Chat with PDF Notes system using Python Flask with Source Code

This project demonstrates how to create a local AI chatbot that can read and answer questions from PDF files. Using Python, LangChain, a local LLM (GPT4All), and Flask for the web interface, you can upload any PDF and start chatting with it – all offline, without using any third-party APIs.
Features
Upload and preview PDF files.
Ask questions about the PDF and get contextual answers.
All processing is done locally with no internet or API required.
Real-time typing effect for responses.
Clear chat functionality.
Tech Stack
Python 3.10+
Flask
LangChain
GPT4All (local model)
FAISS (for vector similarity search)
HuggingFace Sentence Transformers
HTML + CSS + JavaScript
Installation Steps
Clone or download the project folder.
Install dependencies:
pip install -r requirements.txt
Download the local LLM model (e.g.,
ggml-gpt4all-j-v1.3-groovy.bin
) and place it in the models folder.
Run the Flask app:
python app.py
Open your browser and visit http://127.0.0.1:5000
Folder Structure
project/
├── app.py
├── uploads/
├── models/
│ └── ggml-gpt4all-j-v1.3-groovy.bin
├── static/
│ └── styles.css
├── templates/
│ └── index.html
└── requirements.txt
Note
This system works completely offline. However, initial model download (GPT4All) and dependencies like HuggingFace models may require one-time internet access.
Credit
Made with ❤️ by Ajvika Labs.in – AI Projects, Source Code, and Video Tutorials.
Download Link
Demo Video

Detailed Project Description

Chat with PDF Notes system using Python Flask with Source Code enables real-time message exchange between users with delivery status, using a persistent connection instead of page refreshes.

How It Works
1. A client connects to the server (or peer) and authenticates.
2. Messages are sent over a persistent channel (sockets, Bluetooth or a realtime database).
3. The server/peer relays each message to the recipient and stores history.
4. Presence, typing and delivery indicators keep the conversation live.

Technology Roles
- Python
- Java
- JavaScript
- Django
- Flask
- Machine Learning
- HTML
- CSS

Implementation Steps
1. Define requirements and draw the ER / class diagram and screen flow.
2. Set up the environment (Arduino IDE) and create the project skeleton.
3. Design the database schema / data model and seed it with sample data.
4. Implement the core modules with validation and role-based access where needed.
5. Build the user interface and connect it to the backend / data layer.
6. Test each module (unit + manual), fix edge cases and secure inputs (SQL injection, XSS, auth).
7. Prepare documentation, screenshots and a demo build.

Key Features
- Real-time delivery
- Chat history
- Presence indicators
- Group or one-to-one chat

Expected Output
On completion the student will have two or more users exchanging messages instantly.

Deliverables
- Complete source code with comments
- Database schema / data model and screen flow
- Project report with screenshots and results
- Demonstration-ready build