Learn the vocabulary of combining keyword-based and vector-based retrieval into one merged ranking.
0 / 5 completed
1 / 5
A teammate explains that a search system runs a query through both a keyword-based method like BM25 and a dense vector similarity search over embeddings, then merges the two ranked result lists into one combined ranking, so an exact keyword match and a semantically related but differently worded passage can both surface near the top. What retrieval technique is being described?
Hybrid search runs a query through both a keyword-based method, such as BM25, and a dense vector similarity search over embeddings, then merges the two ranked result lists, often with a reranking step, into one combined ranking, capturing both an exact keyword or product-code match that keyword search excels at and a semantically related but differently worded passage that vector search excels at. A DNS zone transfer is an unrelated concept about replicating name server records. This keyword-plus-vector-then-merge approach is exactly why hybrid search is favored in production RAG and search systems because keyword search and vector search each catch cases the other one misses.
2 / 5
During a design review, the team adopts hybrid search for a product search feature that must match both an exact SKU code typed verbatim and a vague, semantically related description like 'comfortable running shoes', specifically so neither type of query is left underserved by a single retrieval method. Which capability does this provide?
Hybrid search here provides combined coverage of exact keyword matches and semantically related matches, since the keyword method catches the literal SKU code and the vector method catches the semantically related description. Relying exclusively on dense vector similarity search, which can miss an exact SKU code match because embeddings emphasize semantic similarity over literal token overlap is the alternative this avoids. This behavior is exactly why hybrid search is favored in this kind of scenario.
3 / 5
In a code review, a dev notices a product search feature relies exclusively on dense vector similarity search, causing an exact SKU code query to return semantically similar but wrong products instead of the literal match, and the team has no keyword-based fallback merged into the ranking. What does this represent?
This is a missed hybrid search-opportunity, since hybrid search would merge in a keyword-based method that catches the literal exact match a pure vector search misses. A cache eviction policy is an unrelated concept about discarded cache entries. This pattern is exactly the kind of gap a reviewer flags once the tradeoffs are understood.
4 / 5
An incident report shows customers reported that searching for an exact product SKU code often failed to surface that exact product, because the search system relied exclusively on dense vector similarity, which favors semantic closeness over literal token matches. What practice would prevent this?
Adding a keyword-based method like BM25 alongside the existing vector search and merging both ranked lists into a hybrid search. Continuing the prior approach regardless of the risk it has already caused is exactly what led to the incident described here. This fix is the standard remedy once the root cause is confirmed.
5 / 5
During a PR review, a teammate asks why the team reaches for hybrid search instead of pure dense vector similarity search alone. What is the reasoning?
hybrid search trades the added complexity of running and merging two separate retrieval methods for coverage of both exact keyword matches and semantically related matches, while pure vector search is simpler to run but can miss an exact literal match that shares little token overlap with its embedding neighbors. This is exactly why hybrid search is favored when queries include both literal identifiers and vague natural-language descriptions, while pure dense vector similarity search alone remains acceptable when queries are consistently natural-language and literal keyword matching adds little value.
What does the "Hybrid Search Vocabulary" vocabulary exercise cover?
This exercise tests real IT vocabulary related to hybrid search vocabulary through 5 multiple-choice questions, each built from realistic workplace sentences rather than abstract definitions.
Is this vocabulary exercise free to use?
Yes. Every exercise on CoderSlingo, including this one, is completely free — no account, sign-up, or payment required.
How many questions does this exercise have?
This exercise has 5 questions. Each one shows a real-world sentence or scenario with multiple-choice options and an explanation once you answer.
What happens after I answer a question?
You'll see immediate feedback showing whether your answer was correct, along with a short explanation of why — then a button to move to the next question, and a full results screen at the end.
Can I retry the exercise if I get questions wrong?
Yes. Once you reach the results screen, click "Try again" to reset your answers and go through the exercise from the start as many times as you like.
Do I need to create an account to take this exercise?
No account is needed. Your answers are scored in your browser during the session — nothing is saved to a server, so you can jump straight in.
Is my progress saved if I leave the page?
No — progress within an exercise resets if you navigate away or reload. Each exercise is short enough to complete in a few minutes in one sitting.
Are these vocabulary exercises connected to other topics?
Yes — browse the full vocabulary exercises hub to find related modules covering adjacent IT topics and roles.
How is this different from reading a glossary or blog article?
Exercises like this one are active recall drills — you have to choose the correct term or phrasing yourself, which builds retention faster than passively reading a definition.
Where can I find more vocabulary exercises?
Browse the full Vocabulary exercises hub for hundreds of modules covering Agile, DevOps, security, databases, architecture, and more — organised by IT role and skill.