ec4f16
commit 3d5022bd79
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 1282 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

115
litellm/responses/litellm_completion_transformation/handler.py Normal file
View file

@ -0,0 +1,115 @@
"""
Handler for transforming responses api requests to litellm.completion requests
"""
from typing import Any, Coroutine, Optional, Union
import litellm
from litellm.responses.litellm_completion_transformation.streaming_iterator import (
LiteLLMCompletionStreamingIterator,
)
from litellm.responses.litellm_completion_transformation.transformation import (
LiteLLMCompletionResponsesConfig,
)
from litellm.responses.streaming_iterator import BaseResponsesAPIStreamingIterator
from litellm.types.llms.openai import (
ResponseInputParam,
ResponsesAPIOptionalRequestParams,
ResponsesAPIResponse,
)
from litellm.types.utils import ModelResponse
class LiteLLMCompletionTransformationHandler:
def response_api_handler(
self,
model: str,
input: Union[str, ResponseInputParam],
responses_api_request: ResponsesAPIOptionalRequestParams,
custom_llm_provider: Optional[str] = None,
_is_async: bool = False,
stream: Optional[bool] = None,
**kwargs,
) -> Union[
ResponsesAPIResponse,
BaseResponsesAPIStreamingIterator,
Coroutine[
Any, Any, Union[ResponsesAPIResponse, BaseResponsesAPIStreamingIterator]
],
]:
litellm_completion_request: dict = (
LiteLLMCompletionResponsesConfig.transform_responses_api_request_to_chat_completion_request(
model=model,
input=input,
responses_api_request=responses_api_request,
custom_llm_provider=custom_llm_provider,
stream=stream,
**kwargs,
)
)
if _is_async:
return self.async_response_api_handler(
litellm_completion_request=litellm_completion_request,
request_input=input,
responses_api_request=responses_api_request,
**kwargs,
)
litellm_completion_response: Union[
ModelResponse, litellm.CustomStreamWrapper
] = litellm.completion(
**litellm_completion_request,
**kwargs,
)
if isinstance(litellm_completion_response, ModelResponse):
responses_api_response: ResponsesAPIResponse = (
LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
chat_completion_response=litellm_completion_response,
request_input=input,
responses_api_request=responses_api_request,
)
)
return responses_api_response
elif isinstance(litellm_completion_response, litellm.CustomStreamWrapper):
return LiteLLMCompletionStreamingIterator(
litellm_custom_stream_wrapper=litellm_completion_response,
request_input=input,
responses_api_request=responses_api_request,
)
async def async_response_api_handler(
self,
litellm_completion_request: dict,
request_input: Union[str, ResponseInputParam],
responses_api_request: ResponsesAPIOptionalRequestParams,
**kwargs,
) -> Union[ResponsesAPIResponse, BaseResponsesAPIStreamingIterator]:
litellm_completion_response: Union[
ModelResponse, litellm.CustomStreamWrapper
] = await litellm.acompletion(
**litellm_completion_request,
**kwargs,
)
if isinstance(litellm_completion_response, ModelResponse):
responses_api_response: ResponsesAPIResponse = (
LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
chat_completion_response=litellm_completion_response,
request_input=request_input,
responses_api_request=responses_api_request,
)
)
return responses_api_response
elif isinstance(litellm_completion_response, litellm.CustomStreamWrapper):
return LiteLLMCompletionStreamingIterator(
litellm_custom_stream_wrapper=litellm_completion_response,
request_input=request_input,
responses_api_request=responses_api_request,
)