ragent-chatbot

# 🤖 RAGent Chatbot — Intelligent RAG + ReAct Assistant

> 💡 **Blog Guide**: [How This Chatbot is Built](https://shafiqulai.github.io/blogs/blog_6.html)

The **RAGent Chatbot** is a smart, modular, and explainable AI assistant that combines **Retrieval-Augmented Generation (RAG)** with **ReAct-style agent reasoning**. It goes beyond document Q&A — deciding when to read, when to think, and when to act using tools like web search, Wikipedia, calculator, and more.

<div align="center">
  <img src="figure/thumbnail.png" width="75%" alt="RAGent Chatbot UI Preview"/>
</div>


## 🧠 What Can RAGent Do?

<ul style="padding-left: 40px;">
  <li>📄 Answer questions from uploaded documents (PDF, DOCX, PPTX, XLSX, TXT, CSV, JSON)</li>
  <li>🛠️ Use external tools dynamically — web search, weather, Wikipedia, calculator, etc.</li>
  <li>🔍 Combine semantic and keyword search using <b>hybrid retrieval</b></li>
  <li>🧠 Think step-by-step using the <b>ReAct agent framework</b></li>
  <li>💬 Maintain chat context using memory for natural multi-turn conversations</li>
</ul>


## 🧱 Architecture Highlights

<ul style="padding-left: 40px;">
  <li>🤖 <b>ReAct Agent</b>: Reasoning + tool calling in a loop: Thought → Action → Observation → Final Answer</li>
  <li>📚 <b>RAG Pipeline</b>: Retrieves relevant chunks from Qdrant DB and answers with Gemini LLM</li>
  <li>🛠️ <b>Custom Tooling</b>: Extensible tool framework (BaseTool) with weather, web, wiki, calculator, LLM, etc.</li>
  <li>💾 <b>Memory</b>: Per-session chat history powered by MemoryManager</li>
  <li>🖥️ <b>Gradio UI</b>: Intuitive chat + upload interface</li>
</ul>


## 🛠 Tech Stack

| Layer        | Technology                          |
|--------------|--------------------------------------|
| 🧠 LLM        | Google Gemini via LangChain          |
| 📦 Embeddings | BAAI/bge-base-en-v1.5               |
| 🔍 Vector DB  | Qdrant (supports hybrid search)     |
| 💬 UI         | Gradio                              |
| 🧰 Tools