YYY
Y
YYY
YY
returnValues: true that's the only option to increase search accuracy. We decided against exposing a dedicated setting for accuracy.YreturnValues: true you should reliably get >90% accuracy.YYY
B
A
LYI
EIEII
III
K
V
B
D
--experimental-vectorize-bind-to-prod flag get stable, it fails 4/5 times resulting in 10000 Auth errorIID can only be part of a single namespace .."embedding_values = [32.4, 74.1, 3.2, ...];
//sampleVectors_1 : (Same embedding value, same namespace, only Vector-ID differ)
const sampleVectors_1: Array<VectorizeVector> = [
{ id: "1", values: embedding_values, namespace: "text", },
{ id: "2", values: embedding_values, namespace: "text", },
]
Y
G
Vectorize update: 
ZZ
SY
NV
Z
vitest-pool-workers to test my app in Github Action, and running into the following error with VectorizeIndex.query():Z
VECTOR_QUERY_ERROR: STATUS + 500 error other than this message and this thread
MR
V
A
Z
AZA
VectorizeIndex looks like the old types for me. For example, upsertPromise<VectorizeVectorMutation> which doesn't include the mutationIdZreturnValues: true returnValues: true --experimental-vectorize-bind-to-prodIDembedding_values = [32.4, 74.1, 3.2, ...];
//sampleVectors_1 : (Same embedding value, same namespace, only Vector-ID differ)
const sampleVectors_1: Array<VectorizeVector> = [
{ id: "1", values: embedding_values, namespace: "text", },
{ id: "2", values: embedding_values, namespace: "text", },
]vitest-pool-workersVectorizeIndex.query()workerd/io/worker.c++:2169: info: uncaught exception; source = Uncaught (in promise); stack = Error: VECTOR_QUERY_ERROR: Status + 500
at VectorizeIndexImpl._send (cloudflare-internal:vectorize-api:185:23)
at VectorizeIndexImpl.queryImplV2 (cloudflare-internal:vectorize-api:205:21)
at VectorizeIndexImpl.query (cloudflare-internal:vectorize-api:45:20)VECTOR_QUERY_ERROR: STATUS + 500VectorizeIndexPromise<VectorizeVectorMutation>mutationIdexport const search = base
.route({ method: 'POST', path: '/ai/vectors/search' })
.input(
z.object({
embeddings: z.array(z.number()),
topK: z.number().optional().default(10),
filter: z.record(z.string(), z.any()).optional(),
})
)
.output(vectorizeMatchesSchema)
.handler(async ({ input, context }) => {
const options: VectorizeQueryOptions = {
returnMetadata: true,
topK: input.topK,
};
if (input.filter) {
options.filter = input.filter;
}
const results = await context.env.VECTORIZE.query(input.embeddings, options);
return vectorizeMatchesSchema.parse(results);
}); return await client.ai.vectors.search({
embeddings: embeddings.data[0] ?? [],
topK,
filter: {
userId: {
$eq: userId,
},
},
});
}