Skip to content

Files

Latest commit

author
Arthur Leung
Sep 29, 2024
df8fb59 · Sep 29, 2024

History

History
17 lines (12 loc) · 725 Bytes

README.md

File metadata and controls

17 lines (12 loc) · 725 Bytes

LLM-NVR

This project is a proof of concept for using multi-modal LLMs to integrate with NVRs and perform narration, explanation on top of object detection and tracking.

Setup

  1. Install python3 and activate the venv: python3 -m venv venv
  2. Install requirements: pip install -r requirements.txt
  3. Edit configs in frigate/ subdirectory and bring up Frigate with docker compose: cd frigate && docker-compose up -d frigate nvr
  4. Run docker compose to bring the frontend and backend up: docker-compose up -d
  5. Run the jupyter notebook in analyze.ipynb

Demo

Link

Architecture

architecture