Hacker News with Generative AI: Text Embeddings

Text Embeddings are All Alike (arxiv.org)
We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches.
Text Embeddings, Machine Learning, Artificial Intelligence
4 points by jxmorris12 3 days ago | 0 comments
Show HN: Model2vec-Rs – Fast Static Text Embeddings in Rust (github.com/MinishLab)
This crate provides a lightweight Rust implementation for loading and inference of Model2Vec static embedding models. For distillation and training, the Python Model2Vec package can be used.
Rust, Machine Learning, NLP, Text Embeddings
59 points by Tananon 5 days ago | 15 comments
Chrome's New Embedding Model: Smaller, Faster, Same Quality (dejan.ai)
Chrome’s latest update incorporates a new text embedding model that is 57% smaller (35.14MB vs 81.91MB) than its predecessor while maintaining virtually identical performance in semantic search tasks.
Chrome, Machine Learning, Search, Software Updates, Text Embeddings
40 points by kaycebasques 10 days ago | 11 comments
The best way to use text embeddings portably is with Parquet and Polars (minimaxir.com)
Text embeddings, particularly modern embeddings generated from large language models, are one of the most useful applications coming from the generative AI boom.
Text Embeddings, Generative AI, Data Science, Tools
247 points by minimaxir 88 days ago | 59 comments
Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models (arxiv.org)
Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less likely to be "over-compressed" in the embeddings.
Information Retrieval, Text Embeddings, Machine Learning
20 points by mfiguiere 246 days ago | 3 comments