From 389a51e05d912ba797a9147d57c9caaf35ac84a3 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Thu, 11 Jul 2024 13:36:55 -0700 Subject: [PATCH] fix: fix linting errors --- .pre-commit-config.yaml | 12 +-- litellm/__init__.py | 1 + litellm/llms/together_ai.py | 146 ++++++++++++++++++------------------ litellm/main.py | 72 ++++-------------- 4 files changed, 97 insertions(+), 134 deletions(-) diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index d429bc6b8..a33473b72 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,12 +1,12 @@ repos: - repo: local hooks: - # - id: mypy - # name: mypy - # entry: python3 -m mypy --ignore-missing-imports - # language: system - # types: [python] - # files: ^litellm/ + - id: mypy + name: mypy + entry: python3 -m mypy --ignore-missing-imports + language: system + types: [python] + files: ^litellm/ - id: isort name: isort entry: isort diff --git a/litellm/__init__.py b/litellm/__init__.py index 6393664c6..1944f886b 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -789,6 +789,7 @@ from .utils import ( get_api_base, get_first_chars_messages, ModelResponse, + EmbeddingResponse, ImageResponse, get_provider_fields, ) diff --git a/litellm/llms/together_ai.py b/litellm/llms/together_ai.py index 3a7e980a3..3adbcae37 100644 --- a/litellm/llms/together_ai.py +++ b/litellm/llms/together_ai.py @@ -3,92 +3,96 @@ Deprecated. We now do together ai calls via the openai client. Reference: https://docs.together.ai/docs/openai-api-compatibility """ -# import os, types -# import json -# from enum import Enum -# import requests # type: ignore -# import time -# from typing import Callable, Optional -# import litellm -# import httpx # type: ignore -# from litellm.utils import ModelResponse, Usage -# from .prompt_templates.factory import prompt_factory, custom_prompt +import json +import os +import time +import types +from enum import Enum +from typing import Callable, Optional + +import httpx # type: ignore +import requests # type: ignore + +import litellm +from litellm.utils import ModelResponse, Usage + +from .prompt_templates.factory import custom_prompt, prompt_factory -# class TogetherAIError(Exception): -# def __init__(self, status_code, message): -# self.status_code = status_code -# self.message = message -# self.request = httpx.Request( -# method="POST", url="https://api.together.xyz/inference" -# ) -# self.response = httpx.Response(status_code=status_code, request=self.request) -# super().__init__( -# self.message -# ) # Call the base class constructor with the parameters it needs +class TogetherAIError(Exception): + def __init__(self, status_code, message): + self.status_code = status_code + self.message = message + self.request = httpx.Request( + method="POST", url="https://api.together.xyz/inference" + ) + self.response = httpx.Response(status_code=status_code, request=self.request) + super().__init__( + self.message + ) # Call the base class constructor with the parameters it needs -# class TogetherAIConfig: -# """ -# Reference: https://docs.together.ai/reference/inference +class TogetherAIConfig: + """ + Reference: https://docs.together.ai/reference/inference -# The class `TogetherAIConfig` provides configuration for the TogetherAI's API interface. Here are the parameters: + The class `TogetherAIConfig` provides configuration for the TogetherAI's API interface. Here are the parameters: -# - `max_tokens` (int32, required): The maximum number of tokens to generate. + - `max_tokens` (int32, required): The maximum number of tokens to generate. -# - `stop` (string, optional): A string sequence that will truncate (stop) the inference text output. For example, "\n\n" will stop generation as soon as the model generates two newlines. + - `stop` (string, optional): A string sequence that will truncate (stop) the inference text output. For example, "\n\n" will stop generation as soon as the model generates two newlines. -# - `temperature` (float, optional): A decimal number that determines the degree of randomness in the response. A value of 1 will always yield the same output. A temperature less than 1 favors more correctness and is appropriate for question answering or summarization. A value greater than 1 introduces more randomness in the output. + - `temperature` (float, optional): A decimal number that determines the degree of randomness in the response. A value of 1 will always yield the same output. A temperature less than 1 favors more correctness and is appropriate for question answering or summarization. A value greater than 1 introduces more randomness in the output. -# - `top_p` (float, optional): The `top_p` (nucleus) parameter is used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities. It specifies a probability threshold, below which all less likely tokens are filtered out. This technique helps to maintain diversity and generate more fluent and natural-sounding text. + - `top_p` (float, optional): The `top_p` (nucleus) parameter is used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities. It specifies a probability threshold, below which all less likely tokens are filtered out. This technique helps to maintain diversity and generate more fluent and natural-sounding text. -# - `top_k` (int32, optional): The `top_k` parameter is used to limit the number of choices for the next predicted word or token. It specifies the maximum number of tokens to consider at each step, based on their probability of occurrence. This technique helps to speed up the generation process and can improve the quality of the generated text by focusing on the most likely options. + - `top_k` (int32, optional): The `top_k` parameter is used to limit the number of choices for the next predicted word or token. It specifies the maximum number of tokens to consider at each step, based on their probability of occurrence. This technique helps to speed up the generation process and can improve the quality of the generated text by focusing on the most likely options. -# - `repetition_penalty` (float, optional): A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition. + - `repetition_penalty` (float, optional): A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition. -# - `logprobs` (int32, optional): This parameter is not described in the prompt. -# """ + - `logprobs` (int32, optional): This parameter is not described in the prompt. + """ -# max_tokens: Optional[int] = None -# stop: Optional[str] = None -# temperature: Optional[int] = None -# top_p: Optional[float] = None -# top_k: Optional[int] = None -# repetition_penalty: Optional[float] = None -# logprobs: Optional[int] = None + max_tokens: Optional[int] = None + stop: Optional[str] = None + temperature: Optional[int] = None + top_p: Optional[float] = None + top_k: Optional[int] = None + repetition_penalty: Optional[float] = None + logprobs: Optional[int] = None -# def __init__( -# self, -# max_tokens: Optional[int] = None, -# stop: Optional[str] = None, -# temperature: Optional[int] = None, -# top_p: Optional[float] = None, -# top_k: Optional[int] = None, -# repetition_penalty: Optional[float] = None, -# logprobs: Optional[int] = None, -# ) -> None: -# locals_ = locals() -# for key, value in locals_.items(): -# if key != "self" and value is not None: -# setattr(self.__class__, key, value) + def __init__( + self, + max_tokens: Optional[int] = None, + stop: Optional[str] = None, + temperature: Optional[int] = None, + top_p: Optional[float] = None, + top_k: Optional[int] = None, + repetition_penalty: Optional[float] = None, + logprobs: Optional[int] = None, + ) -> None: + locals_ = locals() + for key, value in locals_.items(): + if key != "self" and value is not None: + setattr(self.__class__, key, value) -# @classmethod -# def get_config(cls): -# return { -# k: v -# for k, v in cls.__dict__.items() -# if not k.startswith("__") -# and not isinstance( -# v, -# ( -# types.FunctionType, -# types.BuiltinFunctionType, -# classmethod, -# staticmethod, -# ), -# ) -# and v is not None -# } + @classmethod + def get_config(cls): + return { + k: v + for k, v in cls.__dict__.items() + if not k.startswith("__") + and not isinstance( + v, + ( + types.FunctionType, + types.BuiltinFunctionType, + classmethod, + staticmethod, + ), + ) + and v is not None + } # def validate_environment(api_key): diff --git a/litellm/main.py b/litellm/main.py index bc40194b4..0aeff3188 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -1934,51 +1934,7 @@ def completion( """ Deprecated. We now do together ai calls via the openai client - https://docs.together.ai/docs/openai-api-compatibility """ - custom_llm_provider = "together_ai" - together_ai_key = ( - api_key - or litellm.togetherai_api_key - or get_secret("TOGETHER_AI_TOKEN") - or get_secret("TOGETHERAI_API_KEY") - or litellm.api_key - ) - - api_base = ( - api_base - or litellm.api_base - or get_secret("TOGETHERAI_API_BASE") - or "https://api.together.xyz/inference" - ) - - custom_prompt_dict = custom_prompt_dict or litellm.custom_prompt_dict - - model_response = together_ai.completion( - model=model, - messages=messages, - api_base=api_base, - model_response=model_response, - print_verbose=print_verbose, - optional_params=optional_params, - litellm_params=litellm_params, - logger_fn=logger_fn, - encoding=encoding, - api_key=together_ai_key, - logging_obj=logging, - custom_prompt_dict=custom_prompt_dict, - ) - if ( - "stream_tokens" in optional_params - and optional_params["stream_tokens"] == True - ): - # don't try to access stream object, - response = CustomStreamWrapper( - model_response, - model, - custom_llm_provider="together_ai", - logging_obj=logging, - ) - return response - response = model_response + pass elif custom_llm_provider == "palm": palm_api_key = api_key or get_secret("PALM_API_KEY") or litellm.api_key @@ -2461,10 +2417,10 @@ def completion( ## LOGGING generator = ollama.get_ollama_response( - api_base, - model, - prompt, - optional_params, + api_base=api_base, + model=model, + prompt=prompt, + optional_params=optional_params, logging_obj=logging, acompletion=acompletion, model_response=model_response, @@ -2490,11 +2446,11 @@ def completion( ) ## LOGGING generator = ollama_chat.get_ollama_response( - api_base, - api_key, - model, - messages, - optional_params, + api_base=api_base, + api_key=api_key, + model=model, + messages=messages, + optional_params=optional_params, logging_obj=logging, acompletion=acompletion, model_response=model_response, @@ -3465,7 +3421,7 @@ def embedding( or api_base or get_secret("OLLAMA_API_BASE") or "http://localhost:11434" - ) + ) # type: ignore if isinstance(input, str): input = [input] if not all(isinstance(item, str) for item in input): @@ -3475,9 +3431,11 @@ def embedding( llm_provider="ollama", # type: ignore ) ollama_embeddings_fn = ( - ollama.ollama_aembeddings if aembedding else ollama.ollama_embeddings + ollama.ollama_aembeddings + if aembedding is True + else ollama.ollama_embeddings ) - response = ollama_embeddings_fn( + response = ollama_embeddings_fn( # type: ignore api_base=api_base, model=model, prompts=input,