A Streamlit application that combines video analysis and web search capabilities using Google's Gemini 2.5 model. This agent can analyze uploaded videos and answer questions by combining visual understanding with web-search.
Sign in to save downloads to your library and vote.
Preview
🧬 Multimodal AI Agent
A Streamlit application that combines video analysis and web search capabilities using Google's Gemini 2.5 model. This agent can analyze uploaded videos and answer questions by combining visual understanding with web-search.
Features
- Video analysis using Gemini 2.5 Flash/Pro
- Web research integration via DuckDuckGo
- Support for multiple video formats (MP4, MOV, AVI)
- Real-time video processing
- Combined visual and textual analysis
How to get Started?
- Clone the GitHub repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd starter_ai_agents/multimodal_ai_agent
- Install the required dependencies:
pip install -r requirements.txt
- Get your Google Gemini API Key
- Sign up for an Google AI Studio account and obtain your API key.
- Set up your Gemini API Key as the environment variable
GOOGLE_API_KEY=your_api_key_here
- Run the Streamlit App
streamlit run multimodal_agent.py
Ingestion metadata
- Source catalog
- awesome-llm-apps
- Repository
- Shubhamsaboo/awesome-llm-apps · main
- File path
- starter_ai_agents/multimodal_ai_agent/README.md
- Last refreshed
- 7/23/2026, 8:42:18 PM (3mo ago)
- Refresh schedule
- Daily · 03:00 UTC
- Dedupe status
- Unique · deduped by (source, url)