Ved Vekhande
ParticipantVed Vekhande
Multimodal Video Search using Videodb FastAPI Streamlit and OpenAI
Multimodal Video Search using Videodb FastAPI Streamlit and OpenAI
AI Demos Website
Individual
July 26, 2025 at 07:55 PM
Project Demo
Submission Details
hear-about-us
AI Demos Website
name
Ved Vekhande
linkedIn-profile
Project Title
Multimodal Video Search using Videodb FastAPI Streamlit and OpenAI
Describe what your project does?
This project solves the pain of finding specific moments in long videos like a goal in a sports match or a quote in a lecture by enabling natural language search over video content. It uses VideoDB to ingest videos, extract multimodal embeddings (from audio, speech, and visuals), and perform semantic search. When a query is made, the system intelligently maps it to the most relevant video segments using OpenAI LLM and returns streamable clips via a FastAPI backend and Streamlit frontend.
Share a 3–5 minute demo video (Google Drive link only) explaining your core idea, tools used (including VideoDB), challenges faced, and how you improved your solution — make sure the link is viewable
Is this project your original and proprietary work?
Yes
Does it include any private, sensitive, or restricted code or content?
No
Do you give us (AI Demos & VideoDB) permission to feature your work on our website and share it with our community (with full credit)?
Yes
Do you consent to us showcasing your name/profile on our social media platforms and YouTube
Yes
Are you open to freelance, internship, or collaborative opportunities based on this project?
Yes, I’m interested