Here's the Vectorize related stuff. @
Here's the Vectorize related stuff. @garvit would appreciate any insight here
4 Replies
Workaround I'm using atm is to not have wrangler auto-generate my
Env and define Env myself using the auto-generated types.Hi @Austin Williams. If you are working with a Vectorize V2 index (default), then you should be able to use the
Vectorize interface. As you pointed out, the VectorizeIndex is meant for Vectorize V1 indexes, which is now in a deprecated state.
Our docs include examples of the correct usage of the Vectorize interface: https://developers.cloudflare.com/vectorize/get-started/intro/.Cloudflare Docs
Introduction to Vectorize
Vectorize is Cloudflare's vector database. Vector databases allow you to use machine learning (ML) models to perform semantic search, recommendation, classification and anomaly detection tasks, as well as provide context to LLMs (Large Language Models).
We also have some guidance about the query operation: https://developers.cloudflare.com/vectorize/best-practices/query-vectors/.
And about metadata filtering specifically: https://developers.cloudflare.com/vectorize/reference/metadata-filtering/.
Cloudflare Docs
Query vectors
Querying an index, or vector search, enables you to search an index by providing an input vector and returning the nearest vectors based on the configured distance metric.
Cloudflare Docs
Metadata filtering
In addition to providing an input vector to your query, you can also filter by vector metadata associated with every vector. Query results will only include vectors that match the filter criteria, meaning that filter is applied first, and the topK results are taken from the filtered set.
Could you please review these and ensure that you haven't missed anything? Did you create metadata indexes before you upserted/inserted vectors?