Vectorize Configuration

Create Index

npx wrangler vectorize create my-index --dimensions=768 --metric=cosine

⚠️ Dimensions and metric are immutable - cannot change after creation.

Worker Binding

// wrangler.jsonc
{
  "vectorize": [
    { "binding": "VECTORIZE", "index_name": "my-index" }
  ]
}

interface Env {
  VECTORIZE: Vectorize;
}

Metadata Indexes

Must create BEFORE inserting vectors - existing vectors not retroactively indexed.

wrangler vectorize create-metadata-index my-index --property-name=category --type=string
wrangler vectorize create-metadata-index my-index --property-name=price --type=number

Type	Use For
`string`	Categories, tags (first 64 bytes indexed)
`number`	Prices, timestamps
`boolean`	Flags

CLI Commands

# Index management
wrangler vectorize list
wrangler vectorize info <index-name>
wrangler vectorize delete <index-name>

# Vector operations
wrangler vectorize insert <index-name> --file=embeddings.ndjson
wrangler vectorize get <index-name> --ids=id1,id2
wrangler vectorize delete-by-ids <index-name> --ids=id1,id2

# Metadata indexes
wrangler vectorize list-metadata-index <index-name>
wrangler vectorize delete-metadata-index <index-name> --property-name=field

Bulk Upload (NDJSON)

{"id": "1", "values": [0.1, 0.2, ...], "metadata": {"category": "docs"}}
{"id": "2", "values": [0.4, 0.5, ...], "namespace": "tenant-abc"}

Limits: 5000 vectors per file, 100 MB max

Cardinality Best Practice

Bucket high-cardinality data:

// ❌ Millisecond timestamps
metadata: { timestamp: Date.now() }

// ✅ 5-minute buckets
metadata: { timestamp_bucket: Math.floor(Date.now() / 300000) * 300000 }

Production Checklist

Create index with correct dimensions
Create metadata indexes FIRST
Test bulk upload
Configure bindings
Deploy Worker
Verify queries

1.9 KiB Raw Blame History