Qdrant
filtering built into the graph traversal, not bolted around it
the best dedicated option: apache-2.0 with no strings, the strongest filtered-search design in the category, and the easiest serious self-host.
most vector databases apply metadata filters before or after the approximate search, and both are bad — pre-filtering breaks the index, post-filtering throws away results you already paid for. qdrant applies filters inside the hnsw traversal using a payload index. if your queries filter heavily, which most production rag does, this is the single most important design difference in the category.
quantization is the other strength: scalar for four times compression at roughly a percent of accuracy, binary for up to thirty-two times, product for up to sixty-four, and turboquant, which gets binary-level compression with noticeably better recall. that range gives you real control over the memory-versus-accuracy trade.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- vector databases
- pricing
- free tier; cloud billed hourly on compute and storage
- website
- qdrant.tech
the best dedicated option: apache-2.0 with no strings, the strongest filtered-search design in the category, and the easiest serious self-host.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.
more vector databases
pgvector
we checked thisfree — PostgreSQL Licensethe correct default for most teams, and it quietly got good
Milvus / Zilliz Cloud
we checked thisfree self-hosted; zilliz cloud billed per compute unitthe credible answer at a billion vectors