Integrating with Chainlit

In this guide we'll walk through a quick demo app of using BREVIAN's SDK to integrate with Chainlit.

Prerequisites

BREVIAN sdk setup: https://docs
Chainlit setup: https://docs.brevian.ai/sdks#python
BREVIAN API Token: Securely generated from BREVIAN's API keys page.

Always keep your token safe and disable it if you suspect it has been compromised.

Step-by-Step Guide

1. Setup BREVIAN API Token

Follow the chainlit guide to setup a demo script.

Chainlit

2. Simple Example

import chainlit as cl

from brevian import PostChatRequestMessagesItem, PostChatRequestMessagesItemRole
from brevian.client import BrevianApi

client = BrevianApi(
    token={"token"},
    base_url="https://chat.brevian.ai/api/v1/",
)


@cl.on_message  # this function will be called every time a user inputs a message in the UI
async def main(message: cl.Message):
    """
    This function is called every time a user inputs a message in the UI.
    It sends back an intermediate response from the tool, followed by the final answer.

    Args:
        message: The user's message.

    Returns:
        None.
    """

    # Call the BREVIAN
    response = client.post_chat(
        messages=[
            PostChatRequestMessagesItem(
                role=PostChatRequestMessagesItemRole.USER,
                content=message.content,
            )
        ],
        agent_id="{find this is the URL of the agent you want to use e.g e1bf33db-feb6-49a3-a766-2e727ded3ee9}",
    )

    # Send the final answer.
    await cl.Message(content=response.choices[0].message.content).send()

3. Run the app!

chainlit run demo.py -w