From b246c3c56c1f849cf07b73f99718f378b5e4f614 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Tue, 17 Feb 2026 19:13:20 +0530 Subject: [PATCH] Add eval run endpoints and methods --- litellm/__init__.py | 14 +- litellm/evals/main.py | 870 ++++++++++++++++++ litellm/llms/custom_httpx/llm_http_handler.py | 551 +++++++++++ litellm/proxy/common_request_processing.py | 5 + litellm/proxy/route_llm_request.py | 16 + 5 files changed, 1455 insertions(+), 1 deletion(-) diff --git a/litellm/__init__.py b/litellm/__init__.py index ce39c3d9dfb..e3bf585d649 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -1734,7 +1734,9 @@ def __getattr__(name: str) -> Any: # Lazy load evals module functions if name in ["acreate_eval", "alist_evals", "aget_eval", "aupdate_eval", "adelete_eval", "acancel_eval", - "create_eval", "list_evals", "get_eval", "update_eval", "delete_eval", "cancel_eval"]: + "create_eval", "list_evals", "get_eval", "update_eval", "delete_eval", "cancel_eval", + "acreate_run", "alist_runs", "aget_run", "acancel_run", "adelete_run", + "create_run", "list_runs", "get_run", "cancel_run", "delete_run"]: from litellm.evals.main import ( acreate_eval, alist_evals, @@ -1748,6 +1750,16 @@ def __getattr__(name: str) -> Any: update_eval, delete_eval, cancel_eval, + acreate_run, + alist_runs, + aget_run, + acancel_run, + adelete_run, + create_run, + list_runs, + get_run, + cancel_run, + delete_run, ) return locals()[name] diff --git a/litellm/evals/main.py b/litellm/evals/main.py index 976c1dfff9b..a39c2839150 100644 --- a/litellm/evals/main.py +++ b/litellm/evals/main.py @@ -17,11 +17,17 @@ from litellm.llms.base_llm.evals.transformation import BaseEvalsAPIConfig from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler from litellm.types.llms.openai_evals import ( CancelEvalResponse, + CancelRunResponse, CreateEvalRequest, + CreateRunRequest, DeleteEvalResponse, Eval, ListEvalsParams, ListEvalsResponse, + ListRunsParams, + ListRunsResponse, + Run, + RunDeleteResponse, UpdateEvalRequest, ) from litellm.types.router import GenericLiteLLMParams @@ -1072,3 +1078,867 @@ def cancel_eval( completion_kwargs=local_vars, extra_kwargs=kwargs, ) + + +# =================================== +# Run API Functions +# =================================== + + +@client +async def acreate_run( + eval_id: str, + data_source: Dict[str, Any], + name: Optional[str] = None, + metadata: Optional[Dict[str, Any]] = None, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + extra_body: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> Run: + """ + Async: Create a new run for an evaluation + + Args: + eval_id: The ID of the evaluation to run + data_source: Data source configuration for the run (can be jsonl, completions, or responses type) + name: Optional name for the run + metadata: Optional additional metadata + extra_headers: Additional headers for the request + extra_query: Additional query parameters + extra_body: Additional body parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + Run object + """ + local_vars = locals() + try: + loop = asyncio.get_event_loop() + kwargs["acreate_run"] = True + + func = partial( + create_run, + eval_id=eval_id, + data_source=data_source, + name=name, + metadata=metadata, + extra_headers=extra_headers, + extra_query=extra_query, + extra_body=extra_body, + timeout=timeout, + custom_llm_provider=custom_llm_provider, + **kwargs, + ) + + ctx = contextvars.copy_context() + func_with_context = partial(ctx.run, func) + init_response = await loop.run_in_executor(None, func_with_context) + + if asyncio.iscoroutine(init_response): + response = await init_response + else: + response = init_response + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +def create_run( + eval_id: str, + data_source: Dict[str, Any], + name: Optional[str] = None, + metadata: Optional[Dict[str, Any]] = None, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + extra_body: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> Union[Run, Coroutine[Any, Any, Run]]: + """ + Create a new run for an evaluation + + Args: + eval_id: The ID of the evaluation to run + data_source: Data source configuration for the run (can be jsonl, completions, or responses type) + name: Optional name for the run + metadata: Optional additional metadata + extra_headers: Additional headers for the request + extra_query: Additional query parameters + extra_body: Additional body parameters + timeout: Request timeout (default 600s for long-running operations) + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + Run object + """ + local_vars = locals() + try: + litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore + litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None) + _is_async = kwargs.pop("acreate_run", False) is True + + # Get LiteLLM parameters + litellm_params = GenericLiteLLMParams(**kwargs) + + # Determine provider + if custom_llm_provider is None: + custom_llm_provider = "openai" + + # Get provider config + evals_api_provider_config: Optional[BaseEvalsAPIConfig] = ( + ProviderConfigManager.get_provider_evals_api_config( # type: ignore + provider=litellm.LlmProviders(custom_llm_provider), + ) + ) + + if evals_api_provider_config is None: + raise ValueError( + f"CREATE run is not supported for {custom_llm_provider}" + ) + + # Build create request + create_request: CreateRunRequest = { + "data_source": data_source, # type: ignore + } + if name is not None: + create_request["name"] = name + # if metadata is not None: + # create_request["metadata"] = metadata + + # Merge extra_body if provided + if extra_body: + create_request.update(extra_body) # type: ignore + + # Validate environment and get headers + headers = extra_headers or {} + headers = evals_api_provider_config.validate_environment( + headers=headers, litellm_params=litellm_params + ) + + # Transform request + api_base = litellm_params.api_base or DEFAULT_OPENAI_API_BASE + url, request_body = evals_api_provider_config.transform_create_run_request( + eval_id=eval_id, + create_request=create_request, + litellm_params=litellm_params, + headers=headers, + ) + + # Pre-call logging + litellm_logging_obj.update_environment_variables( + model=None, + optional_params=request_body, + litellm_params={ + "litellm_call_id": litellm_call_id, + }, + custom_llm_provider=custom_llm_provider, + ) + + # Make HTTP request (default 600s timeout for long-running operations) + response = base_llm_http_handler.create_run_handler( # type: ignore + url=url, + request_body=request_body, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=litellm_logging_obj, + extra_headers=headers, + timeout=timeout or httpx.Timeout(timeout=600.0, connect=5.0), + _is_async=_is_async, + client=kwargs.get("client"), + shared_session=kwargs.get("shared_session"), + ) + + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +async def alist_runs( + eval_id: str, + limit: Optional[int] = None, + after: Optional[str] = None, + before: Optional[str] = None, + order: Optional[str] = None, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> ListRunsResponse: + """ + Async: List all runs for an evaluation + + Args: + eval_id: The ID of the evaluation + limit: Number of results to return per page (max 100, default 20) + after: Cursor for pagination - returns runs after this ID + before: Cursor for pagination - returns runs before this ID + order: Sort order ('asc' or 'desc', default 'desc') + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + ListRunsResponse object + """ + local_vars = locals() + try: + loop = asyncio.get_event_loop() + kwargs["alist_runs"] = True + + func = partial( + list_runs, + eval_id=eval_id, + limit=limit, + after=after, + before=before, + order=order, + extra_headers=extra_headers, + extra_query=extra_query, + timeout=timeout, + custom_llm_provider=custom_llm_provider, + **kwargs, + ) + + ctx = contextvars.copy_context() + func_with_context = partial(ctx.run, func) + init_response = await loop.run_in_executor(None, func_with_context) + + if asyncio.iscoroutine(init_response): + response = await init_response + else: + response = init_response + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +def list_runs( + eval_id: str, + limit: Optional[int] = None, + after: Optional[str] = None, + before: Optional[str] = None, + order: Optional[str] = None, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> Union[ListRunsResponse, Coroutine[Any, Any, ListRunsResponse]]: + """ + List all runs for an evaluation + + Args: + eval_id: The ID of the evaluation + limit: Number of results to return per page (max 100, default 20) + after: Cursor for pagination - returns runs after this ID + before: Cursor for pagination - returns runs before this ID + order: Sort order ('asc' or 'desc', default 'desc') + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + ListRunsResponse object + """ + local_vars = locals() + try: + litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore + litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None) + _is_async = kwargs.pop("alist_runs", False) is True + + # Get LiteLLM parameters + litellm_params = GenericLiteLLMParams(**kwargs) + + # Determine provider + if custom_llm_provider is None: + custom_llm_provider = "openai" + + # Get provider config + evals_api_provider_config: Optional[BaseEvalsAPIConfig] = ( + ProviderConfigManager.get_provider_evals_api_config( # type: ignore + provider=litellm.LlmProviders(custom_llm_provider), + ) + ) + + if evals_api_provider_config is None: + raise ValueError(f"LIST runs is not supported for {custom_llm_provider}") + + # Build list parameters + list_params: ListRunsParams = {} + if limit is not None: + list_params["limit"] = limit + if after is not None: + list_params["after"] = after + if before is not None: + list_params["before"] = before + if order is not None: + list_params["order"] = order # type: ignore + + # Merge extra_query if provided + if extra_query: + list_params.update(extra_query) # type: ignore + + # Validate environment and get headers + headers = extra_headers or {} + headers = evals_api_provider_config.validate_environment( + headers=headers, litellm_params=litellm_params + ) + + # Transform request + url, query_params = evals_api_provider_config.transform_list_runs_request( + eval_id=eval_id, + list_params=list_params, + litellm_params=litellm_params, + headers=headers, + ) + + # Pre-call logging + litellm_logging_obj.update_environment_variables( + model=None, + optional_params={"eval_id": eval_id, **query_params}, + litellm_params={ + "litellm_call_id": litellm_call_id, + }, + custom_llm_provider=custom_llm_provider, + ) + + # Make HTTP request + response = base_llm_http_handler.list_runs_handler( # type: ignore + url=url, + query_params=query_params, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=litellm_logging_obj, + extra_headers=headers, + timeout=timeout or request_timeout, + _is_async=_is_async, + client=kwargs.get("client"), + shared_session=kwargs.get("shared_session"), + ) + + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +async def aget_run( + eval_id: str, + run_id: str, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> Run: + """ + Async: Get a specific run + + Args: + eval_id: The ID of the evaluation + run_id: The ID of the run to retrieve + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + Run object + """ + local_vars = locals() + try: + loop = asyncio.get_event_loop() + kwargs["aget_run"] = True + + func = partial( + get_run, + eval_id=eval_id, + run_id=run_id, + extra_headers=extra_headers, + extra_query=extra_query, + timeout=timeout, + custom_llm_provider=custom_llm_provider, + **kwargs, + ) + + ctx = contextvars.copy_context() + func_with_context = partial(ctx.run, func) + init_response = await loop.run_in_executor(None, func_with_context) + + if asyncio.iscoroutine(init_response): + response = await init_response + else: + response = init_response + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +def get_run( + eval_id: str, + run_id: str, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> Union[Run, Coroutine[Any, Any, Run]]: + """ + Get a specific run + + Args: + eval_id: The ID of the evaluation + run_id: The ID of the run to retrieve + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + Run object + """ + local_vars = locals() + try: + litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore + litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None) + _is_async = kwargs.pop("aget_run", False) is True + + # Get LiteLLM parameters + litellm_params = GenericLiteLLMParams(**kwargs) + + # Determine provider + if custom_llm_provider is None: + custom_llm_provider = "openai" + + # Get provider config + evals_api_provider_config: Optional[BaseEvalsAPIConfig] = ( + ProviderConfigManager.get_provider_evals_api_config( # type: ignore + provider=litellm.LlmProviders(custom_llm_provider), + ) + ) + + if evals_api_provider_config is None: + raise ValueError(f"GET run is not supported for {custom_llm_provider}") + + # Validate environment and get headers + headers = extra_headers or {} + headers = evals_api_provider_config.validate_environment( + headers=headers, litellm_params=litellm_params + ) + + # Transform request + api_base = litellm_params.api_base or DEFAULT_OPENAI_API_BASE + url, headers = evals_api_provider_config.transform_get_run_request( + eval_id=eval_id, + run_id=run_id, + api_base=api_base, + litellm_params=litellm_params, + headers=headers, + ) + + # Pre-call logging + litellm_logging_obj.update_environment_variables( + model=None, + optional_params={"eval_id": eval_id, "run_id": run_id}, + litellm_params={ + "litellm_call_id": litellm_call_id, + }, + custom_llm_provider=custom_llm_provider, + ) + + # Make HTTP request + response = base_llm_http_handler.get_run_handler( # type: ignore + url=url, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=litellm_logging_obj, + extra_headers=headers, + timeout=timeout or request_timeout, + _is_async=_is_async, + client=kwargs.get("client"), + shared_session=kwargs.get("shared_session"), + ) + + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +async def acancel_run( + eval_id: str, + run_id: str, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> CancelRunResponse: + """ + Async: Cancel a running run + + Args: + eval_id: The ID of the evaluation + run_id: The ID of the run to cancel + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + CancelRunResponse object + """ + local_vars = locals() + try: + loop = asyncio.get_event_loop() + kwargs["acancel_run"] = True + + func = partial( + cancel_run, + eval_id=eval_id, + run_id=run_id, + extra_headers=extra_headers, + extra_query=extra_query, + timeout=timeout, + custom_llm_provider=custom_llm_provider, + **kwargs, + ) + + ctx = contextvars.copy_context() + func_with_context = partial(ctx.run, func) + init_response = await loop.run_in_executor(None, func_with_context) + + if asyncio.iscoroutine(init_response): + response = await init_response + else: + response = init_response + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +def cancel_run( + eval_id: str, + run_id: str, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> Union[CancelRunResponse, Coroutine[Any, Any, CancelRunResponse]]: + """ + Cancel a running run + + Args: + eval_id: The ID of the evaluation + run_id: The ID of the run to cancel + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + CancelRunResponse object + """ + local_vars = locals() + try: + litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore + litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None) + _is_async = kwargs.pop("acancel_run", False) is True + + # Get LiteLLM parameters + litellm_params = GenericLiteLLMParams(**kwargs) + + # Determine provider + if custom_llm_provider is None: + custom_llm_provider = "openai" + + # Get provider config + evals_api_provider_config: Optional[BaseEvalsAPIConfig] = ( + ProviderConfigManager.get_provider_evals_api_config( # type: ignore + provider=litellm.LlmProviders(custom_llm_provider), + ) + ) + + if evals_api_provider_config is None: + raise ValueError(f"CANCEL run is not supported for {custom_llm_provider}") + + # Validate environment and get headers + headers = extra_headers or {} + headers = evals_api_provider_config.validate_environment( + headers=headers, litellm_params=litellm_params + ) + + # Transform request + api_base = litellm_params.api_base or DEFAULT_OPENAI_API_BASE + url, headers, request_body = evals_api_provider_config.transform_cancel_run_request( + eval_id=eval_id, + run_id=run_id, + api_base=api_base, + litellm_params=litellm_params, + headers=headers, + ) + + # Pre-call logging + litellm_logging_obj.update_environment_variables( + model=None, + optional_params={"eval_id": eval_id, "run_id": run_id}, + litellm_params={ + "litellm_call_id": litellm_call_id, + }, + custom_llm_provider=custom_llm_provider, + ) + + # Make HTTP request + response = base_llm_http_handler.cancel_run_handler( # type: ignore + url=url, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=litellm_logging_obj, + extra_headers=headers, + timeout=timeout or request_timeout, + _is_async=_is_async, + client=kwargs.get("client"), + shared_session=kwargs.get("shared_session"), + ) + + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +# =================================== +# Delete Run API Functions +# =================================== + + +@client +async def adelete_run( + eval_id: str, + run_id: str, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> RunDeleteResponse: + """ + Async: Delete a run + + Args: + eval_id: The ID of the evaluation + run_id: The ID of the run to delete + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + RunDeleteResponse object + """ + local_vars = locals() + try: + loop = asyncio.get_event_loop() + kwargs["adelete_run"] = True + + func = partial( + delete_run, + eval_id=eval_id, + run_id=run_id, + extra_headers=extra_headers, + extra_query=extra_query, + timeout=timeout, + custom_llm_provider=custom_llm_provider, + **kwargs, + ) + + ctx = contextvars.copy_context() + func_with_context = partial(ctx.run, func) + init_response = await loop.run_in_executor(None, func_with_context) + + if asyncio.iscoroutine(init_response): + response = await init_response + else: + response = init_response + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) + + +@client +def delete_run( + eval_id: str, + run_id: str, + extra_headers: Optional[Dict[str, Any]] = None, + extra_query: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + custom_llm_provider: Optional[str] = None, + **kwargs, +) -> Union[RunDeleteResponse, Coroutine[Any, Any, RunDeleteResponse]]: + """ + Delete a run + + Args: + eval_id: The ID of the evaluation + run_id: The ID of the run to delete + extra_headers: Additional headers for the request + extra_query: Additional query parameters + timeout: Request timeout + custom_llm_provider: Provider name (e.g., 'openai') + **kwargs: Additional parameters + + Returns: + RunDeleteResponse object + """ + local_vars = locals() + try: + litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore + litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None) + _is_async = kwargs.pop("adelete_run", False) is True + + # Get LiteLLM parameters + litellm_params = GenericLiteLLMParams(**kwargs) + + # Determine provider + if custom_llm_provider is None: + custom_llm_provider = "openai" + + # Get provider config + evals_api_provider_config: Optional[BaseEvalsAPIConfig] = ( + ProviderConfigManager.get_provider_evals_api_config( # type: ignore + provider=litellm.LlmProviders(custom_llm_provider), + ) + ) + + if evals_api_provider_config is None: + raise ValueError(f"DELETE run is not supported for {custom_llm_provider}") + + # Validate environment and get headers + headers = extra_headers or {} + headers = evals_api_provider_config.validate_environment( + headers=headers, litellm_params=litellm_params + ) + + # Transform request + api_base = litellm_params.api_base or DEFAULT_OPENAI_API_BASE + url, headers, request_body = evals_api_provider_config.transform_delete_run_request( + eval_id=eval_id, + run_id=run_id, + api_base=api_base, + litellm_params=litellm_params, + headers=headers, + ) + + # Pre-call logging + litellm_logging_obj.update_environment_variables( + model=None, + optional_params={"eval_id": eval_id, "run_id": run_id}, + litellm_params={ + "litellm_call_id": litellm_call_id, + }, + custom_llm_provider=custom_llm_provider, + ) + + # Make HTTP request + response = base_llm_http_handler.delete_run_handler( # type: ignore + url=url, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=litellm_logging_obj, + extra_headers=headers, + timeout=timeout or request_timeout, + _is_async=_is_async, + client=kwargs.get("client"), + shared_session=kwargs.get("shared_session"), + ) + + return response + except Exception as e: + raise litellm.exception_type( + model=None, + custom_llm_provider=custom_llm_provider, + original_exception=e, + completion_kwargs=local_vars, + extra_kwargs=kwargs, + ) diff --git a/litellm/llms/custom_httpx/llm_http_handler.py b/litellm/llms/custom_httpx/llm_http_handler.py index 63b9f28fe54..ae553b03676 100644 --- a/litellm/llms/custom_httpx/llm_http_handler.py +++ b/litellm/llms/custom_httpx/llm_http_handler.py @@ -136,9 +136,13 @@ if TYPE_CHECKING: from litellm.llms.base_llm.passthrough.transformation import BasePassthroughConfig from litellm.types.llms.openai_evals import ( CancelEvalResponse, + CancelRunResponse, DeleteEvalResponse, Eval, ListEvalsResponse, + ListRunsResponse, + Run, + RunDeleteResponse, ) LiteLLMLoggingObj = _LiteLLMLoggingObj @@ -9983,3 +9987,550 @@ class BaseLLMHTTPHandler: raw_response=response, logging_obj=logging_obj, ) + + # =================================== + # Eval Runs API Handlers + # =================================== + + def create_run_handler( + self, + url: str, + request_body: Dict, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + _is_async: bool = False, + shared_session: Optional["ClientSession"] = None, + ) -> Union["Run", Coroutine[Any, Any, "Run"]]: + """Create a run""" + if _is_async: + return self.async_create_run_handler( + url=url, + request_body=request_body, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=logging_obj, + extra_headers=extra_headers, + timeout=timeout, + client=client, + shared_session=shared_session, + ) + + if client is None or not isinstance(client, HTTPHandler): + sync_httpx_client = _get_httpx_client( + params={"ssl_verify": litellm_params.get("ssl_verify", None)} + ) + else: + sync_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input=request_body.get("name", ""), + api_key="", + additional_args={ + "complete_input_dict": request_body, + "api_base": url, + "headers": headers, + }, + ) + + try: + response = sync_httpx_client.post( + url=url, headers=headers, json=request_body, timeout=timeout + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_create_run_response( + raw_response=response, + logging_obj=logging_obj, + ) + + async def async_create_run_handler( + self, + url: str, + request_body: Dict, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + shared_session: Optional["ClientSession"] = None, + ) -> "Run": + """Async create a run""" + if client is None or not isinstance(client, AsyncHTTPHandler): + async_httpx_client = get_async_httpx_client( + llm_provider=litellm.LlmProviders(custom_llm_provider), + params={"ssl_verify": litellm_params.get("ssl_verify", None)}, + ) + else: + async_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input=request_body.get("name", ""), + api_key="", + additional_args={ + "complete_input_dict": request_body, + "api_base": url, + "headers": headers, + }, + ) + + try: + response = await async_httpx_client.post( + url=url, headers=headers, json=request_body, timeout=timeout + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_create_run_response( + raw_response=response, + logging_obj=logging_obj, + ) + + def list_runs_handler( + self, + url: str, + query_params: Dict, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + _is_async: bool = False, + shared_session: Optional["ClientSession"] = None, + ) -> Union["ListRunsResponse", Coroutine[Any, Any, "ListRunsResponse"]]: + """List runs""" + if _is_async: + return self.async_list_runs_handler( + url=url, + query_params=query_params, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=logging_obj, + extra_headers=extra_headers, + timeout=timeout, + client=client, + shared_session=shared_session, + ) + + if client is None or not isinstance(client, HTTPHandler): + sync_httpx_client = _get_httpx_client( + params={"ssl_verify": litellm_params.get("ssl_verify", None)} + ) + else: + sync_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + "params": query_params, + }, + ) + + try: + response = sync_httpx_client.get( + url=url, headers=headers, params=query_params + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_list_runs_response( + raw_response=response, + logging_obj=logging_obj, + ) + + async def async_list_runs_handler( + self, + url: str, + query_params: Dict, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + shared_session: Optional["ClientSession"] = None, + ) -> "ListRunsResponse": + """Async list runs""" + if client is None or not isinstance(client, AsyncHTTPHandler): + async_httpx_client = get_async_httpx_client( + llm_provider=litellm.LlmProviders(custom_llm_provider), + params={"ssl_verify": litellm_params.get("ssl_verify", None)}, + ) + else: + async_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + "params": query_params, + }, + ) + + try: + response = await async_httpx_client.get( + url=url, headers=headers, params=query_params + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_list_runs_response( + raw_response=response, + logging_obj=logging_obj, + ) + + def get_run_handler( + self, + url: str, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + _is_async: bool = False, + shared_session: Optional["ClientSession"] = None, + ) -> Union["Run", Coroutine[Any, Any, "Run"]]: + """Get a run""" + if _is_async: + return self.async_get_run_handler( + url=url, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=logging_obj, + extra_headers=extra_headers, + timeout=timeout, + client=client, + shared_session=shared_session, + ) + + if client is None or not isinstance(client, HTTPHandler): + sync_httpx_client = _get_httpx_client( + params={"ssl_verify": litellm_params.get("ssl_verify", None)} + ) + else: + sync_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + }, + ) + + try: + response = sync_httpx_client.get(url=url, headers=headers) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_get_run_response( + raw_response=response, + logging_obj=logging_obj, + ) + + async def async_get_run_handler( + self, + url: str, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + shared_session: Optional["ClientSession"] = None, + ) -> "Run": + """Async get a run""" + if client is None or not isinstance(client, AsyncHTTPHandler): + async_httpx_client = get_async_httpx_client( + llm_provider=litellm.LlmProviders(custom_llm_provider), + params={"ssl_verify": litellm_params.get("ssl_verify", None)}, + ) + else: + async_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + }, + ) + + try: + response = await async_httpx_client.get( + url=url, headers=headers + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_get_run_response( + raw_response=response, + logging_obj=logging_obj, + ) + + def cancel_run_handler( + self, + url: str, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + _is_async: bool = False, + shared_session: Optional["ClientSession"] = None, + ) -> Union["CancelRunResponse", Coroutine[Any, Any, "CancelRunResponse"]]: + """Cancel a run""" + if _is_async: + return self.async_cancel_run_handler( + url=url, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=logging_obj, + extra_headers=extra_headers, + timeout=timeout, + client=client, + shared_session=shared_session, + ) + + if client is None or not isinstance(client, HTTPHandler): + sync_httpx_client = _get_httpx_client( + params={"ssl_verify": litellm_params.get("ssl_verify", None)} + ) + else: + sync_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + }, + ) + + try: + response = sync_httpx_client.post( + url=url, headers=headers, json={}, timeout=timeout + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_cancel_run_response( + raw_response=response, + logging_obj=logging_obj, + ) + + async def async_cancel_run_handler( + self, + url: str, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + shared_session: Optional["ClientSession"] = None, + ) -> "CancelRunResponse": + """Async cancel a run""" + if client is None or not isinstance(client, AsyncHTTPHandler): + async_httpx_client = get_async_httpx_client( + llm_provider=litellm.LlmProviders(custom_llm_provider), + params={"ssl_verify": litellm_params.get("ssl_verify", None)}, + ) + else: + async_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + }, + ) + + try: + response = await async_httpx_client.post( + url=url, headers=headers, json={}, timeout=timeout + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_cancel_run_response( + raw_response=response, + logging_obj=logging_obj, + ) + + def delete_run_handler( + self, + url: str, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + _is_async: bool = False, + shared_session: Optional["ClientSession"] = None, + ) -> Union["RunDeleteResponse", Coroutine[Any, Any, "RunDeleteResponse"]]: + """Delete a run""" + if _is_async: + return self.async_delete_run_handler( + url=url, + evals_api_provider_config=evals_api_provider_config, + custom_llm_provider=custom_llm_provider, + litellm_params=litellm_params, + logging_obj=logging_obj, + extra_headers=extra_headers, + timeout=timeout, + client=client, + shared_session=shared_session, + ) + + if client is None or not isinstance(client, HTTPHandler): + sync_httpx_client = _get_httpx_client( + params={"ssl_verify": litellm_params.get("ssl_verify", None)} + ) + else: + sync_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + }, + ) + + try: + response = sync_httpx_client.delete( + url=url, headers=headers, timeout=timeout + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_delete_run_response( + raw_response=response, + logging_obj=logging_obj, + ) + + async def async_delete_run_handler( + self, + url: str, + evals_api_provider_config: "BaseEvalsAPIConfig", + custom_llm_provider: str, + litellm_params: GenericLiteLLMParams, + logging_obj: LiteLLMLoggingObj, + extra_headers: Optional[Dict[str, Any]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None, + shared_session: Optional["ClientSession"] = None, + ) -> "RunDeleteResponse": + """Async delete a run""" + if client is None or not isinstance(client, AsyncHTTPHandler): + async_httpx_client = get_async_httpx_client( + llm_provider=litellm.LlmProviders(custom_llm_provider), + params={"ssl_verify": litellm_params.get("ssl_verify", None)}, + ) + else: + async_httpx_client = client + + headers = extra_headers or {} + + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "api_base": url, + "headers": headers, + }, + ) + + try: + response = await async_httpx_client.delete( + url=url, headers=headers, timeout=timeout + ) + except Exception as e: + raise self._handle_error( + e=e, + provider_config=evals_api_provider_config, + ) + + return evals_api_provider_config.transform_delete_run_response( + raw_response=response, + logging_obj=logging_obj, + ) diff --git a/litellm/proxy/common_request_processing.py b/litellm/proxy/common_request_processing.py index 3bfd4c2e242..71ad1fba9e2 100644 --- a/litellm/proxy/common_request_processing.py +++ b/litellm/proxy/common_request_processing.py @@ -720,6 +720,11 @@ class ProxyBaseLLMRequestProcessing: "aupdate_eval", "adelete_eval", "acancel_eval", + "acreate_run", + "alist_runs", + "aget_run", + "acancel_run", + "adelete_run", ], proxy_logging_obj: ProxyLogging, general_settings: dict, diff --git a/litellm/proxy/route_llm_request.py b/litellm/proxy/route_llm_request.py index eda042f9fe4..d9f75a21790 100644 --- a/litellm/proxy/route_llm_request.py +++ b/litellm/proxy/route_llm_request.py @@ -80,6 +80,12 @@ ROUTE_ENDPOINT_MAPPING = { "aupdate_eval": "/evals/{eval_id}", "adelete_eval": "/evals/{eval_id}", "acancel_eval": "/evals/{eval_id}/cancel", + # OpenAI Evals Runs API routes + "acreate_run": "/evals/{eval_id}/runs", + "alist_runs": "/evals/{eval_id}/runs", + "aget_run": "/evals/{eval_id}/runs/{run_id}", + "acancel_run": "/evals/{eval_id}/runs/{run_id}/cancel", + "adelete_run": "/evals/{eval_id}/runs/{run_id}", } @@ -203,6 +209,11 @@ async def route_request( "aupdate_eval", "adelete_eval", "acancel_eval", + "acreate_run", + "alist_runs", + "aget_run", + "acancel_run", + "adelete_run", ], ): """ @@ -278,6 +289,11 @@ async def route_request( "aupdate_eval", "adelete_eval", "acancel_eval", + "acreate_run", + "alist_runs", + "aget_run", + "acancel_run", + "adelete_run", ]: # If a model is provided, get its credentials from the router model = data.get("model")