Building a Media Detective for Contextual Image Discovery

Description and use

Media Detective automatically searches multiple licensed sources for contextual images and videos, deduplicates results, caches queries, and tracks attribution, simplifying media discovery for content creators.

Problem

Finding contextual, licensed images and videos for news or content creation is difficult because stock sites offer generic media and search engines return irrelevant results.

Outcome

The Media Detective delivers contextual, licensed media from multiple sources, eliminates duplicates, caches queries to respect rate limits, and tracks attribution, enabling creators to find relevant images and videos efficiently.

Workflow

• Define the topic to search for
• Invoke Media Detective’s get_images_for_topic with desired count
• The detective queries Pexels, Pixabay, Wikimedia Commons, and Archive.org for images and videos
• Results are deduplicated using perceptual hashing
• Cached queries reduce API calls
• Attribution information is stored for each media item
• Return the curated list of media to the user

Evidence

The detective searches all sources for contextual images

Source

To avoid using the same image twice, the detective uses perceptual hashing (pHash 8x8 - 16 hex chars).

Source

The detective caches recent queries (2 hours) to avoid API rate limits.

Source