Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →qdrant/qdrant-search-strategies
Guides Qdrant search strategy selection.
Passed 23 of 23 test cases with the skill, and 15 of 23 without it.
and 9 more in the full report
8 fixed15 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/11/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
To lower hosting costs, an organization plans to switch to a small, fast, and cheap embedding model for vector search in Qdrant. What two strategy options can compensate for the reduced quality of a weaker embedding model?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies reranking as a strategy to compensate for weaker embedding models. | Passed | Passed |
| Identifies relevance feedback as a strategy to compensate for weaker embedding models. | Missed | Passed |
The instructions your model reads when the skill loads.
These strategies complement basic vector search. Use them after confirming the embedding model is fitting the task and HNSW config is correct. If exact search returns bad results, verify the selection of the embedding model (retriever) first. If the user wants to use a weaker embedding model because it is small, fast, and cheap, use reranking or relevance feedback to improve search quality.
Each symptom may require a different strategy: diagnose and address them independently. A single project can have multiple symptoms at once, and fixing one (e.g. adding hybrid search for keyword misses) may not fix the others (e.g. redundant results may still need MMR; poor precision may still need reranking).
| Symptom | Strategy |
|---|---|
| Missing exact/keyword matches | Hybrid search |
| Right documents exist but rank low (good recall, poor precision) | Multistage queries / reranking |
| Dense retriever misses relevant items entirely, or reranking too costly | Relevance feedback |
| Results are redundant / near-duplicate | MMR |
| Need to steer with example points | Recommendation / Discovery API |
| Need business-logic-based ranking | Score boosting |
Use when: pure vector search misses keyword/domain term matches, or the use case benefits from combining searches on multiple representations (including languages and modalities) of the same item.
See how to use hybrid search
Use when: good recall but poor precision (right docs in top-100, not top-10).
Use when: dense retriever misses relevant items you know exist in the collection; relevant documents lie outside the initial ANN retrieval pool; reranking a large candidate pool is too slow or expensive; using a small/cheap embedding model but need quality close to a larger model; or want to improve top-1/3 precision without the full cost of reranking.
See Relevance Feedback in Qdrant
Use when: top results are redundant, near-duplicates, or lack diversity. Common in dense content domains (academic papers, product catalogs).
test cases passed, vs 15 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.