add responses_api

litellm/proxy/response_api_endpoints/endpoints.py

@@ -0,0 +1,88 @@
+import backoff
+from fastapi import APIRouter, Depends, Request, Response
+
+from litellm._logging import verbose_proxy_logger
+from litellm.proxy._types import *
+from litellm.proxy.auth.user_api_key_auth import UserAPIKeyAuth, user_api_key_auth
+from litellm.proxy.common_request_processing import ProxyBaseLLMRequestProcessing
+from litellm.proxy.proxy_server import _read_request_body, select_data_generator
+
+router = APIRouter()
+
+
+@router.post(
+    "/v1/responses",
+    dependencies=[Depends(user_api_key_auth)],
+    tags=["responses"],
+)
+@router.post(
+    "/responses",
+    dependencies=[Depends(user_api_key_auth)],
+    tags=["responses"],
+)
+@backoff.on_exception(
+    backoff.expo,
+    Exception,  # base exception to catch for the backoff
+    logger=verbose_proxy_logger,
+)
+async def responses_api(
+    request: Request,
+    fastapi_response: Response,
+    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
+):
+    """
+    Follows the OpenAI Responses API spec: https://platform.openai.com/docs/api-reference/responses
+
+    ```bash
+    curl -X POST http://localhost:4000/v1/responses \
+    -H "Content-Type: application/json" \
+    -H "Authorization: Bearer sk-1234" \
+    -d '{
+        "model": "gpt-4o",
+        "input": "Tell me about AI"
+    }'
+    ```
+    """
+    from litellm.proxy.proxy_server import (
+        general_settings,
+        llm_router,
+        proxy_config,
+        proxy_logging_obj,
+        user_api_base,
+        user_max_tokens,
+        user_model,
+        user_request_timeout,
+        user_temperature,
+        version,
+    )
+
+    data = {}
+    try:
+        data = await _read_request_body(request=request)
+        return await ProxyBaseLLMRequestProcessing.base_process_llm_request(
+            data=data,
+            request=request,
+            fastapi_response=fastapi_response,
+            user_api_key_dict=user_api_key_dict,
+            route_type="aresponses",
+            proxy_logging_obj=proxy_logging_obj,
+            llm_router=llm_router,
+            general_settings=general_settings,
+            proxy_config=proxy_config,
+            select_data_generator=select_data_generator,
+            model=None,
+            user_model=user_model,
+            user_temperature=user_temperature,
+            user_request_timeout=user_request_timeout,
+            user_max_tokens=user_max_tokens,
+            user_api_base=user_api_base,
+            version=version,
+        )
+    except Exception as e:
+        raise await ProxyBaseLLMRequestProcessing._handle_llm_api_exception(
+            e=e,
+            data=data,
+            user_api_key_dict=user_api_key_dict,
+            proxy_logging_obj=proxy_logging_obj,
+            version=version,
+        )