DocChat 📝🤖

🚀 AI-powered Multi-Agent RAG system for intelligent document querying with fact verification

---

📌 Overview

DocChat is a multi-agent Retrieval-Augmented Generation (RAG) system designed to help users query long, complex documents with accurate, fact-verified answers. Unlike traditional chatbots like ChatGPT or DeepSeek, which hallucinate responses and struggle with structured data, DocChat retrieves, verifies, and corrects answers before delivering them.

💡 Key Features:
✅ Multi-Agent System – A Research Agent generates answers, while a Verification Agent fact-checks responses.
✅ Hybrid Retrieval – Uses BM25 and vector search to find the most relevant content.
✅ Handles Multiple Documents – Selects the most relevant document even when multiple files are uploaded.
✅ Scope Detection – Prevents hallucinations by rejecting irrelevant queries.
✅ Fact Verification – Ensures responses are accurate before presenting them to the user.
✅ Web Interface with Gradio – Allowing seamless document upload and question-answering.

---

🎥 Demo Video

📹 Click here to watch the DocChat demo
(Opens in a new tab)

---

🛠️ How DocChat Works

1️⃣ Query Processing & Scope Analysis

• Users upload documents and ask a question.
• DocChat analyzes query relevance and determines if the question is within scope.
• If the query is irrelevant, DocChat rejects it instead of generating hallucinated responses.

2️⃣ Multi-Agent Research & Retrieval

• Docling parses documents into a structured format (Markdown, JSON).
• LangChain & ChromaDB handle hybrid retrieval (BM25 + vector embeddings).
• Even when multiple documents are uploaded, DocChat finds the most relevant sections dynamically.

3️⃣ Answer Generation & Verification

• Research Agent generates an answer using retrieved content.
• Verification Agent cross-checks the response against the source document.
• If verification fails, a self-correction loop re-runs retrieval and research.

4️⃣ Response Finalization

• If the answer passes verification, it is displayed to the user.
• If the question is out of scope, DocChat informs the user instead of hallucinating.

---

🎯 Why Use DocChat Instead of ChatGPT or DeepSeek?

Feature	ChatGPT/DeepSeek ❌	DocChat ✅
Retrieves from uploaded documents	❌ No	✅ Yes
Handles multiple documents	❌ No	✅ Yes
Extracts structured data from PDFs	❌ No	✅ Yes
Prevents hallucinations	❌ No	✅ Yes
Fact-checks answers	❌ No	✅ Yes
Detects out-of-scope queries	❌ No	✅ Yes

🚀 DocChat is built for enterprise-grade document intelligence, research, and compliance workflows.

---

📦 Installation

1️⃣ Clone the Repository

git clone https://github.com/HaileyTQuach/docchat-docling.git docchat
cd docchat

2️⃣ Set Up Virtual Environment

python3.11 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3️⃣ Install Dependencies

pip install -r requirements.txt

4️⃣ Set Up API Keys

DocChat requires an OpenAI API key for processing. Add it to a .env file:

OPENAI_API_KEY=your-api-key-here

5️⃣ Run the Application

python app.py

DocChat will be accessible at http://0.0.0.0:7860.

🖥️ Usage Guide

1️⃣ Upload one or more documents (PDF, DOCX, TXT, Markdown).

2️⃣ Enter a question related to the document.

3️⃣ Click "Submit" – DocChat retrieves, analyzes, and verifies the response.

4️⃣ Review the answer & verification report for confidence.

5️⃣ If the question is out of scope, DocChat will inform you instead of fabricating an answer.

🤝 Contributing

Want to improve DocChat? Feel free to:

• Fork the repo
• Create a new branch (feature-xyz)
• Commit your changes
• Submit a PR (Pull Request)

We welcome contributions from AI/NLP enthusiasts, researchers, and developers! 🚀

---

📜 License

This project is licensed under a Customed Non-Commercial License – check LICENSE for more details.

---

💬 Contact & Support

📧 Email: [[email protected]]