Natural Language Postgres

An Next.js application that allows you to query a PostgreSQL database with natural language.

Natural Language PostgreSQL

This project is a Next.js application that allows users to query a PostgreSQL database using natural language and visualize the results. It's powered by the AI SDK by Vercel and uses OpenAI's GPT-4o model to translate natural language queries into SQL.

Features

Natural Language to SQL: Users can input queries in plain English, which are then converted to SQL using AI.
Data Visualization: Results are displayed in both table and chart formats, with the chart type automatically selected based on the data.
Query Explanation: Users can view the full SQL query and get an AI-generated explanation of each part of the query.

Technology Stack

Next.js for the frontend and API routes
AI SDK by Vercel for AI integration
OpenAI's GPT-4o for natural language processing
PostgreSQL for data storage
Vercel Postgres for database hosting
Framer Motion for animations
ShadowUI for UI components
Tailwind CSS for styling
Recharts for data visualization

How It Works

The user enters a natural language query about unicorn companies.
The application uses GPT-4 to generate an appropriate SQL query.
The SQL query is executed against the PostgreSQL database.
Results are displayed in a table format.
An AI-generated chart configuration is created based on the data.
The results are visualized using the generated chart configuration.
Users can toggle between table and chart views.
Users can request an explanation of the SQL query, which is also generated by AI.

Data

The database contains information about unicorn companies, including:

Company name
Valuation
Date joined (unicorn status)
Country
City
Industry
Select investors

This data is based on CB Insights' list of unicorn companies.

Getting Started

To get the project up and running, follow these steps:

Install dependencies:
```
pnpm install
```

Copy the example environment file:

cp .env.example .env

Add your OpenAI API key and PostgreSQL connection string to the .env file:

OPENAI_API_KEY=your_api_key_here
POSTGRES_URL="..."
POSTGRES_PRISMA_URL="..."
POSTGRES_URL_NO_SSL="..."
POSTGRES_URL_NON_POOLING="..."
POSTGRES_USER="..."
POSTGRES_HOST="..."
POSTGRES_PASSWORD="..."
POSTGRES_DATABASE="..."

Download the dataset:

Go to https://www.cbinsights.com/research-unicorn-companies
Download the unicorn companies dataset
Save the file as unicorns.csv in the root of your project

Seed the database:
```
pnpm run seed
```
Start the development server:
```
pnpm run dev
```

Your project should now be running on http://localhost:3000.

Deployment

The project is set up for easy deployment on Vercel. Use the "Deploy with Vercel" button in the repository to create your own instance of the application.