Youtube Video Analyzer AI Agent

YouTube Video Inspector

YouTube Video Inspector is a multi-agent-based project that provides basic analysis of YouTube videos. It fetches video statistics, analyzes comments, generates detailed reports, and converts them to PDF format.

<video controls src="assets/youtube-video-inspector.mp4"></video>

https://github.com/user-attachments/assets/bb9aeb3c-1166-4b66-97ad-aa86bd3dcec3

Demo

You can try the YouTube Video Inspector application here.

1. Enter a YouTube video URL in the provided input field.
2. Select an LLM from the dropdown menu.
3. Click "Analyze Video" to start the analysis process.
4. The app will fetch video details, analyze comments, and generate a basic report.
5. Once complete, you can view the analysis results and download the PDF report.

Features

• Fetch and analyze YouTube video metadata
• Analyze video comments and viewer sentiment
• Generate detailed reports on video performance and audience engagement
• Convert reports to PDF format
• Supports multiple LLMs:
  • Llama 3.1 70B Versatile
  • Llama 3 70B
  • Mixtral 8x7B

Installation

Using Docker

The easiest way to run YouTube Video Inspector is using Docker. Pull the latest image from Docker Hub:

docker pull emirhnslspr/youtube-video-analyzer:v0.1

Manual Installation

1. Clone the Repository:

   git clone https://github.com/emirhansilsupur/youtube-video-analyzer.git
   

2. Install Poetry:

   pip install poetry
   

3. Install dependencies:

   poetry install
   

4. Run the Streamlit app:

   streamlit run app.py
   

Configuration

Create a .env file in the project root and add your API keys:

GROQ_API_KEY=your_groq_api_key
YOUTUBE_API_KEY=your_youtube_api_key

Note : You will need to replace your_groq_api_key and your_youtube_api_key with your own API keys. You can obtain these keys by signing up for the respective services:

• Groq API Key: Sign up for a Groq account and generate an API key.
• YouTube API Key: Follow the YouTube Data API v3 documentation to create a project and obtain an API key.

Usage

docker run -p 8501:8501 -v $(pwd)/output:/app/output --env-file .env emirhnslspr/youtube-video-analyzer:v0.1

Workflow

License

This project is licensed under the MIT License - see the LICENSE file for details.