LSH

Locality-sensitive hashing narrows the candidate set before scoring vectors. Use it when an in-memory store has enough documents that brute-force search is too slow.

1. Start With the Default

const store = InMemoryVectorStore.fromDocuments(embedded);

The default search strategy is brute force. It is simpler and a good starting point for tests, small datasets, and early prototypes.

2. Enable LSH

const store = InMemoryVectorStore.fromDocuments(embedded, {
  index: {
    type: "lsh",
    numTables: 4,
    numHyperplanes: 8,
    seed: 7,
  },
});

const index = store.index(embeddings);

LSH trades exact candidate selection for faster narrowing. Results are still scored after candidates are selected.

3. Search Normally

const results = await index.search({
  query: "password reset",
  topK: 3,
});

The search API is the same as the default index.

4. Tune Carefully

For production-scale retrieval, use a durable vector database. Anvia's in-memory LSH is best for local workflows and lightweight deployments.