Bibliothecarius is a local data analysis tool designed for building conversational AI services that integrate custom prompts and local data. It targets individuals and enterprises seeking to create knowledge base Q&A assistants, specialized AI assistants, or even interactive AI experiences, offering support for multiple data types and models for horizontal comparison and data isolation.

How It Works

Bibliothecarius leverages a local data analysis approach, enabling conversational interactions based on user-defined prompts and local data sources. It supports various data types (txt, pdf, md) and models, including GPT3.5, localized models like ChatGLM, and localized vector computation (text2vec). This architecture allows for data isolation and direct comparison between different AI models.

Quick Start & Requirements

• Install/Run: docker-compose up -d after cloning the repository.
• Prerequisites: Docker, Docker Compose. MySQL and Qdrant are required; existing instances can be used or initialized via provided SQL scripts and official Qdrant installation guides.
• Configuration: Modify ./bibliothecarius/config/application.yaml for MySQL, OpenAI key, Qdrant address, and storage settings.
• Resources: Backend service can be verified at http://127.0.0.1:8080/. The frontend is available at ./web.
• Docs: Interface document

Highlighted Details

• Supports multi-round dialogue.
• Integrates with localized vector computation (text2vec).
• Offers horizontal comparison of multiple AI models.
• Handles various data types including txt, pdf, and md.

Maintenance & Community

No specific contributors, sponsorships, or community links (Discord/Slack) are mentioned in the README.

Licensing & Compatibility

The README does not explicitly state a license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is in active development, with plans for a better UI and support for more file types (like docx) still pending. The lack of explicit licensing information may pose a barrier to commercial adoption.