🎥 AI YouTube Video Analyzer

An advanced, dual-column AI dashboard designed to ingest any YouTube URL and perform deep semantic content analysis. Extract structured reports, generate logical segment chapters with timestamps, identify key action items, and converse directly with a dedicated AI Video Agent about the video's contents.

🔗 Live Application URL: https://mihir-youtube-analyzer-agent.streamlit.app

---

✨ Features

• 🎥 Interactive Dual-Column Interface: View the embedded video player side-by-side with real-time AI reports and chat panels.
• 📊 Comprehensive Video Metadata: Automatically retrieves video details such as Title, Creator/Channel, and dimensions via oEmbed metadata.
• 🕒 Structured Timestamps & Chapters: Generates structured timestamps marking key logical transitions and topical segments in the video.
• 💡 Action Items & Takeaways: Dynamically compiles the core takeaways, highlights, and lessons from the video.
• 💬 Conversational Video Chat: Chat dynamically with the video context. Ask the Llama AI agent follow-up questions specifically about the video contents.
• ⚙️ Dynamic Configurations:
  • API Status Badges: Active indicators verifying API key status.
  • Key Overrides: Paste custom keys (GROQ_API_KEY, YOUTUBE_API_KEY) directly into the UI.
  • Model Selector: Choose between multiple LLMs (e.g., llama-3.3-70b-versatile, llama-3.1-8b-instant, mixtral-8x7b-32768).
  • Analysis Depth: Toggle between Brief, Standard, or Comprehensive depth levels.
• 🎨 Premium Slate Theme: Optimized using a tailored YouTube-inspired slate-dark aesthetic.

---

🛠️ Technology Stack

• Frontend Dashboard: Streamlit
• AI Agentic Framework: Agno (formerly Phidata)
• Large Language Models: Groq Cloud (Llama 3.3/3.1, Mixtral)
• Transcripts API: youtube-transcript-api
• YouTube Metadata: google-api-python-client

---

🚀 Local Installation & Setup

Follow these steps to run the application locally on your machine:

1. Clone the Repository

git clone https://github.com/mihirgupta665/Youtube-Analyzer-Agent.git
cd Youtube-Analyzer-Agent

2. Create and Activate a Virtual Environment

# Using conda
conda create -n dl_env python=3.10
conda activate dl_env

# Or using venv
python -m venv venv
source venv/bin/activate  # On macOS/Linux
venv\Scripts\activate     # On Windows

3. Install Dependencies

pip install -r requirements.txt

4. Set Up Environment Secrets

Create a .env file in the root directory (or .streamlit/secrets.toml):

GROQ_API_KEY="your_groq_api_key"
GOOGLE_API_KEY="your_google_youtube_api_key" # Optional (falls back to scraping)

5. Run the Application

streamlit run streamlit_app.py

Open http://localhost:8501 in your browser.

---

☁️ Deploying to Streamlit Community Cloud

If you want to host your own clone of this app online:

1. Push your code to GitHub (ensure .env and .streamlit/secrets.toml are gitignored).
2. Log in to Streamlit Share.
3. Click Create app -> Select your repository, set the branch to master (or your active branch), and set the Main file path to streamlit_app.py.
4. Click Advanced settings, paste your secrets in TOML format:

   GOOGLE_API_KEY = "your-google-api-key"
   GROQ_API_KEY = "your-groq-api-key"

5. Click Save and Deploy!

---

📄 License

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