Skip to main content

​
Prerequisites

The instructions below assume you are following best practices and have downloaded this git repo into a parent directory at: ~/atai. If you have already installed the ATAI Python Library and cloned the cookbook repository, proceed directly to Quickstart.

​
Install Conda

wget https://repo.anaconda.com/archive/Anaconda3-2022.05-Linux-x86_64.sh
bash Anaconda3-2022.05-Linux-x86_64.sh
source ~/.bashrc

​
Setup dev environment

conda create -n dev_env python=3.10
conda activate dev_env

​
Install ATAI Python Library

git clone [email protected]:archetypeai/python-client.git
cd python-client
python -m pip install .

​
Clone Cookbook Repository

git clone https://github.com/archetypeai/archetypeai-cookbook.git

​
Quick Start

Analyze video content through natural language queries using the interactive CLI.

​
Running the Demo

From the Cookbook root directory with your conda environment activated: 
cd command-line-demos/activity-monitor
python quickstart.py
Sample videos are available in the sample_videos/ directory for testing the demo.

​
Interactive Prompts

  1. API Key: Your ArchetypeAI API key
  2. Input Type: Choose video (local file) or rtsp (camera stream)
  3. Source:
    • For video: Path to video file (drag & drop supported)
    • For RTSP: Camera stream URL
  4. Focus: Your question about the video (e.g., “Is there a person?”, “What’s happening?”)

​
Example Session

=== Activity Monitor Quickstart ===

Enter your ArchetypeAI API key: your-key-here

Input type (video/rtsp): video
Enter path to video file: /path/to/security_footage.mp4

What should the monitor look for? (e.g., 'person entering', 'vehicle'): Is there anyone at the door?

--- Configuration Summary ---
Input: VIDEO
Video file: /path/to/security_footage.mp4
Focus: Is there anyone at the door?

Press Enter to start monitoring...

🔍 Monitoring started - Looking for: 'Is there anyone at the door?'

Response: No, the door area is empty. I can see a driveway and front yard but no person present.
Response: Yes, there is a person approaching the front door carrying a package.

​
Output

The system provides natural language responses to your questions about the video content. Responses update as the video progresses (for files) or continuously (for RTSP streams).

​
Step Size Configuration (in review)

The step size defines the interval between analyzed frames in each inference cycle. A larger step size means fewer frames are examined, which can reduce detail but speed up processing. A smaller step size increases context for answering queries, but may require more computation.
  • Default: 60 - Optimal for most scenarios
  • Short videos: 30 - Ensures sufficient granularity for brief clips
  • Long-form content: 90-120 - Captures broader context and patterns