2dogsandanerd/Knowledge-Base-Self-Hosting-Kit
A Docker-powered RAG system that understands the difference between code and prose. Ingest your codebase and documentation, then query them with full privacy and zero configuration.
Combines ChromaDB and Docling for hybrid chunking with vector + BM25 fusion search, enabling semantic queries with citations across mixed document types. Exposes a FastAPI backend with live configuration management through the UI's Agent Configuration tab, allowing real-time tuning of MCP connections and LLM settings without container restarts. Integrates with local Ollama instances or OpenAI-compatible endpoints, and surfaces an MCP server for autonomous agent frameworks like OpenClaw.
220 stars.
Stars
220
Forks
24
Language
Python
License
—
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/2dogsandanerd/Knowledge-Base-Self-Hosting-Kit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ConardLi/easy-dataset
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
ItzCrazyKns/Vane
Vane is an AI-powered answering engine.
DS4SD/deepsearch-toolkit
Interact with the Deep Search platform for new knowledge explorations and discoveries
xuwei95/ezdata
基于python和llm大模型开发的数据处理和任务调度系统。...
ModelEngine-Group/DataMate
DataMate is an enterprise-level data processing platform designed for model fine-tuning and RAG...