24 stories tagged embeddings, newest first.
395 points by ilreb | 42 comments
Google blog post announcing EmbeddingGemma 2, an open lightweight on-device model that embeds text, images, audio, and video into a unified space.
26 points by saikatsg | 5 comments
A JetBrains AI blog post presenting a developer diary and field notes on building a retrieval-augmented generation pipeline for semantic code search.
415 points by Bibabomas | 137 comments
GitHub repository for Semble, an open-source CPU-based code search tool and MCP server for AI coding agents combining static embeddings with BM25.
459 points by pmaze | 137 comments
A site showing thematic "trails" of linked excerpts across 100 non-fiction books, automatically discovered by Claude Code.
357 points by Xyra | 123 comments
Landing page for Exopriors Scry, a tool giving Claude arbitrary SQL and vector-algebra search over indexes of arXiv, Hacker News, LessWrong and other sources.
421 points by walterbell | 157 comments
ClickHouse documentation page describing a dataset of 28.74 million Hacker News postings with 384-dimension SentenceTransformers embeddings for vector search.
401 points by skadamat | 225 comments
Substack post discussing Meta Superintelligence Labs' first paper, REFRAG, a method for RAG that feeds compressed chunk embeddings directly to the LLM.
336 points by lawrenceyan | 119 comments
A blog post explaining how language models represent vast numbers of concepts in 12,000-dimensional embedding spaces using near-orthogonality and the Johnson-Lindenstrauss lemma.
402 points by eric-burel | 78 comments
A Hugging Face Space hosting a visual, intuitive guide explaining how embeddings work in large language models.
453 points by zdw | 377 comments
Blog post on ADD / XOR / ROL arguing LLMs should be viewed as mathematical functions mapping paths through embedding space rather than human-like agents.
441 points by jxmorris12 | 133 comments
An essay arguing that text embeddings are an underrated machine learning tool, especially for technical writing and documentation work.
387 points by willbryk | 129 comments
Launch HN post introducing Exa Websets, an embeddings-powered search engine that uses LLM agents to verify results and returns them as enrichable tables.
379 points by 7d7n | 88 comments
Eugene Yan's long-form survey of how industrial recommendation and search systems are using LLMs across model architecture, data generation, training paradigms, and unified frameworks.
396 points by stared | 76 comments
Blog post by Piotr Migdał arguing that cosine similarity on embeddings should be used with care and discussing its pitfalls and alternatives.
432 points by jascha_eng | 81 comments
Timescale blog post arguing that standalone vector databases are the wrong abstraction and embeddings should be managed like database indexes, promoting pgai Vectorizer.
322 points by arunsupe | 49 comments
GitHub repository for semantic-grep, a command-line tool that uses Word2Vec embeddings to grep for words with meanings similar to the query.
345 points by robg | 192 comments
Wilson Lin's blog post describing Hackerverse, which uses 40 million embeddings of Hacker News content to map topics and find which users know what.
358 points by Sirupsen | 63 comments
Launch blog post by turbopuffer's CEO explaining why they built a vector and full-text search engine on object storage to cut search infrastructure costs.
466 points by tjake | 133 comments
Foojay.io article by DataStax CTO Jonathan Ellis on building a vector index of all Wikipedia on a laptop using Java tools.
453 points by wilsonzlin | 139 comments
Wilson Lin's blog post on mapping and analyzing 40 million Hacker News posts and comments, shown as a topic map built from embeddings.
363 points by ubutler | 70 comments
Blog post presenting a semantic map of Australian laws, regulations and cases built from text embeddings of the Open Australian Legal Corpus, with analysis and code.
![Screenshot of tge-data-web.nyc3.digitaloceanspaces.com: Vector Databases: A Technical Primer [pdf]](https://hn.urlbox.com/shots/renders/2024/1/12/cbe02d07-693f-4205-a548-b14e53fbfdec.jpg)
484 points by jide_tracc | 99 comments
A PDF document providing a technical primer on vector databases, shown in a browser PDF viewer that had not yet rendered content.
598 points by simonw | 113 comments
Simon Willison's article, based on his PyBay 2023 talk, explaining what embeddings are and how to apply them to problems like related content and semantic search.
359 points by gk1 | 190 comments
Pinecone's explainer article on what vector databases are and how they store and search embeddings for AI applications.