Collections And Configuration

Agent creates a collection via PUT /collections/products with vectors={size:1536, distance:'Cosine'} to store OpenAI text-embedding-3-small vectors.

Set vectors.size to exactly the embedder's output dimension (1536) and distance to the metric the model was trained for (Cosine for normalized OpenAI embeddings). Both are fixed at create time and immutable — verify the embedder dimension before create rather than guessing.

A product needs both an image embedding and a text embedding per item. Agent configures vectors as a map {image:{size:512,distance:'Cosine'}, text:{size:768,distance:'Cosine'}}.

Define named vectors as a map at create time; every upsert must supply vectors as a dict keyed by the named-vector names; search/query must specify which named vector via the using parameter. Do not mix a default unnamed vector with named vectors in the same collection.

After a bulk upsert, GET /collections/{name} returns status='yellow' and optimizer_status indexing in progress. Agent's health check fails the deploy.

Treat yellow as 'optimizing/indexing in progress', not unhealthy — the collection still serves queries. Gate readiness on status returning to green (or poll optimizer status) rather than failing on yellow. Red/grey indicate real problems.