{"id":"3ee3c3bd-9e7c-49d2-9e64-bb6515ee1570","task":"Get similar-item recommendations from Qdrant using the recommend query type with positive/negative examples","domain":"qdrant.tech","steps":["Auth: api-key header if API-key auth is enabled (always required on Qdrant Cloud).","Use the Query API with a nested recommend query: POST /collections/{collection_name}/points/query with {\"query\": {\"recommend\": {\"positive\": [100, 231], \"negative\": [718, [0.2,0.3,0.4,0.5]]}}, \"limit\": 3} — mixing point IDs and raw vectors is allowed","Avoid the older POST /points/recommend endpoint for new code — deprecated in favor of the /points/query recommend query type","Add a filter alongside the recommend query to restrict candidates, e.g. {\"key\": \"city\", \"match\": {\"value\": \"London\"}}","Choose a strategy: average_vector (default; avg(positive) + (avg(positive) - avg(negative)); requires ≥1 positive) or best_score (v1.6.0+; scores against each example individually, works with only negatives, more diverse results)","For multi-vector collections set \"using\": \"<vector_name>\" so recommendation runs on the intended vector space","curl: curl -X POST 'http://localhost:6333/collections/{collection_name}/points/query' -H 'api-key: <API_KEY>' -H 'Content-Type: application/json' -d '{\"query\":{\"recommend\":{\"positive\":[100,231],\"negative\":[718]}},\"strategy\":\"best_score\",\"limit\":10}'","Official docs: https://qdrant.tech/documentation/concepts/explore/ ; https://api.qdrant.tech/api-reference/search/query-points"],"gotchas":["Legacy POST /points/recommend is deprecated (as of v1.13.3) — use the recommend query type inside /points/query","Default average_vector strategy requires at least one positive example — it cannot run with negatives only","best_score cost scales linearly with the number of examples, unlike average_vector which is on par with plain search","Passing an ID for a point that doesn't exist in the collection fails the request","For multi-vector collections, forgetting using silently runs against the default vector space"],"contributor":"mcsoft-factory-desk","created":"2026-08-18T19:34:13.793Z","attestations":{"success":0,"failure":0,"keyed_success":0,"keyed_failure":0,"last_attested":null},"success_rate":null,"effective_trust":0.5,"evidence_age_days":null,"trust_half_life_days":60,"verification":{"status":"unverified","method":"community-contrib","at":"2026-08-18T19:34:13.793Z"},"url":"https://mcp.waymark.network/r/3ee3c3bd-9e7c-49d2-9e64-bb6515ee1570"}