Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
(github.com/MinishLab)
442 points
Bibabomas
18 days ago
150 comments
2.
▲
Show HN: Model2vec – Lightning-fast Static Embeddings for RAG/Semantic Search
(github.com/MinishLab)
28 points
Pringled
2 years ago
4 comments
3.
▲
Show HN: Model2Vec: make sentence transformers 500x faster on CPU, 15x smaller
(github.com/MinishLab)
9 points
stephantul
2 years ago
2 comments
4.
▲
Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
(github.com/MinishLab)
8 points
stephantul
a month ago
discuss
5.
▲
Show HN: Semble – Fast code search for agents with near-transformer accuracy
(github.com/MinishLab)
7 points
stephantul
a month ago
discuss
6.
▲
Show HN: Model2Vec: make sentence transformers 500x faster on CPU, 15x smaller
(github.com/MinishLab)
6 points
stephantul
2 years ago
2 comments
7.
▲
Show HN: Hardware-Friendly Text Classification with Model2Vec
(github.com/MinishLab)
3 points
Pringled
a year ago
discuss
8.
▲
Show HN: Model2vec-Rs – Fast Static Text Embeddings in Rust
(github.com/MinishLab)
60 points
Tananon
a year ago
15 comments
9.
▲
Show HN: Vicinity – Fast, Lightweight Nearest Neighbors with Flexible Back Ends
(github.com/MinishLab)
57 points
Pringled
2 years ago
8 comments
10.
▲
Show HN: SemHash – Fast Semantic Text Deduplication for Cleaner Datasets
(github.com/MinishLab)
19 points
Pringled
a year ago
6 comments
11.
▲
Show HN: SemHash – Semantic Text Deduplication, Outlier Filtering and Sampling
(github.com/MinishLab)
7 points
Tananon
a year ago
discuss
12.
▲
Show HN: SemHash – Fast Semantic Text Deduplication for Cleaner Datasets
(github.com/MinishLab)
6 points
stephantul
a year ago
discuss
13.
▲
Model2Vec: Distill a Small Static Model from Any Sentence Transformers Model
(github.com/MinishLab)
5 points
dmezzetti
2 years ago
discuss