qwick23

It is true. Some of the projects are just riding the wave of hype. 18M for a Python wrapper around ClickHouse Db is insane.

Is it an answer to GitHub Co-Pilot?

Wouldn't it be better to partner with an existing managed cloud provider like Pinecone or Qdrant? Why Redis at all? :-0

Also my experience. And since Qdrant has now cloud service, it is the choice number one. Best of both worlds. Just missing the GCP support.

Yeah, if you don't need performance, then just take a simple ANN library. No need for a database at all. In terms of databases, Qdrant and Pinecone are the simplest I've tried so far. But Pinecone isn't open-source, not an option for on-prem. PGvector is too much imho, do not want to have all the other Sequel stuff if I just need an NN search.

What do you think about Weaviate or Qdrant? There is a nice benchmarks overview with all the major players https://qdrant.tech/benchmarks/

Sounds like viral marketing campaign in flavor of Midjourney

With Postgres, you can do almost everything, also a full-text search, but you still have Elasticsearch, Mejlisearch, etc when you need performance and advanced features. The multitool approach is suboptimal in most cases.

That is amazing! Would be awesome to have a client-side version of Qdrant https://github.com/qdrant/qdrant

tbh. Looks like a huge overengineered legacy project. What is the clue to having all these ANN indexes in place? Is it a kinda art collection? What is the sense when you can just have HNSW in memory, with quantization, or on disk, GPU accelerated, etc. There are already better alternatives like Qdrant, which is written in Rust and super performant https://github.com/qdrant/qdrant, or Weaviate with GraphQL interface https://github.com/weaviate/weaviate