Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

场景使用vearch的ivfpq的索引模式进行相似度阈值为0.5的计算和直接在内存进行暴力比对返回的结果差距非常大 #702

Open
xueqizhang121 opened this issue Dec 12, 2022 · 4 comments

Comments

@xueqizhang121
Copy link

场景使用vearch的ivfpq的索引模式进行相似度阈值为0.5的计算和直接在内存进行暴力比对返回的结果差距非常大

@ljeagle
Copy link
Member

ljeagle commented Dec 21, 2022

麻烦发一下查询语法 @xueqizhang121

@xueqizhang121
Copy link
Author

{
"client_type": "random",
"is_brute_search": 0,
"query": {
"sum": [
{
"feature": [],
"field": "gaitVector",
"min_score": 0.1
},
{
"feature": [],
"field": "reidVector",
"min_score": 0.1
}
]
},
"retrieval_param": {
"nprobe": 2048,
"parallel_on_queries": 1
},
"size": 100,
"vector_value": true
}

@zcdb
Copy link
Member

zcdb commented Dec 21, 2022

使用的哪个版本?

@xueqizhang121
Copy link
Author

3.2.7的版本

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants