Vector-Knowledge-Base
Active·★ 10·MIT·Updated 2026-03-02
Vector Knowledge Base is a semantic search engine that transforms various document types into a searchable knowledge base. It allows users to upload files like PDFs, Word documents, images, and code, then search them using natural language queries to find relevant information quickly.
#Semantic Search#Vector Database#Document Management#AI Agent Integration#Clustering#Natural Language Processing#FastAPI#Qdrant
01
Features
01Semantic Search
02Auto-Clustering with Semantic Naming
03Multi-Format Document Support (PDF, DOCX, images, code, etc.)
04AI Agent Integration via Model Context Protocol (MCP)
05Interactive 3D Embedding Visualization
02
Compatibility
Python
Runtime
Verified via docs
FastAPI
Backend Framework
Verified via docs
Qdrant
Vector Database
Verified via docs
Docker
Containerization
Verified via docs
Docker Compose
Orchestration
Verified via docs
macOS
OS
Verified via docs
03
Quick start
1
$ git clone https://github.com/i3T4AN/Vector-Knowledge-Base.git
2
$ cd Vector-Knowledge-Base
3
$ docker-compose up -d
04
Use cases
↳Building a personal semantic search engine for various documents.
↳Efficiently searching and organizing research papers, notes, and learning materials.
↳Facilitating AI agent interaction for document creation, search, and management.
↳Managing and exploring large collections of code, images, and office documents.
05
Alternatives
directory-indexer★ 18
Directory Indexer MCP Server - A local MCP Server for indexing your local directories into a knowledgebase for your AI Assistants.
mcp-documentation-server★ 344
MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • Internal guides
emotion_ai★ 13
The Aura Emotion AI system has chroma with a local embedding model, memvid qr code mp4 infinite memory, brainwave and neurochemical simulations, sociobiological reasoning, autonomous subsystem processing with a Gemini flash model so the main model is less taxed, is a MCP client with adaptive tool learning and MCP server.
openchronicle-mcp★ 16
Memory database for LLM agents — persistent keyword + optional semantic memory, project namespacing, served over HTTP REST and MCP from a single ASGI process. SQLite-backed, packaged as a Docker container. Runs on your hardware.
Comments
Log in to leave a comment
No comments yet. Be the first!