PRIYANSHUDHAKED/Intelligent_QA_with_VIDEO_System

Intelligent Video Q&A App with Gemini Vision Pro

This application processes video content using Google's Gemini Vision Pro API, extracts information, and allows users to ask questions about the video. It uses advanced AI techniques to provide intelligent responses.

Features

• —Video upload and processing
• —Text and information extraction from video frames using Gemini Vision Pro
• —Audio transcription (assuming Gemini Vision Pro supports audio)
• —Content summarization
• —Code extraction from video content
• —Question-answering based on video content
• —Similar video search

Setup

1. 1.Clone the repository
2. 2.Install dependencies: pip install -r requirements.txt
3. 3.Set up your Gemini API key in the .env file
4. 4.Run the app: streamlit run app.py

Usage

1. 1.Upload a video file
2. 2.Adjust the summary length as needed
3. 3.Process the video
4. 4.Ask questions about the video content
5. 5.Explore similar videos

Technologies Used

• —Streamlit
• —OpenCV
• —Gemini Vision Pro API
• —Google GenerativeAI
• —LanceDB

Note: Make sure you have access to the Gemini Vision Pro API and have set up the necessary credentials.