lmorchard - Pebbling Club 🐧🪨

Introducing sqlite-lembed: A SQLite extension for generating text embeddings locally | Alex Garcia's Blog

alexgarcia.xyz
2024-10-02T18:50:39.681Z
sqlite search embedding ai ml

Notes

sqlite-lembed is a SQLite extension for generating text embeddings, meant to work alongside sqlite-vec. With a single embeddings model file provided in the .gguf format, you can generate embeddings using regular SQL functions, and store them directly inside your SQLite database. No extra server, process, or configuration needed!

Unfurl

{ "description": "Generate text embeddings in SQL with GGUF models!", "image": "https://blog-static.alxg.xyz/Screen%20Shot%202024-07-23%20at%2011.37.14%20PM.png", "publisher": "Alex Garcia's Blog", "title": "Introducing sqlite-lembed: A SQLite extension for generating text embeddings locally", "url": "https://alexgarcia.xyz/blog/2024/sqlite-lembed-init/index.html", "lang": "en", "failed": true, "failedAt": 1728192764806, "failedError": "TimeoutError: Promise timed out after 10000 milliseconds", "cached": true, "cachedAt": 1728192764644, "expires": 1728363545730, "status": 200, "bodyLength": 32669, "duration": 5146 }
KNN queries | sqlite-vec

alexgarcia.xyz
2024-10-02T18:43:43.454Z
sqlite search ml ai embedding

Notes

The most common use-case for vectors in databases is for K-nearest-neighbors (KNN) queries. You'll have a table of vectors, and you'll want to find the K closest

Unfurl

{ "date": "2024-10-02T17:24:49.000Z", "description": "A vector search SQLite extension that runs anywhere!", "image": "https://alexgarcia.xyz/sqlite-vec/mozilla.svg", "publisher": "sqlite-vec", "title": "KNN queries | sqlite-vec", "url": "https://alexgarcia.xyz/sqlite-vec/features/knn.html", "lang": "en", "failed": true, "failedAt": 1728192764806, "failedError": "TimeoutError: Promise timed out after 10000 milliseconds", "cached": true, "cachedAt": 1728192764645, "expires": 1728363545730, "status": 200, "bodyLength": 61579, "duration": 4868 }

0 - 50 of 2 items

10 25 50 100 250