xndien2004/LLM_Powered_Video_Search

[SOICT 2024] LLM-Powered Video Search: A Comprehensive Multimedia Retrieval System

21
/ 100
Experimental

Combines CLIP vision embeddings with FAISS indexing and TF-IDF for hybrid multimodal search across text (ASR/OCR/captions), images, and metadata attributes. LLM integration processes natural language queries to contextually route requests across these retrieval modalities. Built on Django with TransnetV2 for automated keyframe extraction and supports Docker deployment for the complete pipeline.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

65

Forks

1

Language

Jupyter Notebook

License

Last pushed

Aug 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/xndien2004/LLM_Powered_Video_Search"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.