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 hidden (Show)
Published by generall almost 2 years ago
Published by generall almost 2 years ago
exact
search parameter allows to force exact search of the vectors, even if ANN index is built. Useful for validating accuracy of the current HNSW configuration./cluster
status API. Prevents flood of error messages in case of other node failure in clusterv0.10.5
storage in single node deployment.v0.10.x
serviceThis release finalizes the feature-set of the first road-map of Qdrant. Further updates before v1.0
will be focused on maintainability and stability of the service. The next road-map will be published soon!
Thanks to @IvanPleshkov, @agourlay, and @e-ivkov for contributing into this release
Published by generall about 2 years ago
Published by generall about 2 years ago
Published by generall about 2 years ago
Published by generall about 2 years ago
Published by generall about 2 years ago
See: https://github.com/qdrant/qdrant/releases/tag/v0.10.0
Proposed update process:
v0.9.1
-> v0.10.0
v0.10.0
v0.10.1
v0.10.1
Version compatibility | client v0.9.x | client v0.10.0 | client v0.10.1 |
---|---|---|---|
qdrant v0.9.1 | + | - | - |
qdrant v0.10.0 | + | + | |
qdrant v0.10.1 | - | + | + |
Published by generall about 2 years ago
PUT /collections/{collection_name}/points
{
"points": [
{
"id": 1,
"vectors": {
"image": [0.9, 0.1, 0.1, 0.2],
"text": [0.4, 0.7, 0.1, 0.8, 0.1, 0.1, 0.9, 0.2]
}
}
]
}
POST /collections/{collection_name}/points/search/batch
{
"searches": [
{ "vector": [0.2, 0.1, 0.9, 0.7], "limit": 3 },
{ "vector": [0.5, 0.3, 0.2, 0.3], "limit": 3 }
]
}
x86_64
and aarch64
- allows natively run Qdrant on arm-based CPUs. Pushes price/performance ratio even further. - DockerHub
scroll
API performance for strict filters. In some cases up to 1000x speed improvement.There are a lot of fundamental changes in qdrant segment storage and API, but we did our best to make a transition process as smooth as possible. The v0.10 release be performed in 2 steps: on the first step we upgrade qdrant into transition version v0.10.0 which support both - old and new version of the interface. The second update v0.10.1
will remove deprecated fields from the API.
Proposed update process with minimal downtime:
v0.9.1
-> v0.10.0
v0.10.0
v0.10.1
v0.10.1
Version compatibility | client v0.9.x | client v0.10.0 | client v0.10.1 |
---|---|---|---|
qdrant v0.9.1 | + | - | - |
qdrant v0.10.0 | + | + | |
qdrant v0.10.1 | - | + | + |
Don't forget to make backups and test the process in development environment!
See API changes in client releases:
Next release will be primarily focused on the Replication Support.
Thanks to @IvanPleshkov, @agourlay, @e-ivkov, @joein and @monatis for contributing into this release
Published by generall about 2 years ago
max_request_size_mb
configurationconfig.optimizer_config.max_optimization_threads
is 0Published by generall about 2 years ago
indexed_vectors_count
field in the Collection info APIThe next major release will focus on finalizing the Roadmap and bringing frequently requested functionality into the Qdrant.
The next major release will be 0.10.0. After that, we will work on stabilizing the API and storage as preparation for a 1.0 LTS release.
Thanks @agourlay & @e-ivkov for contributing into this release!
Published by generall about 2 years ago
Published by generall about 2 years ago
https://github.com/qdrant/qdrant/pull/783 - Parallel segment loading - significantly improves service recovery time
Several distributed deployment stability improvements:
wait
flag during distributed callshttps://github.com/qdrant/qdrant/pull/821 - fix backward compatibility with storages created in 0.8.x
The main goal for v0.9.0 is a seamless cluster scaling - ability to add more nodes into the cluster and move shards between this nodes.
Thanks @agourlay, @e-ivkov, and @IvanPleshkov for contributing into this release!
Published by generall over 2 years ago
Snapshots - https://github.com/qdrant/qdrant/pull/764 https://github.com/qdrant/qdrant/pull/772
Count API - https://github.com/qdrant/qdrant/pull/777
Thanks @agourlay @e-ivkov for contributing to the release
Published by generall over 2 years ago
Published by generall over 2 years ago
Published by generall over 2 years ago
Published by generall over 2 years ago
Experimental support for distributed deployment - [docs] [issues]
Filtering by similarity score - https://github.com/qdrant/qdrant/issues/113
On-disk payload storage - https://github.com/qdrant/qdrant/issues/406
On-flight payload indexing - payload indexes are available without segment re-build
Faster payload index - https://github.com/qdrant/qdrant/pull/461
Better error reporting
Enable CORS headers for Swagger UI access - https://github.com/qdrant/qdrant/issues/610
HNSW Speed improvements (https://github.com/qdrant/qdrant/pull/508, https://github.com/qdrant/qdrant/pull/513)
Storage optimization
Better support for Int payload in gRPC - https://github.com/qdrant/qdrant/pull/564
Published by generall over 2 years ago
Qdrant now supports any JSON as payload - https://github.com/qdrant/qdrant/pull/306
Alias API in gRPC - Making up for a lost API https://github.com/qdrant/qdrant/pull/408
New filtering condition
Match
- https://github.com/qdrant/qdrant/pull/421
IsEmpty
filter - https://github.com/qdrant/qdrant/pull/423
Geo payload indexing - https://github.com/qdrant/qdrant/pull/366
Removed BLAS - https://github.com/qdrant/qdrant/pull/182
Use Filtering context instead of Condition Checker - https://github.com/qdrant/qdrant/pull/413
sled
removed - https://github.com/qdrant/qdrant/pull/402
HNSW Performance improvements
Published by generall over 2 years ago
recommend
endpoint can now return payload and vector - https://github.com/qdrant/qdrant/issues/353
Published by generall over 2 years ago