Ollama PostgreSQL Data Analysis

🚀 Ollama MCP Database Assistant

An interactive chat interface that combines the large language model (LLM) capabilities of Ollama with a PostgreSQL database via the Model Context Protocol (MCP). Ask questions about your data in natural language and get AI-driven responses backed by real SQL queries.

🚀 Quick Start

This application allows you to interact with your PostgreSQL database using natural language. Just follow the steps below to get started.

✨ Features

• Access PostgreSQL databases through a natural language interface.
• Automatically generate SQL queries.
• Provide responses based on the database schema.
• Offer an interactive chat interface.
• Ensure secure read-only database access.

📦 Installation

Prerequisites

• Node.js version 16 or higher.
• A running PostgreSQL database.
• Ollama installed and running locally.
• The qwen2.5-coder:7b-instruct model pulled in Ollama.

Steps

1. Clone the repository:

git clone [your-repo-url]
cd [your-repo-name]

2. Install dependencies:

npm install

3. Pull the required Ollama model:

ollama pull qwen2.5-coder:7b-instruct

4. Create a .env file in the project root directory:

DATABASE_URL=postgresql://user:password@localhost:5432/dbname
OLLAMA_MODEL=qwen2.5-coder:7b-instruct  # Optional, default value is qwen2.5-coder:7b-instruct

💻 Usage Examples

Basic Usage

1. Start the chat interface:

npm start

2. Ask questions about your data in natural language:

Connected to the database. You can now ask questions about your data.
Type "exit" to quit.

What data would you like to know? Which products generated the most revenue last month?
Analyzing...

[AI will generate and execute an SQL query, then explain the results]

3. Type 'exit' to exit the application.

📚 Documentation

How It Works

1. The application connects to your PostgreSQL database via the PostgreSQL MCP server.
2. It loads and caches your database schema.
3. When you ask a question:
   • The schema and the question are sent to Ollama.
   • Ollama generates an appropriate SQL query.
   • The query is executed via MCP.
   • The results are returned to Ollama for interpretation.
   • You receive a response in natural language.

Environment Variables

Security

• Read-only access only.
• SQL query restrictions.

Development Information

• Technologies used: TypeScript, MCP, Node.js, etc.

Troubleshooting

Common Issues

1. Unable to connect to the database
   • Check if the DATABASE_URL is correct.
   • Ensure that the PostgreSQL service is running.
2. Ollama does not respond
   • Make sure Ollama is installed and running.
   • Check your network connection.
3. Incorrect environment variable configuration
   • Verify the values in the .env file.

📄 License

[Fill in the license information here]

Contribution Guidelines

Contributions are welcome! Please refer to the Contribution Guidelines