ChatPerplexity Class — langchain Architecture

Source Code

libs/partners/perplexity/langchain_perplexity/chat_models.py lines 105–816

class ChatPerplexity(BaseChatModel):
    """`Perplexity AI` Chat models API.

    Setup:
        To use, you should have the environment variable `PPLX_API_KEY` set to your API key.
        Any parameters that are valid to be passed to the perplexity.create call
        can be passed in, even if not explicitly saved on this class.

        ```bash
        export PPLX_API_KEY=your_api_key
        ```

        Key init args - completion params:
            model:
                Name of the model to use. e.g. "sonar"
            temperature:
                Sampling temperature to use.
            max_tokens:
                Maximum number of tokens to generate.
            streaming:
                Whether to stream the results or not.

        Key init args - client params:
            pplx_api_key:
                API key for PerplexityChat API.
            request_timeout:
                Timeout for requests to PerplexityChat completion API.
            max_retries:
                Maximum number of retries to make when generating.

        See full list of supported init args and their descriptions in the params section.

        Instantiate:

        ```python
        from langchain_perplexity import ChatPerplexity

        model = ChatPerplexity(model="sonar", temperature=0.7)
        ```

        Invoke:

        ```python
        messages = [("system", "You are a chatbot."), ("user", "Hello!")]
        model.invoke(messages)
        ```

        Invoke with structured output:

        ```python
        from pydantic import BaseModel


        class StructuredOutput(BaseModel):
            role: str
            content: str


        model.with_structured_output(StructuredOutput)
        model.invoke(messages)
        ```

        Stream:
        ```python
        for chunk in model.stream(messages):
            print(chunk.content)
        ```

        Token usage:
        ```python
        response = model.invoke(messages)
        response.usage_metadata
        ```

        Response metadata:
        ```python
        response = model.invoke(messages)
        response.response_metadata
        ```
    """  # noqa: E501