tag
4 items · 3 projects · 1 feed item
A geospatial similarity engine that learns the structural fingerprint of a place from OpenStreetMap features and returns 'what other places are like this?' across multiple countries. Custom-trained vision-transformer embeddings, pgvector, MCP server, agent-driven map UI. Built end-to-end.
An AI-powered Slack bot that reads a data-collection-plan document on Confluence, cross-references it against the live event registry and metrics catalog, optionally analyses a GitHub PR alongside, and posts a structured pass/fail review back into the thread. Multi-agent workflow with Agno + ChromaDB vector search + deterministic result caching.
Co-founded a news-aggregation platform that uses GPT models to synthesise stories from multiple sources, removing single-source bias. Plus a RAG-based study chatbot for students preparing for India's public-service exams: embeddings pipeline, vector search, and a conversational interface.
Cosine top-K is doing the right math but the wrong job. Here is the gotcha, the fix (MMR), and a second fix on top of that (geographic deduplication) that production systems actually need.