LLM App With LCEL

This repository provides a basic Language Model (LLM) application using Langchain Expression Language (LCEL). It covers the basics of building an API with FastAPI, handling requests with requests, running the server with uvicorn, and creating a client with Streamlit. You can also test the API on Postman. Screenshots are attached to help illustrate the workflow.

Overview

The project demonstrates how to:

• Build a FastAPI server that leverages Langchain components for prompt engineering and language model inference.
• Create a simple client using the requests library and Streamlit to interact with the API.
• Integrate several important libraries, including FastAPI, uvicorn, python-dotenv, langchain_groq, langchain_core, and streamlit.
• Cover the basics of API development, deployment, and testing.

Features

• FastAPI Server:
  Provides a RESTful API endpoint that accepts a text input and a target language, translates the input using a configured language model, and returns the response.

• Client Application:
  A simple Streamlit app that allows users to input text, select a target language, and see the translated output.

• API Testing:
  You can test the API endpoint on Postman by sending a POST request to the /chain/invoke endpoint.

Technologies and Libraries

• FastAPI: A modern, fast (high-performance) web framework for building APIs with Python.
• uvicorn: An ASGI server used to run the FastAPI application.
• requests: For making HTTP requests in the client.
• python-dotenv: Loads environment variables from a .env file.
• langchain_groq: For interacting with the language model via the Groq API.
• langchain_core: Provides core prompt templating and output parsing functionalities.
• Streamlit: Used to build the simple client UI for interacting with the API.

---

Installation

1. Clone the repository:

   git clone https://github.com/EniolaAdemola/LLM-App-With-LCEL.git

   cd LLM-App-With-LCEL
   

2. Create and activate a virtual environment (optional but recommended) for me i used conda:

   conda create -p venv python==3.10 -y

   conda activate venv
   

3. Install the required libraries:

   pip install -r requirements.txt
   

4. Set up environment variables: Create a .env file in the root directory with the following keys:

   GROQ_API_KEY=your_groq_api_key

---

Running the Application

1. Start the Server

To run the FastAPI server, execute:

python server\server.py

The server will be accessible at http://127.0.0.1:8000. Make sure to add "/docs" to view the Langserve documentations (http://127.0.0.1:8000/docs/)

2. Run the Streamlit Client

To start the client application, run:

streamlit run client\client.py

You can then interact with the LLM application using the provided web interface.

---

API Endpoints

POST /chain/invoke This endpoint accepts a JSON payload with the following structure:

{
    "input": {
        "language": "French",
        "text": "Your input text here"
    },
    "config": {},
    "kwargs": {}
}

It returns a JSON response with the translated or processed output.

Testing with Postman

You can test the API on Postman by sending a POST request to:

streamlit run client\client.py](http://127.0.0.1:8000/chain/invoke

Make sure to set the request body to JSON with the structure shown above.

🤝 Contributing

Contributions are welcome! Feel free to submit a PR or open an issue.

📞 Contact

For inquiries, reach out to Eniola Ademola.

---