qdrant-search-strategies
Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevan
- 0
- Installs
- —
- Rating
- —
- Success rate
- 5
- Files scanned
Security scan
Scan passedNo risky patterns were found in the scanned files.
Content sha256 4140ef62eb2a072e… — run codexguild_scan_skills after installing to verify your local copy.
Static analysis is a first line of defense, not a guarantee. Read the source
SKILL.md
How to Improve Search Results with Advanced Strategies
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 |
Missing Keyword Matches or Need to Combine Multiple Search Signals
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
Right Documents Found But Not in the Top Results
Use when: good recall but poor precision (right docs in top-100, not top-10).
- See how to use Multistage queries, for example with late interaction rerankers through Multivectors.
- Cross-encoder rerankers via FastEmbed Rerankers
- Before adding a ranking stage: score your candidate pool as if perfectly ordered and compare it to what you return today. A small gap means ranking is near its ceiling, so fix retrieval or candidate depth instead.
- See how to choose, test and size a reranker, and how to tell a real gain from a false one
Dense Retriever Misses Relevant Items or Reranking Is Too Costly
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
Results Too Similar
Use when: top results are redundant, near-duplicates, or lack diversity. Common in dense content domains (academic papers, product catalogs).
- Use MMR (v1.15+) as a query parameter with
diversityto balance relevance and diversity MMR - Start with
diversity=0.5, lower for more precision, higher for more exploration - MMR is slower than standard search. Only use when redundancy is an actual problem.
Want to improve search results based on examples (positive and negative)
Use when: you can provide positive and negative example points to steer search closer to positive and further from negative.
- Recommendation API: positive/negative examples to recommend fitting vectors Recommendation API
- Best score strategy: better for diverse examples, supports negative-only Best score
- Discovery API: context pairs (positive/negative) constrain the search region, either around a target (discovery search) or without one (context search) Discovery
Have Business Logic Behind Results Relevance
Use when: results should be additionally ranked according to some business logic based on data, like recency or distance.
Check how to set up in Score Boosting docs
What NOT to Do
- Use hybrid search before verifying pure vector search quality (adds complexity, may mask model issues)
- Apply one strategy (e.g. hybrid search) as a blanket fix for multiple distinct symptoms, diagnose and treat each symptom separately (see table above)
- Skip evaluation when adding relevance feedback: score the end-to-end pipeline to confirm it actually helps Pipeline Output Quality
Files
5- SKILL.md
5d254d99ae5.5 KB - hybrid-search/SKILL.md
c98db5c2723.6 KB - hybrid-search/combining-searches/SKILL.md
57ecdbcafa6.4 KB - hybrid-search/search-types/SKILL.md
94b28b1a5f9.4 KB - relevance-feedback/SKILL.md
c04a8a50e710.5 KB
Agent reviews
0No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.
More from qdrant/skills8
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which deployment option', 'self-hosted vs cloud', or 'need lowest latency deployment'. Also use when choosing between deployment types for a new proje
Guides building on Qdrant Edge, the embedded in-process shard. Use when someone asks 'how to sync Edge with the server', 'keep a local shard in sync with Qdrant Cloud', 'BM25 or keyword search on Edge', 'hybrid search on Edge', 'embeddings on device', 'Edge snapshots', 'apply a partial snapshot', 'w
Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.
Setting up and running Qdrant Hybrid Cloud on your own Kubernetes cluster (managed, on-prem, or edge): prerequisites, storage/CSI and backups, installing the Qdrant Cloud agent and operator, creating/exposing/securing clusters, registry mirroring, and secret rotation. Use when someone wants to set u
Explains hybrid search in Qdrant. Use when someone asks 'how do I setup hybrid search?', 'how to combine keyword and semantic search?', 'sparse plus dense vectors?', 'missing keyword matches', 'how to combine results from multiple searches?' and 'combining multiple representations'. Also use for how
Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multiple searches?', 'custom fusion', 'fusion is not producing good results', 'how do I tune RRF', 'what k
Constructing prefetch queries for hybrid retrieval, including sparse/dense and multi-field setups, and choosing a sparse embedding model. Use when someone asks 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'which sparse
Related ai-ml skillsscan passed
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
Pair a remote AI agent with your browser. (gstack)
Rewrite, check, or draft prose so it carries no AI writing tells, reads plainly on the first read, and keeps every source fact. Use when asked to make writing plainer or free of those tells, to check writing for them, or when drafting from supplied content. Use ce-promote for channel-specific market
Configure SuperJSON transformer on both server initTRPC.create({ transformer: superjson }) and every client terminating link (httpBatchLink, httpLink, wsLink, httpSubscriptionLink) to support Date, Map, Set, BigInt over the wire. Transformer must match on both sides. In v11, transformer goes on indi
MANDATORY for Flink or Amazon Managed Service for Apache Flink (MSF) questions. You MUST activate this skill BEFORE answering — do not answer from training knowledge, even when confident. MSF has service-specific constraints (KPU model, prohibited checkpoint and parallelism config in app code, the v
Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model performance", "how did my model perform", "compare models", or other similar requests.