https://github.com/njaffe/fast_api_chatbot

FastAPI powered chatbot using OpenAI API.
https://github.com/njaffe/fast_api_chatbot

api chatbot fastapi llms python uvicorn

Last synced: 2 months ago
JSON representation

FastAPI powered chatbot using OpenAI API.

• Host: GitHub
• URL: https://github.com/njaffe/fast_api_chatbot
• Owner: njaffe
• Created: 2025-01-20T23:35:14.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2025-01-20T23:49:14.000Z (over 1 year ago)
• Last Synced: 2025-06-19T05:05:11.021Z (about 1 year ago)
• Topics: api, chatbot, fastapi, llms, python, uvicorn
• Language: Python
• Homepage:
• Size: 5.86 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# LLM-Powered Chatbot with FastAPI

This is a simple chatbot application built with FastAPI, integrated with OpenAI’s GPT-3.5 model for natural language processing. The chatbot responds to user messages using OpenAI’s API and is deployed as a REST API.

## Features

- FastAPI backend for handling API requests.

- OpenAI GPT-3.5 model used for generating chatbot responses.

- Supports async operations for scalable performance.

- Built-in exception handling for error management.

## Requirements

- Python 3.9 or higher

- OpenAI API key

- FastAPI

- Uvicorn (for running the server)

## Setup Instructions

1. Clone the repository

`git clone https://github.com/yourusername/fast_api_chatbot.git`

`cd fast_api_chatbot`

2. Create a virtual environment

    You can use either conda or venv to create your environment. If you prefer conda:

`conda create --name chatbot-env python=3.9`

`conda activate chatbot-env`

    Alternatively, if you’re using venv:

`python -m venv chatbot-env`

`source chatbot-env/bin/activate`  # On Windows: chatbot-env\Scripts\activate

3. Install dependencies

    Install the required Python packages via pip:

`pip install -r requirements.txt`

    You will also need an OpenAI API key. You can obtain one from [OpenAI’s website](https://beta.openai.com/signup/).

4. Set up your environment variables

`OPENAI_API_KEY=your-openai-api-key`

5. Run the application

    Start the FastAPI server using uvicorn:

`uvicorn app.main:app --reload`

    This will run the server locally at http://127.0.0.1:8000.

6. Access the API

    You can interact with the chatbot using the /chat endpoint. The API expects a POST request with a JSON payload:

    Request:

    `{"message": "Hello, how are you?"}`

    Response:

    `{"response": "I'm doing well, thank you!"}`

    You can test the API directly from the Swagger UI, which is automatically generated by FastAPI and available at:

http://127.0.0.1:8000/docs

7. Stop the server

    To stop the server, press Ctrl+C in the terminal.

## File Structure

fast_api_chatbot/


├── app/


│   ├── __init__.py        # FastAPI app setup


│   ├── main.py            # FastAPI app setup


│   ├── chatbot.py         # Chatbot logic using OpenAI


│   └── models.py          # Pydantic models for request/response


├── .env                   # Environment variables (OpenAI API key)


├── requirements.txt       # List of dependencies


└── README.md              # Project documentation

## License

This project is licensed under the MIT License - see the LICENSE file for details.