Find answers from the community

Updated 5 months ago

PostgresML

At a glance

The community member is interested in using postgresml to efficiently store and search vectors. The comments indicate that the llama index project does not currently have an integration with postgresml, but they are open to a pull request. The community members recommend considering vector stores like Weaviate, Pinecone, and Qdrant as potential alternatives, with Weaviate and Pinecone being the most powerful and having hosted offerings, while Qdrant is a good option for self-hosting. The community members provide a link to their current vector store integrations for reference.

Useful resources
i would like to use postgresml which allows me to store vectors and search it efficiently
L
C
4 comments
We don't actually have an integration using postgresML yet, but would be super open to a PR on this πŸ™

In a large majority of vector stores, llama index uses the vector store to store embeddings as well as the text! This allows indexes that use these vector stores to not have to be persisted to disk, since the vector store is persisting everything, which is actually super handy.

Our current integrations are over here: https://gpt-index.readthedocs.io/en/latest/how_to/integrations/vector_stores.html
Thanks! I will take a look at the page you linked, which one do you recommend that i use as sort of a template for the integration
I think weaviate and pinecone seem to the most poweful/useful, plus they have their own hosted offerings

If you don't care about hosted stuff and want to run it yourself, qdrant seems pretty good too
Add a reply
Sign up and join the conversation on Discord