Get the latest tech news

A visual exploration of vector embeddings


For Pycon 2025, I created a poster exploring vector embedding models, which you can download at full-size . In this post, I'll translate ...

I found that spike in every single vector embedding generated from the model - short ones, long ones, English ones, Spanish ones, etc. However, once we start growing our vector database size, we typically need to use an Approximate Nearest Neighbors (ANN) algorithm to search the embedding space heuristically. AlgorithmPython packageExample database supportHNSWhnswlib PostgreSQL pgvector extension Azure AI Search Chromadb Weaviate DiskANNdiskannpyCosmos DBIVFFlatfaissPostgreSQL pgvector extensionFaissfaissNone, in-memory index only* When our database grows to include millions or even billions of vectors, we start to feel the effects of vector size.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of vector embeddings

vector embeddings

Photo of visual exploration

visual exploration

Related news:

News photo

Show HN: HNSW index for vector embeddings in approx 500 LOC

News photo

Cascading retrieval: Unifying dense and sparse vector embeddings with reranking