diff --git a/litellm/batches/main.py b/litellm/batches/main.py index 4043606d53..af2dc5059d 100644 --- a/litellm/batches/main.py +++ b/litellm/batches/main.py @@ -10,296 +10,37 @@ https://platform.openai.com/docs/api-reference/batch """ -import os import asyncio -from functools import partial import contextvars -from typing import Literal, Optional, Dict, Coroutine, Any, Union +import os +from functools import partial +from typing import Any, Coroutine, Dict, Literal, Optional, Union + import httpx import litellm from litellm import client from litellm.utils import supports_httpx_timeout -from ..types.router import * + from ..llms.openai import OpenAIBatchesAPI, OpenAIFilesAPI from ..types.llms.openai import ( - CreateBatchRequest, - RetrieveBatchRequest, - CancelBatchRequest, - CreateFileRequest, - FileTypes, - FileObject, Batch, + CancelBatchRequest, + CreateBatchRequest, + CreateFileRequest, FileContentRequest, + FileObject, + FileTypes, HttpxBinaryResponseContent, + RetrieveBatchRequest, ) +from ..types.router import * ####### ENVIRONMENT VARIABLES ################### openai_batches_instance = OpenAIBatchesAPI() -openai_files_instance = OpenAIFilesAPI() ################################################# -async def acreate_file( - file: FileTypes, - purpose: Literal["assistants", "batch", "fine-tune"], - custom_llm_provider: Literal["openai"] = "openai", - extra_headers: Optional[Dict[str, str]] = None, - extra_body: Optional[Dict[str, str]] = None, - **kwargs, -) -> Coroutine[Any, Any, FileObject]: - """ - Async: Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API. - - LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files - """ - try: - loop = asyncio.get_event_loop() - kwargs["acreate_file"] = True - - # Use a partial function to pass your keyword arguments - func = partial( - create_file, - file, - purpose, - 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 create_file( - file: FileTypes, - purpose: Literal["assistants", "batch", "fine-tune"], - custom_llm_provider: Literal["openai"] = "openai", - extra_headers: Optional[Dict[str, str]] = None, - extra_body: Optional[Dict[str, str]] = None, - **kwargs, -) -> Union[FileObject, Coroutine[Any, Any, FileObject]]: - """ - Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API. - - LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files - """ - 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 - - 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 - - _create_file_request = CreateFileRequest( - file=file, - purpose=purpose, - extra_headers=extra_headers, - extra_body=extra_body, - ) - - _is_async = kwargs.pop("acreate_file", False) is True - - response = openai_files_instance.create_file( - _is_async=_is_async, - api_base=api_base, - api_key=api_key, - timeout=timeout, - max_retries=optional_params.max_retries, - organization=organization, - create_file_data=_create_file_request, - ) - 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 - - -async def afile_content( - file_id: str, - custom_llm_provider: Literal["openai"] = "openai", - extra_headers: Optional[Dict[str, str]] = None, - extra_body: Optional[Dict[str, str]] = None, - **kwargs, -) -> Coroutine[Any, Any, HttpxBinaryResponseContent]: - """ - Async: Get file contents - - LiteLLM Equivalent of GET https://api.openai.com/v1/files - """ - try: - loop = asyncio.get_event_loop() - kwargs["afile_content"] = True - - # Use a partial function to pass your keyword arguments - func = partial( - file_content, - file_id, - 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 file_content( - file_id: str, - custom_llm_provider: Literal["openai"] = "openai", - extra_headers: Optional[Dict[str, str]] = None, - extra_body: Optional[Dict[str, str]] = None, - **kwargs, -) -> Union[HttpxBinaryResponseContent, Coroutine[Any, Any, HttpxBinaryResponseContent]]: - """ - Returns the contents of the specified file. - - LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files - """ - 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 - - 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 - - _file_content_request = FileContentRequest( - file_id=file_id, - extra_headers=extra_headers, - extra_body=extra_body, - ) - - _is_async = kwargs.pop("afile_content", False) is True - - response = openai_files_instance.file_content( - _is_async=_is_async, - file_content_request=_file_content_request, - api_base=api_base, - api_key=api_key, - timeout=timeout, - max_retries=optional_params.max_retries, - organization=organization, - ) - 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 - - async def acreate_batch( completion_window: Literal["24h"], endpoint: Literal["/v1/chat/completions", "/v1/embeddings", "/v1/completions"], diff --git a/litellm/files/main.py b/litellm/files/main.py index e11833eb44..c4c4c32edc 100644 --- a/litellm/files/main.py +++ b/litellm/files/main.py @@ -12,11 +12,10 @@ from functools import partial from typing import Any, Coroutine, Dict, Literal, Optional, Union import httpx -from openai.types.file_object import FileObject import litellm from litellm import client -from litellm.batches.main import openai_files_instance +from litellm.llms.openai import FileDeleted, FileObject, OpenAIFilesAPI from litellm.types.llms.openai import ( Batch, CreateFileRequest, @@ -27,6 +26,10 @@ from litellm.types.llms.openai import ( from litellm.types.router import * from litellm.utils import supports_httpx_timeout +####### ENVIRONMENT VARIABLES ################### +openai_files_instance = OpenAIFilesAPI() +################################################# + async def afile_retrieve( file_id: str, @@ -148,3 +151,386 @@ def file_retrieve( return response except Exception as e: raise e + + +# Delete file +async def afile_delete( + file_id: str, + custom_llm_provider: Literal["openai"] = "openai", + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +) -> Coroutine[Any, Any, FileObject]: + """ + Async: Delete file + + LiteLLM Equivalent of DELETE https://api.openai.com/v1/files + """ + try: + loop = asyncio.get_event_loop() + kwargs["is_async"] = True + + # Use a partial function to pass your keyword arguments + func = partial( + file_delete, + file_id, + 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 file_delete( + file_id: str, + custom_llm_provider: Literal["openai"] = "openai", + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +) -> FileDeleted: + """ + Delete file + + LiteLLM Equivalent of DELETE https://api.openai.com/v1/files + """ + 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 + + 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("is_async", False) is True + + response = openai_files_instance.delete_file( + file_id=file_id, + _is_async=_is_async, + api_base=api_base, + api_key=api_key, + timeout=timeout, + max_retries=optional_params.max_retries, + organization=organization, + ) + 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 + + +async def acreate_file( + file: FileTypes, + purpose: Literal["assistants", "batch", "fine-tune"], + custom_llm_provider: Literal["openai"] = "openai", + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +) -> Coroutine[Any, Any, FileObject]: + """ + Async: Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API. + + LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files + """ + try: + loop = asyncio.get_event_loop() + kwargs["acreate_file"] = True + + # Use a partial function to pass your keyword arguments + func = partial( + create_file, + file, + purpose, + 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 create_file( + file: FileTypes, + purpose: Literal["assistants", "batch", "fine-tune"], + custom_llm_provider: Literal["openai"] = "openai", + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +) -> Union[FileObject, Coroutine[Any, Any, FileObject]]: + """ + Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API. + + LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files + """ + 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 + + 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 + + _create_file_request = CreateFileRequest( + file=file, + purpose=purpose, + extra_headers=extra_headers, + extra_body=extra_body, + ) + + _is_async = kwargs.pop("acreate_file", False) is True + + response = openai_files_instance.create_file( + _is_async=_is_async, + api_base=api_base, + api_key=api_key, + timeout=timeout, + max_retries=optional_params.max_retries, + organization=organization, + create_file_data=_create_file_request, + ) + 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 + + +async def afile_content( + file_id: str, + custom_llm_provider: Literal["openai"] = "openai", + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +) -> Coroutine[Any, Any, HttpxBinaryResponseContent]: + """ + Async: Get file contents + + LiteLLM Equivalent of GET https://api.openai.com/v1/files + """ + try: + loop = asyncio.get_event_loop() + kwargs["afile_content"] = True + + # Use a partial function to pass your keyword arguments + func = partial( + file_content, + file_id, + 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 file_content( + file_id: str, + custom_llm_provider: Literal["openai"] = "openai", + extra_headers: Optional[Dict[str, str]] = None, + extra_body: Optional[Dict[str, str]] = None, + **kwargs, +) -> Union[HttpxBinaryResponseContent, Coroutine[Any, Any, HttpxBinaryResponseContent]]: + """ + Returns the contents of the specified file. + + LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files + """ + 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 + + 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 + + _file_content_request = FileContentRequest( + file_id=file_id, + extra_headers=extra_headers, + extra_body=extra_body, + ) + + _is_async = kwargs.pop("afile_content", False) is True + + response = openai_files_instance.file_content( + _is_async=_is_async, + file_content_request=_file_content_request, + api_base=api_base, + api_key=api_key, + timeout=timeout, + max_retries=optional_params.max_retries, + organization=organization, + ) + 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