feat: add support for Lindorm#718
Conversation
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: Poisky The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
Poisky
force-pushed
the
main
branch
2 times, most recently
from
19004b6 to
e83a6eb
Compare
|
/assign @XuanYang-cn |
|
@Poisky Please update this pr to the latest commit to pass the lint checks |
* upstream/main: Feat/endee version (zilliztech#715) fix: Use StrEnum instead of str, Enum (zilliztech#722)
@XuanYang-cn I have update pr to the latest commit, please check it |
Please run `make format` to auto re-format the code.
|
@XuanYang-cn I have run |
|
@Poisky What's the requirements to run lindorm? Is it opensearch-py ? Please update the readme.md and pyproject.toml accordingly. |
|
3 participants
Description
This PR introduces support for Lindorm, an Alibaba Cloud multi-model cloud-native database, as a new database engine in VectorDBBench. Lindorm's vector search capability provides high-performance and scalable vector indexing, making it suitable for large-scale AI and similarity search scenarios.
Supported Index Types：
（1）HNSW : High-performance graph-based indexing.
（2）IVFPQ : Optimized for memory efficiency and high-speed retrieval.
（3）IVFBQ : Designed for ultra-fast search with minimal storage footprint via binary quantization.