Hybrid search
Hybrid search is an information-retrieval technique that combines multiple retrieval methods or relevance signals to find or rank relevant results.
Enterprise RAG
Hybrid search combines multiple retrieval strategies, typically semantic vector search and lexical keyword search, and merges or ranks their results.
- How it is used
- Retrieves RAG context by combining exact text matching with semantic vector matching.
- How deep it goes
- Implements document preparation, index configuration, dual queries, ranked results, and index synchronization; defers retrieval-model internals.
- Examples
- Demonstrates a “Dubious parenting advice” product query and page-by-page PDF indexing with text, embeddings, and metadata.
- What you can do after
- Apply it via Azure AI Search by embedding queries and submitting text and vector queries together.
AI Agents in Action, Second Edition
Hybrid search combines multiple retrieval methods, typically including vector-based and lexical or structured search, to improve information retrieval.
- How it is used
- Supplies retrieval-augmented agents with context that balances exact-term precision and meaning-based recall.
- How deep it goes
- Explains parallel retrieval and rank-based fusion, then contrasts service-managed fusion with agent-directed search tools.
- Examples
- Uses an error-code lookup and a movie-script agent with separate semantic and keyword tools.
- What you can do after
- Evaluate retrieval choices and use complementary search tools to gather grounded answer context.
Read how AI Agents in Action, Second Edition explains hybrid search →
AI-Powered Search
Hybrid keyword and vector search combines lexical term matching with vector-similarity retrieval or ranking.
- How it is used
- Combines lexical and vector retrieval results to improve search relevance.
- How deep it goes
- Explains integration options and implements reciprocal rank fusion, including its rank-based scoring and k trade-off.
- Examples
- Compares lexical, vector, and fused movie searches for “singin' in the rain” and “the hobbit.”
- What you can do after
- Build it from scratch with Python reciprocal rank fusion or apply it through a collection's hybrid_search interface.
LLM Evaluation and Alignment, The Foundational Ideas
Hybrid retrieval combines multiple retrieval signals, typically sparse lexical matching and dense vector similarity, to retrieve relevant information.
- How it is used
- Combines lexical and semantic signals to improve retrieval robustness in retrieval-augmented generation.
- How deep it goes
- Explains complementary failure modes, ranked-list fusion, and diagnostic tuning without specifying an RRF formula or implementation.
- Examples
- Contrasts product SKUs and error codes with queries and documents using different terminology.
- What you can do after
- Diagnose retrieval gaps and adjust fusion weighting using context recall and precision signals.
Read how LLM Evaluation and Alignment, The Foundational Ideas explains hybrid search →
Retrieval Augmented Generation, The Foundational Ideas
Hybrid search combines dense and sparse retrieval methods to improve the range and quality of retrieved results.
- How it is used
- Combines exact-term precision with semantic reach in retrieval for mixed enterprise queries.
- How deep it goes
- Explains retriever selection and rank fusion, while leaving detailed fusion implementation to a separate treatment.
- Examples
- Uses exact regulatory terms, part numbers, entity lookups, and a question-context taxonomy to show where retrieval paths differ.
- What you can do after
- Evaluate/understand it by selecting an initial retriever for the query mix and testing hybrid weights across question types.
Read how Retrieval Augmented Generation, The Foundational Ideas explains hybrid search →
Designing AI Systems
Hybrid retrieval combines multiple retrieval methods, such as semantic vector search and keyword search, into a unified result ranking.
- How it is used
- Supplies retrieved chunks to workflows that ground model responses, combining vector and keyword retrieval when either alone is insufficient.
- How deep it goes
- Works through the retrieval interface, PostgreSQL keyword indexing, rank fusion, candidate oversampling, and service orchestration.
- Examples
- Uses an error-code query and a laptop-return vocabulary mismatch to contrast keyword and semantic retrieval.
- What you can do after
- Build it from scratch using a vector-store interface, PostgreSQL full-text search, and rank fusion in a retrieval service.
Building Reliable AI Systems
A retrieval technique that combines multiple approaches to find relevant information.
- How it is used
- Combines retrieval methods to find relevant context for RAG applications and enterprise search.
- How deep it goes
- Works through candidate retrieval, deduplication, and cross-encoder reranking in an employee-policy retriever.
- Examples
- Uses employee-policy questions about resignation, adoption leave, and termination to illustrate retrieved and ranked documents.
- What you can do after
- Build it from scratch as a hybrid retriever combining BM25, E5 embeddings, and cross-encoder reranking.
Read how Building Reliable AI Systems explains hybrid search →
Domain-Specific Small Language Models
A retrieval method that combines keyword-based and vector-based search to improve retrieval quality.
- How it is used
- Improves retrieval of local document chunks for agentic RAG by combining keyword and semantic search.
- How deep it goes
- Shows retriever setup, weighted combination, and an agent tool; does not specify a ranking formula for the combined results.
- Examples
- Uses PDF text chunks, a local LanceDB table, and a CodeAgent that can choose between local and web search.
- What you can do after
- Apply it via LangChain’s EnsembleRetriever and a smolagents tool backed by BM25 and LanceDB.
Read how Domain-Specific Small Language Models explains hybrid search →
Generative AI in Action
Hybrid search combines multiple search methods, such as text-based, categorical, numerical, and vector-based retrieval, in one query.
- How it is used
- Uses hybrid retrieval to find relevant blog content for search and retrieval-augmented chat.
- How deep it goes
- Explains query construction and result handling in Redis, and describes Azure's result fusion without mathematical derivation.
- Examples
- Uses a Longhorn blog-post query and an end-to-end chat application over indexed blog chunks.
- What you can do after
- Apply hybrid search via Redis to retrieve similar posts and supply results to a chat prompt.
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.
- How it is used
- Narrows semantic retrieval to metadata-constrained candidates before supplying context to a RAG answer generator.
- 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 you can do after
- Operate/configure a Qdrant search function that applies an optional locality filter before retrieving semantic matches.
Read how Build an Advanced RAG Application (From Scratch) explains hybrid search →
Essential GraphRAG
Hybrid search is an information-retrieval technique that combines multiple retrieval methods, such as vector similarity search and full-text search.
- How it is used
- Improves RAG retrieval by combining precise keyword matching with broader semantic matching.
- How deep it goes
- Implements normalized score merging, deduplication, and top-k selection, but stops short of resolving limitations from unstructured data.
- Examples
- Demonstrates Neo4j Cypher queries and retrieved passages about Einstein’s upbringing, inventions, patents, and laboratory work.
- What you can do after
- Build it in Neo4j by querying vector and full-text indexes, combining normalized results, and returning top-k passages.
Natural Language Processing in Action, Second Edition
A hybrid search pipeline combines vector-similarity retrieval with full-text retrieval to search by both semantic and lexical signals.
- How it is used
- Combines semantic similarity and lexical retrieval to improve search over language and documents.
- How deep it goes
- Builds from term-frequency retrieval and full-text search toward embeddings and a scalable hybrid pipeline.
- Examples
- Uses keyword search, embedding-based semantic search, PostgreSQL, and pgvector as concrete implementation examples.
- What you can do after
- Operate/configure PostgreSQL with pgvector and full-text indexes for scalable hybrid retrieval.
Read how Natural Language Processing in Action, Second Edition explains hybrid search →
LLM Customization and Fine-Tuning
A retrieval approach that combines multiple methods, commonly lexical search and vector similarity search.
- How it is used
- Combines lexical and vector retrieval in RAG to improve matching across paraphrases and rare corpus terms.
- How deep it goes
- Defines weighted score combination, gives a starting split, and recommends corpus-specific tuning.
- Examples
- Uses product codes, part numbers, and error identifiers as rare terms that keyword search can retrieve.
- What you can do after
- Apply it by combining vector and BM25 scores, starting with a 0.6/0.4 split and tuning per corpus.
Read how LLM Customization and Fine-Tuning explains hybrid search →
Build an AI Agent (From Scratch)
Hybrid search combines multiple retrieval methods and integrates their scores to rank results.
- How it is used
- Combines retrieval methods to rank results for queries requiring both exact matching and semantic similarity.
- How deep it goes
- Explains score normalization and weighted averaging, but stops short of specifying an implementation or weight-selection procedure.
- Examples
- Uses get_user_by_id, error code 404, natural-language storage questions, sofa and couch, codebases, and extracted zip files.
- What you can do after
- Apply it by combining normalized keyword and vector scores into a weighted final ranking.
Read how Build an AI Agent (From Scratch) explains hybrid search →
Context Engineering
Hybrid retrieval combines keyword-based and semantic retrieval to find relevant information.
- How it is used
- Balances exact-term matching and semantic recall when retrieving external knowledge for RAG.
- How deep it goes
- Defines sparse and dense retrieval, describes their fusion with BM25, and explains rank fusion without detailing implementation code.
- Examples
- Pairs embedding search with BM25 and illustrates fusion through RRF rankings across lexical and vector results.
- What you can do after
- Configure hybrid RAG by pairing embedding search with BM25 and fusing ranked results with RRF.
Also covered in
- Architecting an Apache Iceberg Lakehouse
- Agent Design PatternsIn early access (MEAP)
- AI Recommender SystemsIn early access (MEAP)
- Build AI-Enhanced Web Apps
- Designing AI AgentsIn early access (MEAP)
What to know first
- similarity searchSimilarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- lexical searchLexical search retrieves or ranks items by matching query terms or other surface-text features against indexed content, often using sparse representations and statistical weighting.
- retrieval-augmented generationRetrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- vector databaseA vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
Related concepts
- lexical searchuses · Lexical search retrieves or ranks items by matching query terms or other surface-text features against indexed content, often using sparse representations and statistical weighting.
- similarity searchuses · Similarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- information retrievaluses · Information retrieval is the process of finding and selecting information relevant to a query or information need from a collection.
- reciprocal rank fusionuses · Reciprocal rank fusion is a rank-aggregation technique that combines ranked lists by summing reciprocal-rank contributions for each item across the lists.
- BM25uses · BM25 is a probabilistic information-retrieval ranking function that scores documents for a query using term frequency, inverse document frequency, and document-length normalization.
Questions about hybrid search
What is hybrid search?
Hybrid search is an information-retrieval technique that combines multiple retrieval methods or relevance signals to find or rank relevant results.
Which Manning books explain hybrid search?
Enterprise RAG, AI Agents in Action, Second Edition, AI-Powered Search, LLM Evaluation and Alignment, The Foundational Ideas, Retrieval Augmented Generation, The Foundational Ideas, Designing AI Systems, Building Reliable AI Systems, Domain-Specific Small Language Models and 7 more.
What should I know before learning hybrid search?
Manning books that teach hybrid search usually introduce similarity search, lexical search, retrieval-augmented generation and vector database first.
What is hybrid search also called?
Hybrid search is also called hybrid retrieval.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.














