dyj-naj/agentic-rag-knowledge-assistant

★ 14PythonAudience · developerComplexity · 4/5Setup · hard

Mindmap

mindmap
  root((agentic-rag))
    Pipeline stages
      Query rewriting
      Sub-question splitting
      Multi-source retrieval
      Relevance checking
      Answer generation
      Hallucination check
    Data sources
      Vector database
      Keyword search
      Relational database
      Live web search
    Features
      Multi-user knowledge bases
      File upload support
      Conversation history
    Tech stack
      Python FastAPI
      React frontend
      Qdrant
      DeepSeek or Qwen

mindmap root((agentic-rag)) Pipeline stages Query rewriting Sub-question splitting Multi-source retrieval Relevance checking Answer generation Hallucination check Data sources Vector database Keyword search Relational database Live web search Features Multi-user knowledge bases File upload support Conversation history Tech stack Python FastAPI React frontend Qdrant DeepSeek or Qwen

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Upload company documents and ask natural-language questions across all of them with automatic web search fallback

USE CASE 2

Build a private per-user knowledge base where each person's uploaded files are kept separate and searchable

USE CASE 3

Use the hallucination-check and retry loop as a reference for building self-correcting RAG pipelines in your own projects

Tech stack

PythonFastAPIReactQdrantMySQLDocker

Getting it running

Difficulty · hard Time to first run · 1h+

Requires a running Qdrant vector database via Docker, an API key for DeepSeek or Qwen, and optionally MySQL and a Serper web search API key.

No license information was mentioned in the explanation.

In plain English

This repository contains a question-answering system built around a technique called Retrieval-Augmented Generation, or RAG. The basic idea behind RAG is that instead of relying purely on an AI model's internal knowledge, you also pull in relevant information from external sources at the time of each question, then combine that information with the AI's reasoning to generate a more accurate answer. This project takes that idea several steps further by adding a multi-stage pipeline with quality checks and automatic retry loops. When a user asks a question, the system runs it through seven stages. It first rewrites and expands the question to make it more searchable, then decides whether the question even needs external information or can be answered directly. Complex questions are broken into smaller sub-questions. The system then searches four different sources simultaneously: a vector database (which finds content based on meaning rather than exact words), a keyword search index, a relational database for structured data, and a live web search. Results are checked for relevance, and if they do not match well enough, the system retries with a refined query. The answer is generated from whatever was retrieved, and then a final quality check looks for hallucinations, logical errors, and missing information. If the answer fails that check, the whole process starts over from query rewriting. The system supports multiple users, each with their own private knowledge base. A user can upload PDF, Word, Excel, PowerPoint, or text files, and the system automatically converts them into a searchable format. Conversation history is kept across sessions with a three-tier compression approach: recent messages are stored fully, older ones are progressively summarized to save space. The project is written in Python with FastAPI on the back end and React on the front end. The README is written in Chinese. Setup requires a running Qdrant vector database (available via Docker), an API key for a compatible AI model such as DeepSeek or Qwen, and optionally a MySQL database and a Serper web search API key. The README includes detailed setup instructions and a breakdown of every source file.

Copy-paste prompts

Prompt 1

I want to set up agentic-rag-knowledge-assistant locally. Walk me through starting Qdrant with Docker, getting a DeepSeek API key, and running the FastAPI backend and React frontend.

Prompt 2

How does agentic-rag-knowledge-assistant handle multi-user isolation? I want to make sure one user cannot access another user's uploaded documents.

Prompt 3

I want to add a new file type to agentic-rag-knowledge-assistant beyond PDF and Word. Which part of the code handles document ingestion and conversion to a searchable format?

Prompt 4

Explain the seven-stage pipeline in agentic-rag-knowledge-assistant. I want to add a custom stage that logs each retrieval result to a database for auditing.

Open on GitHub → Explain another repo

← dyj-naj on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.