--- title: "What Is Hybrid Search? Keyword and Vector Search Explained | Ceisium" description: "Learn how hybrid search combines keyword and vector results, why raw scores need fusion, where filters and reranking fit, and how to evaluate quality." canonical: https://ceisium.com/blog/what-is-hybrid-search/ --- > For the complete documentation and public content index, see [llms.txt](/llms.txt). This page is the Markdown alternative to the canonical HTML page. ![Keyword and vector result paths join to make one ordered hybrid search result list.](https://ceisium.com/blog/hybrid-search-cover-ceisium.webp) Keyword and vector result paths join to make one ordered hybrid search result list. ![Keyword and vector result paths join to make one ordered hybrid search result list.](https://ceisium.com/blog/hybrid-search-cover-ceisium.webp) Keyword and vector result paths join to make one ordered hybrid search result list. 1. [Home](https://ceisium.com/) 2. / 3. [Blog](https://ceisium.com/blog/) 4. / 5. What Is Hybrid Search? Published July 21, 2026 Updated August 9, 2026 # What Is Hybrid Search? Hybrid search combines keyword and vector retrieval. Learn how fusion, candidate windows, filters, and reranking turn two result lists into one. [![](https://ceisium.com/blog/share-icons/x.webp)](https://twitter.com/intent/tweet?text=What%20Is%20Hybrid%20Search%3F&url=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F)[![](https://ceisium.com/blog/share-icons/linkedin.webp) ](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F)[![](https://ceisium.com/blog/share-icons/hacker-news.webp)](https://news.ycombinator.com/submitlink?u=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F&t=What%20Is%20Hybrid%20Search%3F) [Search](https://ceisium.com/blog/?tag=Search) [Learn](https://ceisium.com/blog/?tag=Learn) Assume a developer searches fictional documentation with an invented error code: TEXT ``` How do I keep users logged in longer after ERR_AUTH_004? ``` The best page is **Configure session lifetime**. It solves the task, but it does not use the words in the query. Another page is **ERR\_AUTH\_004: Session expired**. It contains the exact code but only explains why the session ended. The query has two useful clues: - A task in ordinary language - An exact error code Lexical retrieval can preserve the code when text analysis keeps it intact. Vector retrieval can connect `logged in longer` with `session lifetime`. Hybrid search uses both types of evidence. ## What is hybrid search? Hybrid search combines ranked results from more than one retrieval method. Our example uses lexical retrieval and vector retrieval. Each method returns one ranked list. A fusion step then combines the lists into one candidate list. Lexical retrieval uses indexed terms. Vector retrieval compares numeric representations, called embeddings, of the query and content. The basic process is: TEXT ``` query ├─ lexical retrieval → ranked list └─ vector retrieval → ranked list ↓ fusion ↓ fused candidate list ``` Products can combine the results in different ways. We will explain one common process that joins two result lists. All hybrid designs use different evidence sources. They do not require one method to solve every query. Hybrid search gives more evidence to the ranker. It does not guarantee that the evidence is better. ## What lexical retrieval contributes Lexical retrieval starts with the exact error code. An analyzer converts page text into a token stream. A tokenizer creates tokens, and token filters can change them. The engine then stores the analyzer output as indexed terms. [Lucene analyzer documentation opens in a new tab](https://lucene.apache.org/core/10_2_0/core/org/apache/lucene/analysis/Analyzer.html) explains these stages. The analysis settings can convert text to lowercase or split punctuation. They can also preserve one technical identifier. An exact ID helps only when page analysis and query analysis produce compatible forms. Lexical rankers compare query terms with indexed terms. [BM25 ![](https://ceisium.com/blog/bm25-cover-ceisium-bottom-right-aligned.webp)Search / Jun 24, 2026 What is BM25? A Plain English Guide BM25 is a keyword search ranking function that scores documents using term frequency, term rarity, and document length. Learn how it works, where it helps, and how it differs from TF-IDF.](https://ceisium.com/blog/what-is-bm25/) is one common lexical ranking method. Its inverse document frequency can give more value to a rare error code. [Lucene BM25 documentation opens in a new tab](https://lucene.apache.org/core/10_3_0/core/org/apache/lucene/search/similarities/package-summary.html) describes this behavior. [TF-IDF ![](https://ceisium.com/blog/tf-idf-cover.webp)Search / Jul 1, 2026 TF-IDF: The Search Ranking Idea Behind BM25 TF-IDF is a classic lexical ranking method that scores documents using repeated query words and rare query words. Learn how it works, where it helps, and how BM25 addresses some of its limits.](https://ceisium.com/blog/what-is-tf-idf/) uses a related term-ranking idea. The lexical list can look like this: Lexical rank Page Illustrative score 1 ERR\_AUTH\_004: Session expired 8.4 2 Rotate an API key 5.1 3 Authentication concepts 3.7 The first result preserves the exact code. The other pages share common authentication terms but do not solve the session task. **Configure session lifetime** can be absent from the first three results. The heading and query use different words. Lexical retrieval found the exact error code but did not find the task page. ## What vector retrieval contributes Vector retrieval starts with the task in ordinary language. An embedding model converts the query and passages into lists of numbers. These lists are embeddings. An embedding represents text as a point in a learned comparison space. The system finds related content by comparing these points. The [vector search guide ![](https://ceisium.com/blog/vector-search-cover.webp)Search / Jul 10, 2026 What Is Vector Search? Vector search finds related content by comparing embeddings. Learn how vectors, similarity, approximate nearest-neighbor search, and hybrid retrieval work together.](https://ceisium.com/blog/what-is-vector-search/) explains embeddings and similarity in more detail. The vector list can look like this: Vector rank Page Illustrative score 1 Configure session lifetime 0.78 2 Authentication concepts 0.71 3 ERR\_AUTH\_004: Session expired 0.65 The vector path finds the task page. It connects `keep users logged in longer` with `session lifetime`. Vector retrieval also finds the broad **Authentication concepts** page. This page is related but does not explain the setting. Vector similarity is not correctness. It does not prove that a page is useful, current, or permitted. Each list contains one useful page and one weak page. The lexical list favors the incomplete error page. The vector list includes a broad concepts page. ![A llama-head character joins lexical and vector result paths into one fused queue.](https://ceisium.com/blog/what-is-hybrid-search/two-paths-one-list.webp) The error page occurs in both lists. The session-lifetime page comes from the vector path. Fusion keeps both candidates. ![A llama-head character joins lexical and vector result paths into one fused queue.](https://ceisium.com/blog/what-is-hybrid-search/two-paths-one-list.webp) The error page occurs in both lists. The session-lifetime page comes from the vector path. Fusion keeps both candidates. ## Raw retrieval scores are not directly comparable The error page has a lexical score of `8.4`. The session-lifetime page has a vector score of `0.78`. Do not add these values without a defined calibration method. The scorers use different functions, ranges, and distributions. A lexical score of `8.4` is not automatically stronger than a vector score of `0.78`. The vector score does not mean 78 percent relevant. A retrieval score is usually comparable only within one scorer and one query. It is not a probability or confidence value. Different retrieval scores do not share one measurement unit. A retrieval score orders results for one scorer and query. It is not calibrated confidence. A hybrid system needs a defined fusion method. One simple method uses result positions instead of raw scores. ![A llama-head character converts different lexical and vector scores into rank positions.](https://ceisium.com/blog/what-is-hybrid-search/different-scores-one-order.webp) Lexical and vector scores use different scales. The system needs a defined fusion method to produce one order. ![A llama-head character converts different lexical and vector scores into rank positions.](https://ceisium.com/blog/what-is-hybrid-search/different-scores-one-order.webp) Lexical and vector scores use different scales. The system needs a defined fusion method to produce one order. ## Rank fusion combines positions Rank fusion uses the position of each document in each source list. A high position contributes more to the fused rank than a low position. A document can also receive contributions from both lists. A document can remain in the fused list even when only one retrieval method finds it. In our example: - **ERR\_AUTH\_004: Session expired** is first in the lexical list and third in the vector list. - **Authentication concepts** is third in the lexical list and second in the vector list. - **Configure session lifetime** occurs only in the vector list. - **Rotate an API key** occurs only in the lexical list. One rank-fusion result can be: 1. ERR\_AUTH\_004: Session expired 2. Authentication concepts 3. Configure session lifetime 4. Rotate an API key Fusion keeps the task page, but it does not put that page first. Appearances in two lists can outweigh one high position. Fusion combines ranks or scores. It does not determine which page correctly completes the user’s task. [Reciprocal Rank Fusion opens in a new tab](https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion) is one common method. High positions contribute more, and repeated appearances can strengthen a document. Some systems normalize source scores and apply weights. [OpenSearch normalization opens in a new tab](https://docs.opensearch.org/latest/search-plugins/search-pipelines/normalization-processor/) makes numeric ranges more comparable. Normalization makes score ranges more comparable, but it does not give the scores the same meaning. Min-max normalization also depends on the observed extremes. Outliers and candidate changes can therefore change the result. A weight controls the influence of one signal. It is not a measure of confidence, and no one weight works for all query sets. ## Candidate windows limit fusion Our examples use the first three results from each retrieval method. This limit is the **candidate window**. Fusion sees only the union of candidates inside both windows. Candidate windows define what fusion can see. Fusion cannot restore a document that both retrieval windows omit. If the session-lifetime page is fourth in both lists, fusion cannot include it. Score normalization cannot restore an absent document. A larger window gives more opportunities to keep the correct page. It can also increase retrieval, transfer, memory, and reranking work. The [Elasticsearch RRF reference opens in a new tab](https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion) describes this quality and performance tradeoff. First measure whether useful pages enter the candidate set. Then measure their final order. ## Filters, fusion, and reranking have different jobs Search products can put these stages in different positions. The stages still answer different questions. ### Filters define eligibility Authorization and tenant boundaries must restrict retrieval before exposure. Every retrieval path must fail closed. A private page must not become visible because one path omits an access rule. Other filters can use version, category, language, price, or date. Their exact placement depends on the system. Filtering defines permitted documents. Ranking puts permitted documents in order. Eligibility is a hard boundary. Ranking orders only the documents that pass it. A small ranking penalty is not a substitute for a required version filter. ### Fusion combines evidence Fusion combines the candidate lists. After this step, the search system already uses both retrieval methods. Hybrid search does not require another model or a generative language model. ### Reranking examines the shortlist A reranker is an optional later stage. It uses more computation on a smaller candidate set. For our query, a reranker can move **Configure session lifetime** above the error page. It can also move the broad concepts page lower. A reranker cannot restore a document outside both candidate windows. It can only reorder the supplied candidates. This table summarizes the jobs: Stage Question Filter Is this document permitted? Retrieval Did a retrieval method include this document? Fusion How must the lists combine? Reranking Which remaining candidate best answers the query? The stage definitions make diagnosis easier. If the correct page is absent, do not start with reranking. ## Common hybrid search designs The parallel two-list method is common. Hybrid search also includes other multi-retriever designs. ### Parallel retrieval and fusion The system runs lexical and vector retrieval for the same query. It then combines the two lists. The paths can run at the same time to reduce total response time. They still require a query embedding, two retrieval operations, and fusion. The system can also add reranking. ### Conditional retriever routing Some systems use one retrieval path first. They use a second path only when the first result set is weak or sparse. A request with one active path does not perform two-list fusion. It is outside the narrow definition that this article uses. Conditional routing still uses multiple retrieval methods across the system. It can reduce work for simple queries. The routing rule becomes another source of search errors. ### Candidate union and reranking The system can give the combined candidates directly to a reranker. A simple union can replace a scored fusion step. The reranker still depends on the candidate windows. A missing document stays missing. Each design has different quality, latency, and cost effects. Select a design that fits the query mix, filters, and quality target. ## When to use hybrid search Hybrid search is useful when queries contain exact and semantic clues. It also helps when different query groups need different retrieval methods. Do not add hybrid search when one method already meets the quality and latency targets. Use labeled tests to find lost exact terms or missed paraphrases. [BEIR opens in a new tab](https://openreview.net/pdf?id=wCu6T5xFjeJ) also shows that one retrieval method does not win on all datasets. ### Developer documentation A user can know an error code but describe the required fix with different words. Lexical retrieval protects the code. Vector retrieval protects the task description. ### Product search A shopper can combine a natural-language category with an exact model code. Lexical and vector retrieval can both help. Structured requirements such as size, price, or availability usually belong in fields and filters. ### Support search A user can describe a symptom and include a feature name. Hybrid retrieval can preserve the name and find related explanations. ### Site search A user can search for `keep users signed in` when the page uses `session lifetime`. Semantic evidence connects the phrases. Lexical evidence still protects product names and navigation terms. Use lexical and semantic evidence when real queries contain both exact terms and natural-language descriptions. ## When hybrid search can reduce quality More evidence can make the final order worse. ### Broad semantic noise Vector retrieval can add pages that share the topic but do not solve the task. **Authentication concepts** is one example. ### Strong but stale exact matches Lexical retrieval can rank an old page high because it contains an exact code. A version filter can be more important than another rank adjustment. ### Missing candidates Fusion and reranking cannot restore a page outside both candidate windows. ### Incorrect fusion settings One normalized score can dominate because of poor calibration. Rank-fusion settings can also give too much influence to one window or position. A setting that helps paraphrases can damage exact-identifier queries. ### Added latency and cost Hybrid search can add query embedding, another index lookup, larger windows, and reranking. Parallel paths overlap in time. Do not add their individual durations to estimate the complete request. Measure end-to-end latency. These failure modes require careful tests. A measured quality gain can still justify hybrid search. ## How to evaluate hybrid search Start with one practical question: Does **Configure session lifetime** appear in the first visible results within the required response time? Run the same labeled query set through these configurations: 1. Lexical retrieval only 2. Vector retrieval only 3. Hybrid retrieval 4. Hybrid retrieval with reranking, when applicable Keep the corpus, filters, labels, and test period equal. Use separate names for these limits: - **Candidate N:** The number of documents from retrieval - **Reranker input size:** The number of fused candidates for the reranker - **Evaluation k:** The number of final results that the user sees Group queries by evidence type: - Exact identifiers and names - Paraphrases - Queries with tasks and identifiers - Version-sensitive or filter-sensitive queries - Queries with no correct answer Then measure candidate quality and final ranking quality. ### Candidate quality Candidate Recall@N measures the fraction of labeled relevant documents in the first N candidates. Hit@N asks only whether at least one relevant candidate is present. A page at rank 80 cannot reach a reranker that receives only 20 candidates. ### Final ranking quality - Hit@k asks whether at least one relevant result occurs in the first k positions. - MRR uses the reciprocal position of the first relevant result. - nDCG@k supports graded relevance and gives less value to low positions. Select metrics that match the user experience. A search box with three visible results must not celebrate a useful page at rank 80. ### Latency and hard constraints Report P50 and P95 response time with the quality results. P50 is the median response time. P95 is the response time that 95 percent of measured requests do not exceed. State the test period, request population, cache state, and load conditions. Also test authorization, tenant, version, and language constraints. Relevance cannot replace access control or correctness. A useful comparison shows the quality gain from each added stage and its measured time cost. ## Frequently asked questions ### Is hybrid search the same as semantic search? No. Semantic search uses meaning as evidence. Vector retrieval is one common semantic method. Hybrid search combines several retrieval signals. A hybrid system can include semantic retrieval, but the terms are not equal. ### Does hybrid search require BM25? No. BM25 is a common lexical ranker, but a system can use another lexical method. The combination of evidence defines hybrid search. ### Does hybrid search require a large language model? No. Embedding models often use machine learning, but hybrid search does not require a generative model. Rank fusion can be deterministic. A reranker is optional and can use different scoring methods. ## Conclusion Hybrid search combines different retrieval evidence. Lexical retrieval preserves words, identifiers, and exact clues when text analysis keeps them intact. Vector retrieval connects related content with different wording. Fusion combines the candidate lists. Filters enforce eligibility, and an optional reranker examines the shortlist again. The additional path can also add noise, cost, and failure modes. Candidate windows can hide the correct page. An exact match can be the wrong task. A close vector can be broad or stale. The final test is practical. The correct page must rank near the top for labeled queries within the required P95 latency. [![](https://ceisium.com/blog/share-icons/x.webp)](https://twitter.com/intent/tweet?text=What%20Is%20Hybrid%20Search%3F&url=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F)[![](https://ceisium.com/blog/share-icons/linkedin.webp) ](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F)[![](https://ceisium.com/blog/share-icons/hacker-news.webp)](https://news.ycombinator.com/submitlink?u=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F&t=What%20Is%20Hybrid%20Search%3F) Copy image[](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F)[](https://twitter.com/intent/tweet?text=%E2%80%9CWhat%20Is%20Hybrid%20Search%3F%E2%80%9D&url=https%3A%2F%2Fceisium.com%2Fblog%2Fwhat-is-hybrid-search%2F) **Yuvraj** _Building Ceisium and working on growth @ SigNoz_ ceisium.com ## Next reads [ ![BM25 scores query terms using rarity, repetition, and document length signals.](https://ceisium.com/blog/bm25-cover-ceisium-bottom-right-aligned.webp) What is BM25? A Plain English Guide BM25 is a keyword search ranking function that scores documents using term frequency, term rarity, and document length. Learn how it works, where it helps, and how it differs from TF-IDF. ](https://ceisium.com/blog/what-is-bm25/)[ ![A query vector follows a highlighted path toward a nearby cluster of related content.](https://ceisium.com/blog/vector-search-cover.webp) What Is Vector Search? Vector search finds related content by comparing embeddings. Learn how vectors, similarity, approximate nearest-neighbor search, and hybrid retrieval work together. ](https://ceisium.com/blog/what-is-vector-search/)[ ![TF-IDF combines term frequency and inverse document frequency to rank matching documents.](https://ceisium.com/blog/tf-idf-cover.webp) TF-IDF: The Search Ranking Idea Behind BM25 TF-IDF is a classic lexical ranking method that scores documents using repeated query words and rare query words. Learn how it works, where it helps, and how BM25 addresses some of its limits. ](https://ceisium.com/blog/what-is-tf-idf/)