ViditOstwal/TEXT-2-SQL-CHATBOT

Pharma Data QA — Text-to-SQL Chatbot

About

This application is a Text-to-SQL Chatbot designed to answer natural language questions about pharmaceutical sales and prescription data. It leverages a Large Language Model (LLM) to translate user queries into SQL, executes them against a local SQLite database (pharma_data.db), and presents the results in an interactive interface.

Key features:

• —Natural Language Querying: Ask questions like "Which territory has the highest prescription volume?" without knowing SQL.
• —Transparent Logic: View the generated SQL, the raw result, and a natural language explanation of the answer.
• —Interactive UI: Built with Gradio for a user-friendly experience.

Setup

This project uses uv for fast Python package management.

Prerequisites

• —Python 3.11 or higher
• —uv installed

Installation

1. 1.Install uv (if not already installed):

    curl -LsSf https://astral.sh/uv/install.sh | sh

1. 1.Clone the repository Navigate to the project directory.

1. 1.Sync dependencies: This command will create a virtual environment and install all dependencies defined in pyproject.toml.

    uv sync

1. 1.Set up environment variables:

    export OPENAI_API_KEY="your_openai_api_key_here"

Running the Application

To run the Gradio application:

uv run app.py

The application will launch in your browser (typically at http://127.0.0.1:7860).