Skip to content

README.md

Latest commit

 

History

History
151 lines (102 loc) · 2.46 KB

README.md

File metadata and controls

151 lines (102 loc) · 2.46 KB
Raw

🧠 IntelliDoc AI – Local RAG Document Assistant

IntelliDoc AI is a fully local Retrieval-Augmented Generation (RAG) application that lets you upload PDF documents and ask intelligent questions about them using a locally running LLM.

Built with Streamlit + LangChain + Ollama + ChromaDB, it runs entirely on your machine — no external API calls required.

🚀 Features

  • 📄 Upload and chat with multiple PDF documents
  • 🔎 Semantic search using vector embeddings
  • 🤖 Local LLM inference via Ollama
  • 🧠 Retrieval-Augmented Generation (RAG) pipeline
  • 💬 Clean Streamlit chat interface
  • 💾 Persistent vector store (ChromaDB)

🏗️ Tech Stack

  • Frontend: Streamlit
  • LLM: Ollama (Qwen2.5 / Mistral supported)
  • Embeddings: FastEmbed
  • Vector Database: ChromaDB
  • Framework: LangChain

⚙️ Setup Instructions

1️⃣ Clone the Repository

git clone https://github.com/your-username/intellidoc-ai.git
cd intellidoc-ai

2️⃣ Create Virtual Environment

python -m venv venv

Activate:

Mac/Linux

source venv/bin/activate

Windows

venv\Scripts\activate

3️⃣ Install Dependencies

pip install -r requirements.txt

4️⃣ Install & Setup Ollama

Download from:

https://ollama.com

Pull a model:

ollama pull qwen2.5

(Optional alternative)

ollama pull mistral

Ensure Ollama is running in the background.

▶️ Run the Application

streamlit run app.py

Open in browser:

http://localhost:8501

📂 How It Works

  1. Upload a PDF
  2. Text is split into chunks
  3. Chunks are embedded using FastEmbed
  4. Stored in ChromaDB
  5. User query retrieves relevant chunks
  6. Context + Question → LLM → Final Answer

📁 Project Structure

.
├── app.py
├── rag.py
├── requirements.txt
├── chroma_db/
└── README.md

🔐 Why Local RAG?

  • No API costs
  • Full data privacy
  • Works offline
  • Fully customizable
  • Ideal for experimentation & research

📌 Future Improvements

  • DOCX / TXT support
  • Hybrid retrieval (BM25 + embeddings)
  • Streaming responses
  • Cloud deployment
  • Authentication support

👨‍💻 Author

Ashutosh Zawar
MS Computer Science
AI/ML • Backend • Cloud • RAG Systems

⭐ If you found this useful, consider giving it a star!