martin-papy/qdrant-loader

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration.

61
/ 100
Established

This toolkit helps organizations transform their internal documents, code, and project data from sources like Confluence, Jira, and Git into a searchable knowledge base. It ingests various file types including PDFs, Office documents, and images, intelligently processes them, and then allows AI development tools to perform semantic searches for information. This is ideal for developers and technical teams building AI assistants that need to understand and retrieve information from complex, enterprise-level content.

Available on PyPI.

Use this if you need to create a unified, AI-searchable knowledge base from disparate enterprise data sources (documentation, code, tickets) to power intelligent AI assistants for your development team.

Not ideal if you are looking for a simple document search solution that doesn't require integrating with AI development tools or managing complex, multi-source enterprise content.

knowledge-management technical-documentation software-development enterprise-search AI-assistant-integration
Maintenance 10 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

31

Forks

20

Language

Python

License

GPL-3.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

41

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/martin-papy/qdrant-loader"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.