{"full_name":"qdrant/qdrant","owner":"qdrant","name":"qdrant","shard":"1","url":"https://github.com/qdrant/qdrant","description":"Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/","homepage":"https://qdrant.tech","topics":["neural-network","search-engine","knn-algorithm","hnsw","vector-search","nearest-neighbor-search","image-search","embeddings-similarity","recommender-system","vector-search-engine","mlops","search-engines","neural-search","similarity-search","vector-database"],"tag_pages":["hnsw","image-search","mlops","nearest-neighbor-search","neural-network","neural-search","recommender-system","search-engine","similarity-search","vector-database","vector-search"],"language":"Rust","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/73504361?v=4","created_at":"2020-05-30T21:37:01Z","pushed_at":"2026-11-16T09:14:05Z","metrics":{"stars":35583,"forks":2818,"watchers":164,"issues":2150,"prs":8873,"releases":120,"issues_open":489,"issues_closed":1661,"prs_open":309,"prs_closed":1240,"prs_merged":7324,"discussions":332},"growth":{"day":{"stars":27,"forks":0,"base_day":"2026-11-15"},"week":{"stars":104,"forks":13,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[35479,35497,35515,35527,35527,35539,35556,35583],"forks":[2805,2806,2810,2814,2814,2814,2818,2818],"watchers":[163,163,163,163,163,163,163,164],"issues_open":[null,null,484,488,487,488,488,489],"prs_open":[null,null,302,304,309,307,308,309]},"boards":{},"same_owner":[],"issues":[{"number":3121,"title":"Timeout on collection deletion","comments":34,"created_at":"2023-12-01T11:07:00Z"},{"number":4655,"title":"Transport error on self hosted 3 node cluster","comments":24,"created_at":"2024-07-10T18:04:53Z"},{"number":3132,"title":"qdrant_client-1.6.9: \"Can't init WAL\" when creating simple collection","comments":23,"created_at":"2023-11-29T15:27:04Z"},{"number":1327,"title":"TTL","comments":23,"created_at":"2023-01-09T09:20:05Z"},{"number":6081,"title":"GPU problem","comments":21,"created_at":"2025-02-28T07:22:18Z"},{"number":3956,"title":"on_disk payload is not decreasing RAM on system ","comments":20,"created_at":"2024-04-02T06:19:26Z"},{"number":5774,"title":"Error when uploading large collection","comments":19,"created_at":"2025-01-10T20:29:15Z"},{"number":5327,"title":"Specify IDs for distance matrix API","comments":16,"created_at":"2024-10-28T21:36:18Z"}],"discussions":[{"number":11552,"title":"Chopper: a small open model that cuts only the needed sentences out of retrieved text","comments":0,"category":"Show and tell","created_at":"2026-11-15T09:06:24Z"},{"number":11335,"title":"Proposal: a rehearsal tool for vector-index migrations","comments":0,"category":"Ideas","created_at":"2026-10-29T15:17:21Z"},{"number":11334,"title":"Qdrant on your own box, from the release binary, in one OpenTofu-style config","comments":0,"category":"Show and tell","created_at":"2026-10-29T14:09:25Z"},{"number":11270,"title":"⚡ Powered by FastEmbed: PolyVector brings In-Engine Hybrid Search to Postgres (3.2x faster than Elasticsearch)","comments":0,"category":"Show and tell","created_at":"2026-10-20T15:20:23Z"},{"number":11179,"title":"Showcase: ATS Zero-Browser Gateway — Fast protocol scraper & delta data feeder for vector search","comments":0,"category":"Show and tell","created_at":"2026-10-15T20:49:40Z"},{"number":9940,"title":"Metadata lookup tail latency: measurements on arithmetic field addressing vs B-tree/LSM","comments":3,"category":"Ideas","created_at":"2026-07-22T17:32:26Z"},{"number":9936,"title":"Kdrant — an idiomatic, coroutine-first Kotlin client for Qdrant","comments":0,"category":"Show and tell","created_at":"2026-07-21T21:56:13Z"},{"number":9327,"title":"Built Agent Magnet — episodic memory layer using Qdrant","comments":1,"category":"Show and tell","created_at":"2026-06-05T08:50:11Z"}],"latest_release":{"name":"v1.20.1","tag":"v1.20.1","published_at":"2026-11-13T12:30:26Z","body":"  # Change log\r\n\r\n  ## Improvements\r\n\r\n  * https://github.com/qdrant/qdrant/milestone/56 - Build HNSW graphs of large segments faster with PiPNN\r\n  * https://github.com/qdrant/qdrant/milestone/59 - Make filters with several conditions much faster on cold on-disk payload indexes\r\n  * https://github.com/qdrant/qdrant/pull/10743 - Halve the number of reads in HNSW graph search on cold on-disk storage\r\n  * https://github.com/qdrant/qdrant/pull/11490 - Speed up batch searches that apply the same filter to several named vectors\r\n  * https://github.com/qdrant/qdrant/pull/11480 - Speed up stream records and resharding shard transfers by pipelining batches\r\n  * https://github.com/qdrant/qdrant/pull/11429 - Quantize Turbo8 and Turbo16 vectors about 2x faster\r\n  * https://github.com/qdrant/qdrant/pull/11479, https://github.com/qdrant/qdrant/pull/11482 - Estimate filter cardinality once per filtered read and facet request\r\n  * https://github.com/qdrant/qdrant/pull/11415 - Open segments with bool and null payload indexes faster\r\n  * https://github.com/qdrant/qdrant/pull/11418 - Reduce the per-upsert overhead of appendable segments\r\n  * https://github.com/qdrant/qdrant/pull/11329 - Use the nearest point in the `geo_distance` formula when a field holds several geo points\r\n  * https://github.com/qdrant/qdrant/pull/11394 - Propagate peer metadata through consensus faster after a leader change\r\n  * https://github.com/qdrant/qdrant/pull/11471 - Use Debian 13 as the base of GPU Docker images, same as the regular image\r\n\r\n  ## Bug Fixes\r\n\r\n  * https://github.com/qdrant/qdrant/pull/11343 - Fix HNSW index builds being up to 3x slower on hosts with many cores, a regression in v1.20.0\r\n  * https://github.com/qdrant/qdrant/pull/11461, https://github.com/qdrant/qdrant/pull/11018 - Fix slow collection reads and shard snapshots blocking cluster state updates\r\n  * https://github.com/qdrant/qdrant/pull/11400 - Fix a copy-on-write flush cycle that could flush moved points in the wrong order\r\n  * https://github.com/qdrant/qdrant/pull/11031 - Fix aliases created in single-node mode not resolving on peers that join the cluster later\r\n  * https://github.com/qdrant/qdrant/pull/11506 - Fix unnecessary Raft leader elections right after a local consensus stall\r\n  * https://github.com/qdrant/qdrant/pull/11453 - Fix updating a collection with unchanged optimizer config not triggering optimizers\r\n  * https://github.com/qdrant/qdrant/pull/10014 - Fix `optimizers_overwrite.max_optimization_threads` being ignored when the collection config sets it to 0\r\n  * https://github.com/qdrant/qdrant/pull/11370 - Fix group-by returning empty results when many points have unsupported group values\r\n  * https://github.com/qdrant/qdrant/pull/11350 - Fix the score threshold of recommend with the best score strategy for Euclid distance\r\n  * https://github.com/qdrant/qdrant/pull/11395 - Fix a panic in the Greek stemmer\r\n  * https://github.com/qdrant/qdrant/pull/11401 - Fix very long tokens stalling full-text indexing with stemming\r\n  * https://github.com/qdrant/qdrant/pull/9955 - Fix a panic on an empty multi-dense vector in internal query requests\r\n  * https://github.com/qdrant/qdrant/pull/11332 - Fix collection deletion on Windows\r\n  * https://github.com/qdrant/qdrant/pull/11340 - Fix the build on targets without jemalloc, such as FreeBSD on PowerPC\r\n\r\n  ## Security\r\n\r\n  * https://github.com/qdrant/qdrant/pull/11477 - Hide snapshot telemetry of collections a collection-scoped JWT has no access to\r\n","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}