WOLBΛRG

Semantic Search

How Wolbarg embeds queries and retrieves memories by cosine similarity.

What is it?

Semantic search is the default recall() path: embed the query, compare against stored memory embeddings, return the top-K closest records.

Why does it exist?

Agents ask questions in natural language. Exact string match fails when vocabulary drifts; vectors catch meaning.

How does it work?

  1. embedding.embed(query) produces a query vector
  2. Storage runs nearest-neighbor search (sqlite-vec / pgvector or in-process cosine)
  3. Optional filters (agent, metadata, archived) shrink the candidate set
  4. Results are ranked by similarity and trimmed to topK
const results = await ctx.recall({
  query: "How do recurring invoices work?",
  topK: 5,
  threshold: 0.3,
  filter: { agent: "research" },
});

When should it be used?

Always. Semantic search is the baseline. Add Hybrid Search when exact tokens matter, Rerankers when precision matters, and Metadata Filtering to scope corpora.

Performance notes

  • Latency is dominated by embedding network calls + vector scan size
  • Keep threshold above 0 for noisy corpora
  • Prefer metadata filters before raising topK

PostgreSQL Backend

Shared PostgreSQL storage with connection pooling, JSONB metadata, and optional pgvector.

Hybrid Search

Combine semantic vectors with BM25 keyword scores for more robust recall.

On this page

What is it?Why does it exist?How does it work?When should it be used?Performance notesRelated pages