liveBook · Manning

Hybrid search

As explained in Build an Advanced RAG Application (From Scratch)

Hybrid search combines multiple retrieval signals or modalities, such as lexical sparse-vector search and semantic dense-vector search.

Hybrid search combines metadata filtering with semantic vector retrieval. A constraint such as locality narrows the candidate set before similarity search, improving geographic relevance, search efficiency, and the context supplied to the LLM. section 6.2

Istanbul hotel retrieval

For “Amazing hotel close to everything,” applying the Istanbul filter surfaces properties such as White House Hotel Istanbul, Skalion Hotel & Spa, Hotel Amira Istanbul, and Tomtom Suites, with location-focused evidence and scores.

How Build an Advanced RAG Application (From Scratch) covers it

How deep it goes
Explains the filter-before-search workflow, implementation shape, efficiency benefits, and relevance trade-offs without detailing ranking fusion.
Examples
Demonstrates city-filtered Istanbul hotel retrieval using review embeddings, locality payloads, similarity scores, and cited recommendations.
What it assumes
Assumes embeddings, a vector collection, stored metadata payloads, and a basic RAG answer-generation pipeline.
What you can do after
Operate/configure a Qdrant search function that applies an optional locality filter before retrieving semantic matches.
How it connects
Connects metadata filtering, semantic search, embeddings, vector databases, and retrieval-augmented generation.

Also explained in

Compare how 15 books explain hybrid search →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build an Advanced RAG Application (From Scratch). The section links point to the parts of the book it draws on.