Retrieval
Metadata Filters
Filter vector search results by document metadata.
Metadata filters constrain retrieval before results are returned. Use them for tenant boundaries, product scopes, document status, and other application rules.
1. Store Metadata During Embedding
const embedded = await embedDocuments(embeddings, documents, {
id: (doc) => doc.id,
content: (doc) => doc.body,
metadata: (doc) => ({
tenantId: doc.tenantId,
product: doc.product,
rank: doc.rank,
}),
});Metadata values can be strings, numbers, booleans, or null.
2. Filter a Search
import { vectorFilter } from "@anvia/core";
const results = await index.search({
query: "billing limits",
topK: 5,
filter: vectorFilter.eq("tenantId", "acme"),
});3. Combine Filters
const filter = vectorFilter.and(
vectorFilter.eq("tenantId", "acme"),
vectorFilter.eq("product", "billing"),
);
const results = await index.search({
query: "invoice settings",
topK: 5,
filter,
});Use and(...) and or(...) to build larger filters.
4. Use Range Filters
const results = await index.search({
query: "priority support",
topK: 5,
filter: vectorFilter.gt("rank", 2),
});gt(...) and lt(...) compare numbers, strings, and booleans.
5. Apply Filters to Dynamic Context
const agent = new AgentBuilder("support", model)
.dynamicContext(index, {
topK: 3,
filter: vectorFilter.eq("tenantId", tenantId),
})
.build();Keep security-sensitive filters in application code. Do not ask the model to enforce tenant or permission boundaries.