Skip to content

Quick Start Guide

This guide will help you get up and running with DataDialogue in minutes.

Prerequisites

  • Docker
  • Docker Compose

Quick Installation

  1. Clone the repository: 

    git clone https://github.com/ggeop/data-dialogue.git
cd data-dialogue

  2. Start the services: 

    docker-compose --env-file .env.prod up

  3. Access the application at http://localhost:5000

First Steps

  1. Choose Your Model
  2. Select a model provider (Google, OpenAI, Anthropic, or HuggingFace)
  3. For cloud models, you'll need to provide your API key

  4. For local models (HuggingFace), ensure you have sufficient computing power

  5. Connect Your Data Source

  6. Select from supported data sources:
    • PostgreSQL
    • MySQL
    • Databricks
    • MongoDB
    • CSV files

  7. Provide your connection details

  8. Start Querying

  9. Write natural language queries instead of SQL
  10. Get instant results and visualizations
  11. Copy validated queries for reuse

Example Workflow

  1. Select Model: Choose Google Gemini (recommended for beginners)
  2. Connect Data: Link your PostgreSQL database
  3. Write Query: "Show me the top 10 customers by total purchases"
  4. View Results: See the data in a table or chart format
  5. Copy Query: Save the generated SQL for future use

Tips for Success

  • Start with simple queries to test the system
  • Use the "Copy Query" feature to learn how your questions are translated to SQL
  • Try different visualization options for your results
  • Check the Common Issues guide if you encounter problems

Next Steps