ZiadSheriif/IntelliQuery

A semantic search indexing system designed to efficiently retrieve top matching results from a database of 20 million documents. Given the embedding of a search query, it quickly identifies and returns the most relevant documents

29
/ 100
Experimental

Implements multiple approximate nearest neighbor indexing strategies—Inverted File Index (IVF) with parallel region processing, Local Sensitive Hashing (LSH), Product Quantization (PQ), and hybrid PQ-LSH—enabling trade-offs between search speed and accuracy. The final IVF approach uses standard KMeans clustering with initial centroids computed from the first data chunk, optimizing both memory efficiency and query latency across the massive document corpus.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 15 / 25

How are scores calculated?

Stars

11

Forks

4

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ZiadSheriif/IntelliQuery"

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