A new release of Qdrant vector search engine went live!
Version 0.11 brings the replication, making Qdrant fully scalable! There is a new administration API and exact search support, but also some more improvements.
0.11 is backwards compatible with 0.10.5 storage in single-node deployment!
There are still other options available :) For example, Qdrant vector search engine. It's written in Rust, and it's not about crypto. And currently they are hiring Rust developer. Check job openings in LinkedIn
A case study on how to simply create a search system with txtai, Qdrant and pretrained language models. The cool thing about the semantic search is that none of the words used in a query has to be used in any document in our dataset, as the model is already capable of capturing synonyms. This is a huge advantage over conventional search algorithms like BM25.
Because, solo traveling is a pretty good experience when you don't need to wait for smb if you want to travel (totally agree with it btw). And disaster is not about solo traveling.
The latest release of Qdrant 0.10.0 has introduced a lot of functionalities that simplify some common tasks. Those new possibilities come with some slightly modified interfaces of the client library. One of the recently introduced features is the possibility to query the collection with multiple vectors at once — a batch search mechanism.