Just Brute Force Your Embeddings Instead of Using a Vector Database
I often see teams overcomplicating search by adopting heavy vector databases for small datasets. For around one million documents with low traffic, a simple Numpy brute-force approach on an M4 MacBook Pro delivers impressive speed without the operational overhead. You can achieve fast retrieval using basic dot products in Python until your scale truly demands a specialized database.
My O(n) algorithm can run circles around your O(log n) algorithm; why much of what you learned in school simply doesn't matter.
- emschwartz
This works especially well if your embedding model was trained to perform well with quantized embeddings. Binary + hamming distance = incredibly fast.
This post is from 2024 but I wrote about using this technique in https://emschwartz.me/binary-vector-embeddings-are-so-cool/
- Ellis_dev
The 1M-document numbers are a great reality check. I’d happily start with the NumPy version and only reach for a vector DB once it actually hurts.
- firasd
Yes! I'm working on an MCP server called Liveclip (not released yet) and we just store embeddings as text in SQLite.. it works over ~40MB of text, 1450 SCOTUS opinions
start=$(date +%s); curl -s -X POST "https://[urlredacted].workers.dev/mcp" -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"table_search_similar","arguments":{"key":"scotus_2010s","col":"M","query":"endangered fish"}}}'
2>&1 | grep '^data:' | sed 's/^data: //' | jq; end=$(date +%s); echo "elapsed: $((end-start))s"
{
"result": {
"content": [],
"structuredContent": {
"has_more": true,
"headers": {
"A": "author_name",
"B": "category",
"C": "per_curiam",
"D": "case_name",
"E": "date_filed",
"F": "federal_cite_one",
"G": "absolute_url",
"H": "year_filed",
"I": "scdb_id",
"J": "scdb_decision_direction",
"K": "scdb_votes_majority",
"L": "scdb_votes_minority",
"M": "text"
},
"offset": 0,
"ok": true,
"rows": [
{
"A": "Justice Thomas",
"B": "dissenting",
"C": "False",
"D": "Florida v. Georgia",
"E": "2018-06-27",
"F": "",
"G": "https://www.courtlistener.com/opinion/4511641/florida-v-geor...",
"H": "2018",
"I": "",
"J": "",
"K": "",
"L": "", […]