KB-Agent-Platform — Enterprise Knowledge Base Q&A Platform (RAG + Multi-Agent + MCP)

In one sentence: an enterprise knowledge base Agent based on RAG and LangGraph Supervisor, with SSE streaming Q&A with citation tracing, dual MCP entry points, and one-click deployment via docker compose.

Architecture

Frontend Vue3 ──SSE──> FastAPI ──> Supervisor (LLM routing) ──┬─> KB Agent ──> Qdrant (4096-dim) └─> Chat Agent MCP Host (Cursor/Claude) ──stdio──> MCP Server ──> same Qdrant

Related MCP server: tero-mcp-lite

Quick Start

1. https://github.com/embracingTheFuture/kb-agent-platform.git && cd kb-agent-platform

2. cp .env.example .env # fill in your key

3. docker compose up --build -d

4. docker compose run --rm api python task2_pipeline.py # ingest data

5. Open http://localhost:8000/docs

Screenshots

Quality: Evaluation Set Regression

6 test cases covering routing correctness + citation integrity, reproducible inside the container.

Technical Highlights

• Handwritten ReAct core (tool registry + while loop, no framework)

• Self-developed chunking-vectorization-retrieval pipeline, Qdrant cosine similarity

• Citation tracing: numbered context + [i] annotations + citations structure

• Supervisor multi-agent routing + conversation memory compression (rolling summary)

• MCP Server dual entry points / SSE streaming / evaluation set regression