diff --git a/litellm/batches/main.py b/litellm/batches/main.py index 79aefa5f5..3c41cf5d2 100644 --- a/litellm/batches/main.py +++ b/litellm/batches/main.py @@ -20,10 +20,8 @@ import httpx import litellm from litellm import client -from litellm.utils import supports_httpx_timeout - -from ..llms.openai import OpenAIBatchesAPI, OpenAIFilesAPI -from ..types.llms.openai import ( +from litellm.llms.openai import OpenAIBatchesAPI, OpenAIFilesAPI +from litellm.types.llms.openai import ( Batch, CancelBatchRequest, CreateBatchRequest, @@ -34,7 +32,8 @@ from ..types.llms.openai import ( HttpxBinaryResponseContent, RetrieveBatchRequest, ) -from ..types.router import * +from litellm.types.router import GenericLiteLLMParams +from litellm.utils import supports_httpx_timeout ####### ENVIRONMENT VARIABLES ################### openai_batches_instance = OpenAIBatchesAPI() @@ -314,17 +313,139 @@ def retrieve_batch( raise e -def cancel_batch(): - pass +async def alist_batches( + after: Optional[str] = None, + limit: Optional[int] = None, + custom_llm_provider: Literal["openai"] = "openai", + metadata: Optional[Dict[str, str]] = None, + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +) -> Batch: + """ + Async: List your organization's batches. + """ + try: + loop = asyncio.get_event_loop() + kwargs["alist_batches"] = True + + # Use a partial function to pass your keyword arguments + func = partial( + list_batches, + after, + limit, + custom_llm_provider, + extra_headers, + extra_body, + **kwargs, + ) + + # Add the context to the function + 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 # type: ignore + + return response + except Exception as e: + raise e -def list_batch(): - pass +def list_batches( + after: Optional[str] = None, + limit: Optional[int] = None, + custom_llm_provider: Literal["openai"] = "openai", + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +): + """ + Lists batches + List your organization's batches. + """ + try: + optional_params = GenericLiteLLMParams(**kwargs) + if custom_llm_provider == "openai": + # for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there + api_base = ( + optional_params.api_base + or litellm.api_base + or os.getenv("OPENAI_API_BASE") + or "https://api.openai.com/v1" + ) + organization = ( + optional_params.organization + or litellm.organization + or os.getenv("OPENAI_ORGANIZATION", None) + or None # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105 + ) + # set API KEY + api_key = ( + optional_params.api_key + or litellm.api_key # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there + or litellm.openai_key + or os.getenv("OPENAI_API_KEY") + ) + ### TIMEOUT LOGIC ### + timeout = ( + optional_params.timeout or kwargs.get("request_timeout", 600) or 600 + ) + # set timeout for 10 minutes by default -async def acancel_batch(): + if ( + timeout is not None + and isinstance(timeout, httpx.Timeout) + and supports_httpx_timeout(custom_llm_provider) == False + ): + read_timeout = timeout.read or 600 + timeout = read_timeout # default 10 min timeout + elif timeout is not None and not isinstance(timeout, httpx.Timeout): + timeout = float(timeout) # type: ignore + elif timeout is None: + timeout = 600.0 + + _is_async = kwargs.pop("alist_batches", False) is True + + response = openai_batches_instance.list_batches( + _is_async=_is_async, + after=after, + limit=limit, + api_base=api_base, + api_key=api_key, + organization=organization, + timeout=timeout, + max_retries=optional_params.max_retries, + ) + else: + raise litellm.exceptions.BadRequestError( + message="LiteLLM doesn't support {} for 'create_batch'. Only 'openai' is supported.".format( + custom_llm_provider + ), + model="n/a", + llm_provider=custom_llm_provider, + response=httpx.Response( + status_code=400, + content="Unsupported provider", + request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"), # type: ignore + ), + ) + return response + except Exception as e: + raise e pass async def alist_batch(): pass + + +def cancel_batch(): + pass + + +async def acancel_batch(): + pass diff --git a/litellm/llms/openai.py b/litellm/llms/openai.py index afd49ab14..fab3ff26d 100644 --- a/litellm/llms/openai.py +++ b/litellm/llms/openai.py @@ -2602,26 +2602,52 @@ class OpenAIBatchesAPI(BaseLLM): response = openai_client.batches.cancel(**cancel_batch_data) return response - # def list_batch( - # self, - # list_batch_data: ListBatchRequest, - # api_key: Optional[str], - # api_base: Optional[str], - # timeout: Union[float, httpx.Timeout], - # max_retries: Optional[int], - # organization: Optional[str], - # client: Optional[OpenAI] = None, - # ): - # openai_client: OpenAI = self.get_openai_client( - # api_key=api_key, - # api_base=api_base, - # timeout=timeout, - # max_retries=max_retries, - # organization=organization, - # client=client, - # ) - # response = openai_client.batches.list(**list_batch_data) - # return response + async def alist_batches( + self, + openai_client: AsyncOpenAI, + after: Optional[str] = None, + limit: Optional[int] = None, + ): + verbose_logger.debug("listing batches, after= %s, limit= %s", after, limit) + response = await openai_client.batches.list(after=after, limit=limit) + return response + + def list_batches( + self, + _is_async: bool, + api_key: Optional[str], + api_base: Optional[str], + timeout: Union[float, httpx.Timeout], + max_retries: Optional[int], + organization: Optional[str], + after: Optional[str] = None, + limit: Optional[int] = None, + client: Optional[OpenAI] = None, + ): + openai_client: Optional[Union[OpenAI, AsyncOpenAI]] = self.get_openai_client( + api_key=api_key, + api_base=api_base, + timeout=timeout, + max_retries=max_retries, + organization=organization, + client=client, + _is_async=_is_async, + ) + if openai_client is None: + raise ValueError( + "OpenAI client is not initialized. Make sure api_key is passed or OPENAI_API_KEY is set in the environment." + ) + + if _is_async is True: + if not isinstance(openai_client, AsyncOpenAI): + raise ValueError( + "OpenAI client is not an instance of AsyncOpenAI. Make sure you passed an AsyncOpenAI client." + ) + return self.alist_batches( # type: ignore + openai_client=openai_client, after=after, limit=limit + ) + response = openai_client.batches.list(after=after, limit=limit) + return response class OpenAIAssistantsAPI(BaseLLM):