# Memector

Memector is a meme-template search built by Nicholas Hopper that fuses up to five ranking channels with Reciprocal Rank Fusion in pgvector.

- **Type:** Personal project
- **Period:** 2026 to present
- **Updated:** November 17, 2026

## What Memector does and how it is built

- Searches 1,859 templates by fusing CLIP text-to-image, MiniLM text, Postgres keyword search and two sketch channels with Reciprocal Rank Fusion.
- Measured recall@1 of 94% and recall@5 of 100% on 50 vague queries that do not contain the template's name, with median latency around 100 ms.
- Raised candidate depth per channel from 80 to 150 after finding that a result one place past a channel's cutoff scored zero there, which moved recall@5 from 98% to 100%.

## Skills used on Memector

- [pgvector](https://nicholashopper.com/skills/pgvector.md)
- [Reciprocal Rank Fusion](https://nicholashopper.com/skills/reciprocal-rank-fusion.md)
- [FastAPI](https://nicholashopper.com/skills/fastapi.md)
- [LLM evaluation](https://nicholashopper.com/skills/evals.md)

---

Canonical page: https://nicholashopper.com/projects/memector  
Last updated: 2026-11-17  
Index of all pages: https://nicholashopper.com/llms.txt
