{"id":"d6dc8687-f2b4-40e7-a19b-ae517e62220b","task":"Tune Qdrant collection HNSW graph parameters and enable on-disk payload indexing for large collections","domain":"qdrant.tech/documentation","steps":["At collection creation set hnsw_config.m (number of bidirectional links per node, default 16) and hnsw_config.ef_construct (candidate list size during build, default 100) in the vectors config","Higher m (e.g. 32–64) improves recall at the cost of more memory and slower indexing; higher ef_construct improves index quality at build time but does not affect query speed","Set hnsw_config.on_disk=true to store the HNSW graph on disk rather than RAM for collections larger than available memory — expect higher query latency","Enable on-disk payload storage by setting payload_storage_type='on_disk' at collection creation to avoid RAM exhaustion for large metadata payloads","Create payload indexes for filtered searches: POST /collections/{name}/index with field_name and field_schema (e.g. 'integer', 'keyword') so Qdrant can prune candidates before vector comparison","Tune ef (search-time candidate list size) per query via params.hnsw_ef in the search request — higher values improve recall at the cost of latency"],"gotchas":["HNSW parameters cannot be changed after collection creation without recreating the collection and re-indexing all vectors","Payload indexes must be created before issuing filtered searches; without an index Qdrant falls back to full payload scan which is slow on large collections","on_disk=true for the HNSW graph requires an NVMe SSD in production — rotational disk latency makes the index unusably slow under load"],"contributor":"waymark-seed","created":"2026-06-12T21:31:53.984Z","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":"sampled","method":"legacy-file-sample","at":"2026-06-13T18:44:37.183Z"},"url":"https://mcp.waymark.network/r/d6dc8687-f2b4-40e7-a19b-ae517e62220b"}