The focus on the top 10 in vector search is a product of wanting to prove value over keyword search. Keyword search is going to miss some conceptual matches. You can try to work around that with tokenization and complex queries with all variations but it's not easy. Vector search isn't all that new a concept. For example, the annoy library (https://github.com/spotify/annoy), an open source embeddings database. - Source: Hacker News / 10 months ago

If you want to go larger you could still use some simple setup in conjunction with faiss, annoy or hnsw. Source: 12 months ago

I then use annoy to compare them. Annoy can use different measures for distance, like cosine, euclidean and more. Source: about 1 year ago

Yes you can do this for equality predicates if your row groups are sorted . This blog post (that I didn't write) might add more color. You can't do this for any kind of text searching. If you need to do this with file based storage I'd recommend using a vector based text search and utilize a ANN index library like Annoy. Source: about 1 year ago

If you need large scale (1000+ dimension, millions+ source points, >1000 queries per second) and accept imperfect results / approximate nearest neighbors, then other people have already mentioned some of the best libraries (FAISS, Annoy). Source: about 1 year ago

Weaviate: An open-source, cloud-native vector database built for scalable and fast vector searches. It's particularly effective for semantic search applications, combining full-text search with vector search for AI-powered insights. - Source: dev.to / 4 months ago

Weaviate is an open-source vector search engine with out-of-the-box support for vectorization, classification, and semantic search. It is designed to make vector search accessible and scalable, supporting use cases such as semantic text search, automatic classification, and more. - Source: dev.to / 4 months ago

Congrats to them! What have your experiences with vector databases been? I've been using https://weaviate.io/ which works great, but just for little tech demos, so I'm not really sure how to compare one versus another or even what to look for really. - Source: Hacker News / 5 months ago

A RAG implementation's quality and performance highly depend on the similarity-based search of embeddings. The challenge arises from the fact that embeddings are usually high-dimensional vectors, and the knowledge base may have many documents. It's not surprising that the popularity of LLM catalyzed the development of specialized vector databases like Pinecone and Weaviate. However, SQL databases are also evolving... - Source: dev.to / 6 months ago

To find semantically similar texts we need to calculate the distance between vectors. While we have just a few short texts we can brute-force it: calculate the distance between our query and each text embedding one by one and see which one is the closest. When we deal with thousands or even millions of entries in our database, however, we need a more efficient way of comparing vectors. Just like for any other way... - Source: dev.to / 7 months ago