Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
APACHE-2.0 License
Bot releases are visible (Hide)
Full change log: https://github.com/qdrant/qdrant-web-ui/releases/tag/v0.1.26
Published by timvisee 5 months ago
Published by generall 6 months ago
snapshot
shard transfer with API Key Auth.Published by timvisee 6 months ago
indexed_only
reliability on proxy shardsvectors_count
from collection info because it is unreliable. Check usage of this field before upgrading
wait=true
during shard transfersThanks to @abhishek818 @RPallas92 @tellet-q @xzfc @ffuugoo @IvanPleshkov @agourlay @coszio @generall @timvisee for their contributions!
Published by timvisee 7 months ago
Published by timvisee 7 months ago
Published by generall 7 months ago
max_optimization_threads
on the collection params update/readyz
check reliable on horizontal scalingPublished by generall 8 months ago
Published by timvisee 8 months ago
set_payload
API, adds ability to modify nested fieldsdiscover
endpoint statistics in the metricsThanks to @AlexandruCihodaru @Florents-Tselai @Shylock-Hg @amietn @ding-young @Okabe-Rintarou-0 @JojiiOfficial @mrbusche @gabrieldemian @2k4sm @Anush008 @TuanaCelik @kwkr @neo773 @Dhanus3133 @KShivendu @joein @xzfc @ffuugoo @IvanPleshkov @agourlay @coszio @generall @timvisee for their contributions!
Published by timvisee 9 months ago
Published by timvisee 10 months ago
Published by timvisee 10 months ago
/readyz
reporting error for Kubernetes if not enough other nodes are available, preventing full cluster startsPublished by timvisee 10 months ago
/readyz
reporting error if other nodes are still on 1.16, preventing cluster upgradesPublished by timvisee 11 months ago
with_payloads
more efficientlyindexed_only
more lenient/readyz
health check, only mark as ready when started node has caught upbest_score
formula with just negative examplesNO_COLOR
not having an effect on output logsThanks to @kaancfidan @keremnc @ava57r @Apmats @julianbraha @golangboy @ilkecan @ologbonowiwi @russcam @dzhao @joein @ffuugoo @IvanPleshkov @agourlay @coszio @timvisee for their contributions!
Published by generall about 1 year ago
Published by timvisee about 1 year ago
sentence-transformers/all-MiniLM-L6-v2
, intfloat/multilingual-e5-large
BAAI/bge-small-en
, BAAI/bge-base-en
Thanks to @kwkr @etolbakov @smark-d @dzhao @zzzz-vincent @jsoref @ffuugoo @IvanPleshkov @agourlay @coszio @timvisee for their contributions!
Published by timvisee about 1 year ago
Published by timvisee about 1 year ago
indexed_only
parameter to skip unindexed segments speeding up searchOur Python client (qdrant-client
) now integrates with our FastEmbed package - a lightweight, fast, Python library built for retrieval embedding generation.
That allows to seamlessly add and search documents in Qdrant, avoiding manual encoding and configuration of the collections.
Read more: https://github.com/qdrant/qdrant-client/releases/tag/v1.5.0
Thanks to @DengYiping @camdencheek @zpp12354321 @dzhao @zzzz-vincent @ffuugoo @IvanPleshkov @agourlay @coszio @timvisee for their contributions!
Published by generall about 1 year ago
Published by generall about 1 year ago
multilingual
tokenizer for non-latin alphabets, optionally supporting CJKThanks to @yarikoptic @hi-rustin @zzzz-vincent @zarkone @ffuugoo @IvanPleshkov @agourlay @coszio @timvisee for their contributions!