Semantic Search on Your Own Documents: Embeddings, Vector DBs, and Practical Limits

Sat, 28 Jun 2025 10:00:00 +0000

Keyword search has a glaring weakness: it only finds documents containing the words you typed. Search your notes for “how to back up the database” and you’ll miss the page titled “nightly Postgres dump cron,” because it shares not a single word with your query. Semantic search fixes this by matching on meaning rather than spelling, and you can run the whole thing on your own hardware over your own documents. I did exactly that for a few thousand markdown notes, and it’s genuinely changed how I find things. It has also taught me, painfully, where the approach breaks.

Vector-Search - Tag - vo.rs

Semantic Search on Your Own Documents: Embeddings, Vector DBs, and Practical Limits