Skip to main content
Open In ColabOpen on GitHub

ChatLiteLLM 和 ChatLiteLLMRouter

LiteLLM 是一个简化调用 Anthropic、Azure、Huggingface、Replicate 等的库。

本笔记本介绍了如何开始使用 Langchain 和 LiteLLM I/O 库。

此集成包含两个主要类:

  • ChatLiteLLM: 用于 LiteLLM 基本用法的主 Langchain 包装器(文档)。
  • ChatLiteLLMRouter: 一个利用 LiteLLM 路由器的 ChatLiteLLM 封装器(文档)。

目录

  1. 概述
  2. 设置
  3. 凭据
  4. 安装
  5. 实例化
  6. 调用
  7. 异步和流式功能
  8. API 参考

概览

集成详情

本地可序列化的JS 支持软件包下载最新包裹
ChatLiteLLMlangchain-litellmPyPI - DownloadsPyPI - Version
ChatLiteLLMRouterlangchain-litellmPyPI - DownloadsPyPI - Version

模型特性

工具调用结构化输出JSON模式图像输入音频输入视频输入令牌级流式传输原生异步令牌使用量对数概率

设置

要访问ChatLiteLLMChatLiteLLMRouter模型,您需要安装langchain-litellm包,并创建一个OpenAI、Anthropic、Azure、Replicate、OpenRouter、Hugging Face、Together AI或Cohere帐户。然后,您需要获取API密钥并将其导出为环境变量。

凭据

你必须选择所需的LLM提供商,并注册以获取他们的API密钥。

示例 - Anthropic

前往 https://console.anthropic.com/ 注册Anthropic并生成API密钥。完成后,请设置ANTHROPIC_API_KEY环境变量。

示例 - OpenAI

前往 https://platform.openai.com/api-keys 注册OpenAI并生成API密钥。完成后,请设置OPENAI_API_KEY环境变量。

## Set ENV variables
import os

os.environ["OPENAI_API_KEY"] = "your-openai-key"
os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-key"

安装

LangChain LiteLLM 集成在 langchain-litellm 包中可用:

%pip install -qU langchain-litellm

实例化

ChatLiteLLM

您可以通过提供一个 model 名称来实例化 ChatLiteLLM 模型,该名称受 LiteLLM 支持

from langchain_litellm import ChatLiteLLM

llm = ChatLiteLLM(model="gpt-4.1-nano", temperature=0.1)

ChatLiteLLMRouter

您还可以通过按此处指定的方式定义模型列表,来利用LiteLLM的路由功能。

from langchain_litellm import ChatLiteLLMRouter
from litellm import Router

model_list = [
{
"model_name": "gpt-4.1",
"litellm_params": {
"model": "azure/gpt-4.1",
"api_key": "<your-api-key>",
"api_version": "2024-10-21",
"api_base": "https://<your-endpoint>.openai.azure.com/",
},
},
{
"model_name": "gpt-4o",
"litellm_params": {
"model": "azure/gpt-4o",
"api_key": "<your-api-key>",
"api_version": "2024-10-21",
"api_base": "https://<your-endpoint>.openai.azure.com/",
},
},
]
litellm_router = Router(model_list=model_list)
llm = ChatLiteLLMRouter(router=litellm_router, model_name="gpt-4.1", temperature=0.1)

调用

无论你实例化的是 ChatLiteLLM 还是 ChatLiteLLMRouter,你现在都可以通过Langchain的API使用ChatModel。

response = await llm.ainvoke(
"Classify the text into neutral, negative or positive. Text: I think the food was okay. Sentiment:"
)
print(response)
content='Neutral' additional_kwargs={} response_metadata={'token_usage': Usage(completion_tokens=2, prompt_tokens=30, total_tokens=32, completion_tokens_details=CompletionTokensDetailsWrapper(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0, text_tokens=None), prompt_tokens_details=PromptTokensDetailsWrapper(audio_tokens=0, cached_tokens=0, text_tokens=None, image_tokens=None)), 'model': 'gpt-3.5-turbo', 'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo'} id='run-ab6a3b21-eae8-4c27-acb2-add65a38221a-0' usage_metadata={'input_tokens': 30, 'output_tokens': 2, 'total_tokens': 32}

异步和流功能

ChatLiteLLMChatLiteLLMRouter 还支持异步和流功能:

async for token in llm.astream("Hello, please explain how antibiotics work"):
print(token.text(), end="")
Antibiotics are medications that fight bacterial infections in the body. They work by targeting specific bacteria and either killing them or preventing their growth and reproduction.

There are several different mechanisms by which antibiotics work. Some antibiotics work by disrupting the cell walls of bacteria, causing them to burst and die. Others interfere with the protein synthesis of bacteria, preventing them from growing and reproducing. Some antibiotics target the DNA or RNA of bacteria, disrupting their ability to replicate.

It is important to note that antibiotics only work against bacterial infections and not viral infections. It is also crucial to take antibiotics as prescribed by a healthcare professional and to complete the full course of treatment, even if symptoms improve before the medication is finished. This helps to prevent antibiotic resistance, where bacteria become resistant to the effects of antibiotics.

API 参考

有关所有 ChatLiteLLMChatLiteLLMRouter 功能及配置的详细文档,请访问API参考: https://github.com/Akshay-Dongare/langchain-litellm