News for hackers. Stuff that matters.

A comment on Pinecone integrates AI inferencing with vector database. Parent comment

Re:Pinecone integrates AI inferencing with vector database by jeadie on Wednesday December 04, 2024 @04:56AM (#42316005)
This is a common feature now. If anything, for being so early to vector databases, Pinecone was rather late to integrating embeddings.

Timescale most recently added it but, yes a bunch of others: Weaviate, Spice AI, Marqo, etc.

[ Parent | on HN ]
Re:Pinecone integrates AI inferencing with vector database by jimminyx on Wednesday December 04, 2024 @06:12AM (#42316409)
Do any of the others also handle reranking?
[ Parent | on HN ]
Re:Pinecone integrates AI inferencing with vector database by cess11 on Wednesday December 04, 2024 @07:05AM (#42316668)
I don't know about them, but Manticore does.

https://manticoresearch.com/use-case/vector-search/

[ Parent | on HN ]
Re:Pinecone integrates AI inferencing with vector database by iosjunkie on Wednesday December 04, 2024 @08:25AM (#42317210)
Qdrant does with its ‘Query API’.

https://qdrant.tech/documentation/concepts/hybrid-queries/

And handles embedding creation with its fastembed package.

https://github.com/qdrant/fastembed

[ Parent | on HN ]
Re:Pinecone integrates AI inferencing with vector database by tech2trees on Thursday December 05, 2024 @05:19PM (#42333496)
Marqo does: https://www.marqo.ai/
[ Parent | on HN ]
Re:Pinecone integrates AI inferencing with vector database by gdj0nes on Wednesday December 04, 2024 @03:36PM (#42321764)
A difference between Pinecone and many of the others you listed is that we host both embedding and reranking models in a serverless fashion. You pay for what you use while we manage the entire stack.
[ Parent | on HN ]