vector-search

Problem: It is pretty challenging to find resource material and valuable articles, videos and such, and we spend a lot of time searching and finding the appropriate resource for us.

Proposed solution: Faceted search can come a long way when looking for a quick way to find a solution designed for our needs. Ratings on the resource can help us select the best solution based on our search

Is there an existing issue for this?

• I have searched the existing issues

What would you like to be added?

Current chunk manager didn't accept ctx for timeout and tracing control.
such as:
Read(ctx, Context, filePath string) ([]byte, error)

Why is this needed?

No response

Anything else?

No response

It will be great help if we can provide an out of box example about how to use SPTAG in what kind of scenario.

//community contributors are all welcome to contribute on this as well.

... to make it easier to read Vespa documentation on an e-reader / offline

Vespa documentation is generated using Jekyll from .md and .html files, look into options for generating the artifact as part of site generation (there might be plugins we can use here)

I am finding a product which can replace Elasticsearch.

Crate:         tempdir
Version:       0.3.7
Warning:       unmaintained
Title:         `tempdir` crate has been deprecated; use `tempfile` instead
Date:          2018-02-13
ID:            RUSTSEC-2018-0017
URL:           https://rustsec.org/advisories/RUSTSEC-2018-0017
Dependency tree: 
tempdir 0.3.7
├── storage 0.2.0
│   └── qdrant 0.7.0
├── segment 0.3.1
│   ├── storage 0.2.0
│

使用的3.2.7版本，3台服务器(1个master、3个ps、3个router)，按天建表(如：db_20210601、db_20210602、db_20210603)，每张表的结构如下 ：
`{
"name": "space",
"partition_num": 3,
"replica_num": 1,
"engine": {
"name": "gamma",
"index_size": 100000,
"retrieval_type": "IVFPQ",
"retrieval_param": {
"ncentroids": 2048,
"nsubvector": 64,
"metric_type": "InnerProduct"
},
"id_type": "String"
},
"propertie