Dialoqbase is an open-source application for creating custom chatbots powered by user-provided knowledge bases. It targets developers and users seeking to build AI assistants with personalized data, leveraging advanced language models and PostgreSQL for efficient vector search and data storage.

How It Works

The application utilizes a stack including React, Node.js, Fastify, LangChain, and PostgreSQL. LangChain orchestrates interactions with various language and embedding models, while PostgreSQL handles vector search and knowledge base storage. Server-Sent Events (SSE) are employed for real-time communication. This architecture allows for flexibility in model selection and robust data management.

Quick Start & Requirements

• Installation: Clone the repository, navigate to the docker directory, edit the .env file (setting DB_SECRET_KEY), and run docker-compose up -d.
• Access: Open http://localhost:3000 in a browser.
• Credentials: Default login is username: admin, password: admin.
• Prerequisites: Docker and Docker Compose.
• Demo:

Highlighted Details

• Supports a wide range of data loaders including websites, PDFs, text files, and YouTube.
• Offers flexibility in choosing language models (OpenAI, Anthropic, Google, Fireworks, Ollama) and embedding models.
• Integrations include web embed scripts, Telegram, Discord, and WhatsApp.
• One-click deployment option available via Railway.

Maintenance & Community

• Active development with a Discord community for support and updates.
• Roadmap and feature requests are managed via GitHub issues.
• Discord

Licensing & Compatibility

• License: MIT.
• Compatibility: Permissive MIT license allows for commercial use and integration into closed-source projects.

Limitations & Caveats

The project is explicitly stated as a side project and not ready for production, warning of potential bugs, security issues, and breaking changes without notice. Notion data loader is currently not supported.