Routes Qdrant search-quality complaints to guidance on diagnosis, hybrid search, reranking and relevance feedback.
- What it does
- This skill acts as a router for questions about poor Qdrant search relevance. It matches the user's reported symptom, such as low precision, low recall, missing expected results, or quality drops after quantization or a model change, to one of several guidance files and instructs the agent to read that file before answering. It also points to guidance on measuring retrieval quality, golden sets, recall@k, hybrid search with fusion or RRF, reranking, and relevance feedback. It produces routing decisions and answers drawn from the referenced guidance rather than from the routing page itself.
- When to use it
- Use it when someone reports bad, wrong, or irrelevant search results, missing expected matches, low precision or recall, or asks how to improve search quality. It also fits questions about embedding-model choice, hybrid keyword-plus-vector search, reranking, relevance feedback, and measuring retrieval quality with a golden set or recall@k.
- Requirements
- No scripts are shipped; it is instructions only. The agent needs file-reading tools (Read, Grep, Glob) and access to the referenced guidance files, which are not included in this skill folder.
Qdrant Search Quality
Route first, then answer. Match the user's symptom in the table, Read that file, and answer from it.
Do not answer from this page alone: it contains routing only, not the guidance. If two rows match, read both.
Most quality issues come from the embedding model or the data, not from Qdrant's configuration — splitting chunks mid-sentence alone can drop quality 30-40%.
Rule that out with exact search before tuning any Qdrant parameter:
Search API