Indexatron: Teaching Local LLMs to See Family Photos
Status: ✅ SUCCESS Hypothesis: Local LLMs can analyse family photos with useful metadata extraction I've been building the-mcculloughs.org - a family photo sharing app. The Rails side handles upload...

Source: DEV Community
Status: ✅ SUCCESS Hypothesis: Local LLMs can analyse family photos with useful metadata extraction I've been building the-mcculloughs.org - a family photo sharing app. The Rails side handles uploads, galleries, and all the usual stuff. But I wanted semantic search - not just "photos from 2015" but "photos at the beach" or "pictures with grandma." The cloud APIs exist. But uploading decades of family photos to someone else's servers? Hard pass. Time for a science experiment - two apps working together. The Experiment I called it Indexatron 🤖 The goal: prove that Ollama running locally with LLaVA:7b and nomic-embed-text can: Analyse photos - Extract descriptions, detect people/objects, estimate era Generate embeddings - Create 768-dimensional vectors for similarity search Process batches - Handle multiple images with progress tracking Test Results Metric Value Images Processed 3/3 Failed 0 Total Time 40.82s Avg Time/Image ~13.6s Sample Outputs 🐕 family_photo_03.jpg Description: "A tan-