Cai Yudong

Clean IVF_FLAT_NM compatible codes

6

issue: #30

[Enhancement]: Rename FLOAT16_VECTOR and BFLOAT16_VECTOR

2

### Is there an existing issue for this? - [x] I have searched the existing issues ### What would you like to be added? Rename FLOAT16_VECTOR to Float16Vector, and BFLOAT16_VECTOR...

[Enhancement]: optimize iterator handle in search request

1

### Is there an existing issue for this? - [x] I have searched the existing issues ### What would you like to be added? In prepare.py::search_requests_with_expr()  all above params...

[Question] Why #1346 only brings the patch version change ?

2

PR #1346 adds the parameter “milvus::OpContext*” to every public interface, which is a breaking change. Per semantic versioning, this requires bumping knowhere’s major version. Why it increments only knowhere's patch...

"--refine-type" and "--refine-k" should be required only when "--refine" is set to True

1

When "--refine" is set to False, user is still required to set the params "--refine-type" and "--refine-k", it's unreasonable. "--refine-type" and "--refine-k" should be required only when "--refine" is set...

vectordbbench should detect the index mis-match

1

Reproduce steps: 1. create HNSW-SQ index with following command: ``` vectordbbench milvushnswsq --uri "http://10.220.56.72:19530" --case-type Performance1024D10M --drop-old --m 16 --ef-construction 128 --ef-search 100 --refine false --refine-type fp32 --refine-k 100 --sq-type...

Package dependency missing

2

Miss some package dependency for client "milvus" and "pgvector" Reproduce steps: 1. conda create -n tmp python=3.11 2. conda activate tmp 3. pip install vectordb-bench 4. run command "vectordbbench milvushnsw...

Cannot run vectordb-bench in offline env

6

Meet some issues when run vectordb-bench in offline env. Reproduce steps: 1. download cohere_medium_1m dataset 2. run milvus standalone 3. install vectordb-bench official pip package ``` pip install vectordb-bench pip...

1. download "bioasq_medium_1m" and "bioasq_large_10m" dataset from "s3://assets.zilliz.com/benchmark" 2. save above dataset to local dir, and treat them as customized dataset 3. do test with following command  4. vectordb-bench...