https://github.com/parth1899/chat-with-pdf
Chat-With-PDF is an AI-powered tool that lets users interact with PDF documents using natural language. Built with LangChain, RAG, Qdrant, and Mistral (Groq), it enables efficient document search, question-answering, and retrieval-augmented generation for seamless information extraction.
https://github.com/parth1899/chat-with-pdf
Last synced: 11 months ago
JSON representation
Chat-With-PDF is an AI-powered tool that lets users interact with PDF documents using natural language. Built with LangChain, RAG, Qdrant, and Mistral (Groq), it enables efficient document search, question-answering, and retrieval-augmented generation for seamless information extraction.
- Host: GitHub
- URL: https://github.com/parth1899/chat-with-pdf
- Owner: parth1899
- Created: 2025-01-11T06:12:10.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-26T21:05:36.000Z (over 1 year ago)
- Last Synced: 2025-02-26T22:19:49.496Z (over 1 year ago)
- Language: Python
- Homepage:
- Size: 477 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: ReadMe.md
Awesome Lists containing this project
README
# 🗂️ Chat-With-PDF
## 📌 About the Project
**Chat-With-PDF** is an AI-powered application that allows users to interact with PDF documents using natural language. Built with **LangChain, RAG, Qdrant, and Mistral (Groq)**, this tool enables seamless document search, question-answering, and retrieval-augmented generation (RAG) for a more efficient and intuitive user experience.
---
## 🚀 Features
- **Conversational AI** – Chat with PDFs and get relevant answers instantly.
- **Qdrant Vector Database** – Efficiently stores and retrieves document embeddings.
- **RAG (Retrieval-Augmented Generation)** – Enhances the accuracy of responses by retrieving relevant document sections.
- **Fast Processing** – Leverages Mistral (Groq) for optimized AI interactions.
- **Streamlit Interface** – Easy-to-use web-based application for seamless user experience.
---
## 🛠️ Installation & Setup
### 1️⃣ Run Qdrant using Docker
Ensure Qdrant is running locally before proceeding:
```bash
docker run -p 6333:6333 -v .:/qdrant/storage/ qdrant/qdrant
```
### 2️⃣ Set Up the Qdrant Database
Run the ingestion script to process and store PDF embeddings:
```bash
python ingest_bot.py
```
### 3️⃣ Start the Application
Launch the Streamlit web interface to interact with PDFs:
```bash
streamlit run app_bot.py
```