ChatLiteLLM and ChatLiteLLMRouter
LiteLLM is a library that simplifies calling Anthropic, Azure, Huggingface, Replicate, etc.
This notebook covers how to get started with using Langchain + the LiteLLM I/O library.
This integration contains two main classes:
ChatLiteLLM: The main Langchain wrapper for basic usage of LiteLLM (docs).ChatLiteLLMRouter: AChatLiteLLMwrapper that leverages LiteLLM's Router (docs).
Table of Contents
- Overview
- Setup
- Credentials
- Installation
- Instantiation
- Invocation
- Async and Streaming Functionality
- API Reference
Overview
Integration details
| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |
|---|---|---|---|---|---|---|
| ChatLiteLLM | langchain-litellm | ❌ | ❌ | ❌ | ||
| ChatLiteLLMRouter | langchain-litellm | ❌ | ❌ | ❌ |
Model features
| Tool calling | Structured output | JSON mode | Image input | Audio input | Video input | Token-level streaming | Native async | Token usage | Logprobs |
|---|---|---|---|---|---|---|---|---|---|
| ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ |
Setup
To accessChatLiteLLM andChatLiteLLMRouter models, you'll need to install thelangchain-litellm package and create an OpenAI, Anthropic, Azure, Replicate, OpenRouter, Hugging Face, Together AI, or Cohere account. Then, you have to get an API key and export it as an environment variable.
Credentials
You have to choose the LLM provider you want and sign up with them to get their API key.
Example - Anthropic
Head tohttps://console.anthropic.com/ to sign up for Anthropic and generate an API key. Once you've done this, set the ANTHROPIC_API_KEY environment variable.
Example - OpenAI
Head tohttps://platform.openai.com/api-keys to sign up for OpenAI and generate an API key. Once you've done this, set the OPENAI_API_KEY environment variable.
## Set ENV variables
import os
os.environ["OPENAI_API_KEY"]="your-openai-key"
os.environ["ANTHROPIC_API_KEY"]="your-anthropic-key"
Installation
The LangChain LiteLLM integration is available in thelangchain-litellm package:
%pip install-qU langchain-litellm
Instantiation
ChatLiteLLM
You can instantiate aChatLiteLLM model by providing amodel namesupported by LiteLLM.
from langchain_litellmimport ChatLiteLLM
llm= ChatLiteLLM(model="gpt-4.1-nano", temperature=0.1)
ChatLiteLLMRouter
You can also leverage LiteLLM's routing capabilities by defining your model list as specifiedhere.
from langchain_litellmimport ChatLiteLLMRouter
from litellmimport 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)
Invocation
Whether you've instantiated aChatLiteLLM or aChatLiteLLMRouter, you can now use the ChatModel through Langchain's API.
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}
Async and Streaming Functionality
ChatLiteLLM andChatLiteLLMRouter also support async and streaming functionality:
asyncfor tokenin 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 reference
For detailed documentation of allChatLiteLLM andChatLiteLLMRouter features and configurations, head to the API reference:https://github.com/Akshay-Dongare/langchain-litellm
Related
- Chat modelconceptual guide
- Chat modelhow-to guides