VectorHub icon indicating copy to clipboard operation
VectorHub copied to clipboard

VectorHub is a free, open-source learning website for people (software developers to senior ML architects) interested in adding vector retrieval to their ML stack.

Results 24 VectorHub issues
Sort by recently updated
recently updated
newest added

here are my changes to the article

stage: ready to publish

Please contact me via email at kobie (dot) crawford (at) databricks (dot) com if you need any references authorizing the publishing of this content.

This content explores semantic chunking in depth. I have shown how to implement semantic chunking from scratch using 3 methods: embedding similarity, hierarchical clustering, and LLMs. This article also includes...

stage: style review

notebook article on semantic search, news

stage: style review

in progress, will update then start review

stage: ready to publish

The limit for the vector type is 16,000 dimensions ([docs](https://github.com/pgvector/pgvector?tab=readme-ov-file#vector-type)). 2,000 is the limit for indexing it (you'll see an error if you try).

This pull request adds [Chromia's Vector DB](https://docs.chromia.com/intro/extensions/vector-db) to the vector database comparison table

This pull request adds ObjectBox database to the vector database comparison table.