patricktrainer/duckdb-embedding-search

Fast similarity search using DuckDB

34
/ 100
Emerging

This tool helps you quickly find text that is semantically similar to a given piece of text. You input a collection of text documents (like comments or articles) and then provide a specific query text. The system outputs a list of the most similar documents, ranked by how closely they match your query's meaning. This is ideal for anyone needing to analyze large text datasets, such as researchers, content strategists, or community managers.

146 stars. No commits in the last 6 months.

Use this if you need to rapidly discover semantically related documents within a large collection without relying on exact keyword matches.

Not ideal if your primary goal is exact keyword search, rule-based text filtering, or if you don't want to use OpenAI's embedding models.

semantic-search content-analysis text-similarity community-moderation information-retrieval
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

146

Forks

7

Language

Python

License

MIT

Last pushed

Oct 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/patricktrainer/duckdb-embedding-search"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.