> ## Documentation Index
> Fetch the complete documentation index at: https://docs.adaptive-ml.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LangChain

> Make API calls to Adaptive using LangChain Chat models

If you are using a supported LangChain [Chat model class](https://python.langchain.com/docs/integrations/chat/) to invoke an LLM API in your application,
you can continue when switching to Adaptive Engine. You can also [connect proprietary models](/v0.5/integrations/proprietary-models) to be invoked through the Adaptive API.

Currently, the Adaptive API is compatible with the following LangChain Chat models classes:

* [*ChatOpenAI*](https://python.langchain.com/docs/integrations/chat/openai/)
* [*ChatGoogleGenerativeAI*](https://python.langchain.com/docs/integrations/chat/google_generative_ai/)

Below are usage examples for the supported classes:

<Tabs>
  <Tab title="ChatGoogleGenerativeAI">
    ```python theme={null}
    from langchain_google_genai import ChatGoogleGenerativeAI
    import os 

    os.environ["GOOGLE_API_KEY"] = "ADAPTIVE_API_KEY"

    llm = ChatGoogleGenerativeAI(
        model="use_case_key",
        client_options={"api_endpoint": "ADAPTIVE_URL/api/v1/google"},
        transport="rest",
        # api_key="ADAPTIVE_API_KEY"    # alternative to GOOGLE_API_KEY env var
    )
    messages = [
        (
            "system",
            "You are a helpful assistant that translates English to French. Translate the user sentence.",
        ),
        ("human", "I love programming."),
    ]
    response = llm.invoke(messages)
    print(response)
    ```
  </Tab>

  <Tab title="ChatOpenAI">
    ```python theme={null}
    from langchain_openai import ChatOpenAI
    import os 

    os.environ["OPENAI_API_KEY"] = "ADAPTIVE_API_KEY"

    llm = ChatOpenAI(
        model="use_case_key/optional[model_key]",
        base_url="ADAPTIVE_URL/api/v1",
        # api_key="ADAPTIVE_API_KEY"    # alternative to OPENAI_API_KEY env var
    )
    messages = [
        (
            "system",
            "You are a helpful assistant that translates English to French. Translate the user sentence.",
        ),
        ("human", "I love programming."),
    ]
    response = llm.invoke(messages)
    print(response)
    ```
  </Tab>
</Tabs>