NeuroQuery: Intelligent Answers from Your Documents

A state-of-the-art document question answering system that extracts knowledge from your PDFs using AI.

Features

Feature	Description
📄 Multi-PDF Processing	Upload and analyze up to 3 PDFs simultaneously (300 pages max each)
💬 Natural Language Interface	Ask questions in plain English about your documents
🧠 Smart Context Understanding	Gemini AI provides accurate answers based on document content
⚡ Fast Retrieval	Chroma vector database enables quick information lookup

Technical Architecture

graph TD
    A[PDF Upload] --> B[Text Extraction]
    B --> C[Chunking]
    C --> D[Vector Embeddings]
    D --> E[Chroma DB Storage]
    E --> F[User Query]
    F --> G[Relevant Chunk Retrieval]
    G --> H[Gemini Answer Generation]
    H --> I[Response Display]

Loading

Technology Stack

Core Libraries

Category	Libraries
Framework	langchain, langchain_community
AI Models	langchain_google_genai (Gemini)
Vector DB	langchain_chroma
PDF Processing	pypdf, pdfminer.six, unstructured
Utilities	python-dotenv, nest_asyncio, sentence-transformers
UI	streamlit

Setup Instructions

Prerequisites

• Python 3.8+
• Google API key with Gemini access

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/neuroquery.git
   cd neuroquery

2. Create and activate virtual environment:

   python -m venv venv
   source venv/bin/activate  # Linux/Mac
   venv\Scripts\activate  # Windows

3. Install dependencies:

   pip install -r requirements.txt

4. Create .env file:

   GOOGLE_API_KEY=your_api_key_here

Running the Application

streamlit run app.py

Deployment Options

Platform	Instructions
Streamlit Cloud	Deploy Guide
Hugging Face	Spaces Guide
AWS/Azure	Use Docker with Streamlit server

Usage Guide

1. Upload PDF documents (max 3 files)
2. Wait for processing to complete
3. Ask questions about the document content
4. View AI-generated answers with source references

Troubleshooting

• Processing Errors: Ensure PDFs contain selectable text (not scanned images)
• API Errors: Verify your Google API key has Gemini access
• Performance: For large documents, increase chunk size in config.py

License

MIT License

---

Developed with ❤️ by Jasjeev Singh Kohli