ChatPDF: A Local RAG System for Querying PDFs

ChatPDF is a local Retrieval-Augmented Generation (RAG) system designed to query PDF documents. It combines a local vector database (ChromaDB) and a language model (Ollama models like Vicuna) to provide fast, accurate, and private answers based on document content.

✨ Features

• Privacy-Focused: All processing is done locally—no cloud dependency.
• PDF Support: Upload one or more PDF documents for querying.
• Customizable: Modify prompts to tailor the assistant’s behavior.
• Interactive Interface: User-friendly chat interface powered by Streamlit.
• Expandable: Easily add new documents or adjust the model.

---

📸 Demo

---

🛠 Installation

Follow these steps to set up and run the project:

1. Clone the Repository

git clone git@github.com:your-username/local-rag-chatpdf.git
cd local-rag-chatpdf

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

2. Set Up a Virtual Environment

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

3. Install Dependencies

pip install -r requirements.txt

4. Pull the Language Model

ollama pull mistral

🚀 Usage

1. Start the Streamlit App

Run the following command to launch the application:

streamlit run local_rag_UI.py

2. Interact with the Chat

Upload a PDF file via the interface. Ask questions about the document's content. View responses directly in the chat interface.