Data Analysis API

A FastAPI application that provides AI-powered natural language querying of database tables, built with FastAPI, asyncpg, and pydantic-ai.

Features

• Natural language querying of database tables
• CSV data import
• Multi-agent AI system for query understanding and data analysis
• RESTful API with OpenAPI documentation

Setup

1. Clone the repository

git clone <repository-url>
cd <project-directory>

2. Install dependencies

pip install -r requirements.txt

3. Set up environment variables

Create a .env file based on .env.example with your configuration:

cp .env.example .env
# Edit .env with your settings

4. Set up the database

python scripts/setup_db.py

5. Run the application

Development mode:

uvicorn app.main:app --reload

Production mode:

gunicorn app.main:app -k uvicorn.workers.UvicornWorker -w 4

API Usage

After starting the server, visit:

• API documentation: http://localhost:8000/docs
• ReDoc alternative documentation: http://localhost:8000/redoc

Core Endpoints

• GET /api/v1/tables: List all available tables
• GET /api/v1/tables/{table_name}: Get detailed table information
• POST /api/v1/query: Analyze a natural language query
• POST /api/v1/import/csv: Import data from CSV file

CSV Import Tool

You can import CSV files directly from the command line:

python scripts/import_csv_cli.py path/to/your/file.csv --table optional_table_name

Development

The project follows a modular structure:

• app/: Main application package
  • main.py: FastAPI application entry point
  • config.py: Configuration settings
  • database.py: Database connection handling
  • models/: Pydantic schemas
  • api/: API routes and dependencies
  • agents/: AI agents for various tasks
  • services/: Business logic
  • utils/: Utilities and helpers