OpenAPI Spec Generator

This FastAPI application generates OpenAPI v3 specifications based on user prompts using an AI model. It also logs all requests and responses.

Table of Contents

• Features
• Requirements
• Installation
• Usage
• API Endpoints
• Database
• Docker Deployment
• Contributing
• License

Features

• Generate OpenAPI v3 specifications from user prompts
• Log all requests and responses
• Retrieve logs of past interactions
• Dockerized application for easy deployment

Requirements

• Python 3.12+
• FastAPI
• Pydantic
• OpenAI Python Client
• Peewee ORM
• Uvicorn ASGI server

Installation

1. Clone the repository:

   git clone https://github.com/0xstackforge/openapi-spec-generator.git
   cd openapi-spec-generator
   

2. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`
   

3. Install the required packages:

   pip install -r requirements.txt
   

Usage

1. Start the FastAPI server:

   uvicorn main:app --reload
   

2. The API will be available at http://localhost:8000

3. Use the /openapi-spec-generator endpoint to generate OpenAPI specifications

4. View logs using the /logs endpoint

API Endpoints

POST /openapi-spec-generator

Generate an OpenAPI v3 specification based on a user prompt.

Request Body:

{
  "prompt": "Create an API for a todo list application"
}

Response:

A JSON object containing the generated OpenAPI v3 specification.

GET /logs

Retrieve the logs of past interactions.

Query Parameters:

• limit (optional): Number of log entries to return (default: 1000)

Response:

An array of log entries, each containing:

• timestamp: The time of the request
• request: The original request
• response: The generated response

Database

The application uses SQLite to store logs. The database file ai_service.db will be created in the project root directory.

Docker Deployment

Local Development with Docker Compose

Prerequisites

• Docker
• Docker Compose

Steps

1. Build and start the services:

docker-compose up --build

2. Access the application:

• Main application: http://localhost:8000
• Ollama API: http://localhost:11434

3. Stop the services:

docker-compose down

Running with Docker

To run the application using Docker directly:

1. Build the Docker image:

   docker build -t openapi-spec-generator .
   

2. Run the container:

   docker run -p 8000:8000 openapi-spec-generator
   

The API will be available at http://localhost:8000

Entity Relationship Diagram

erDiagram
    LogEntry {
        int id PK
        datetime timestamp
        text request
        text response
    }

Loading

Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/your-feature-name)
3. Commit your changes (git commit -m 'Add your feature')
4. Push to the branch (git push origin feature/your-feature-name)
5. Open a Pull Request

License

• Will