LangChain is a framework for developing applications powered by language models, and it can be integrated with Cycls to create powerful conversational applications.

​
Prerequisites

To be able to use Langchain, you will need an OpenAI API Key. You can get one by creating an account and heading here. Once you have a key you need to set it to a .env file:

OPENAI_API_KEY=<YOUR_API_KEY>

​
Integrating with Langchain

By following these steps, you can integrate LangChain with Cycls to create an asynchronous application that processes and responds to user messages using LangChain’s capabilities.

1

Set Up Your Environment

First, ensure you have the necessary packages installed. You’ll need langchain-openai, and python-dotenv for managing environment variables.

pip install python-dotenv langchain-openai
2

Import Required Modules

Import the necessary modules, including AsyncApp from Cycls, load_dotenv from dotenv, and Groq from the groq package. Also, import os to access environment variables.

from cycls import AsyncApp
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
import os
3

Load Environment Variables

Use load_dotenv to load your environment variables from a .env file. Ensure you have CYCLS_SECRET_KEY and OPENAI_API_KEY defined in your .env file.

load_dotenv()

secret = os.getenv("CYCLS_SECRET_KEY")
openai_api_key = os.getenv("OPENAI_API_KEY")
4

Initialize the Groq Client

Create an instance of the Groq client using the API key from your environment variables.

llm = ChatOpenAI(api_key=openai_api_key)
5

Initialize the AsyncApp

Create an instance of AsyncApp with the necessary parameters.

app = AsyncApp(
    secret=secret,
    handler="@your-handler",
)
6

Define the Entry Point

Define the entry point function for your application. This function will process incoming messages and use the Groq client to generate a response.

@app
async def entry_point(context):
    received_message = context.message.content.text

    response = llm.invoke(received_message)

    await context.send.text(response)
7

Publish Your App

Finally, publish your app by calling the publish method.

app.publish()
8

Run Your App

Run your app in the directory containing main.py:

python main.py

​
Complete Example

Here is the complete code for integrating Groq with Cycls:

from cycls import AsyncApp
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
import os

load_dotenv()

secret = os.getenv("CYCLS_SECRET_KEY")
openai_api_key = os.getenv("OPENAI_API_KEY")

app = AsyncApp(
    secret=secret,
    handler="@your-handler",
)

llm = ChatOpenAI(api_key=openai_api_key)

@app
async def entry_point(context):
    received_message = context.message.content.text

    response = llm.invoke(received_message)

    await context.send.text(response)

app.publish()