Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.wazoo.dev/llms.txt

Use this file to discover all available pages before exploring further.

Before reasoning about facts, agents must find the correct starting point. Hybrid search disambiguates natural language queries, resolving them to the correct semantic entity (IRI) before executing symbolic logic. Standard vector search retrieves semantically similar text, but agents require factual precision. If an agent searches for “Ethan’s manager”, a pure vector query might return “Gregory’s manager” because their text embeddings are nearly identical in vector space.

​
Hybrid retrieval

Worlds fuses three complementary signals to guarantee retrieval accuracy. By layering keyword precision and structural graph filters on top of vector embeddings, hybrid search ensures the agent resolves the exact item it needs.
SignalTechniqueWhat it captures
SemanticVector embeddings (1536-dim)Conceptual meaning
KeywordFTS5 / BM25Exact term matches
Graph contextRDF relationship filtersStructural relationships

​
Reciprocal rank fusion

Results from each signal are merged using Reciprocal Rank Fusion (RRF), an algorithm that produces a single unified relevance ranking: score=∑d∈D160+rank(d)score = \sum_{d \in D} \frac{1}{60 + rank(d)} This ensures that a result ranked highly by multiple signals surfaces to the top, while noise from any single signal is suppressed. Use the worlds.search method to perform a hybrid retrieval across your world.
TypeScript
import { Worlds } from "@wazoo/worlds-sdk";

const worlds = new Worlds({
  apiKey: process.env.WORLDS_API_KEY,
});

// Search for an item using natural language
const results = await worlds.search("my-world-id", "Ethan's manager", {
  limit: 5,
  types: ["schema:Person"],
});

console.log("Search results:", results);