A cloud-native vector database, storage for next generation AI applications

anns cloud-native distributed embedding-database embedding-similarity embedding-store faiss golang hnsw image-search llm nearest-neighbor-search tensor-database vector-database vector-search vector-similarity vector-store

Go to file

jinhai 7d4f356972 Merge branch 'branch-0.4.0' into 'branch-0.4.0' MS-436 Delete vectors failed if index created with index_type: IVF_FLAT/IVF_SQ8 See merge request megasearch/milvus!456 Former-commit-id: 75ec88eedc5f7569579d2885811ab79a9e8e0dff		2019-08-30 16:51:44 +08:00
ci	fix jenkinfile bug	2019-08-30 11:24:16 +08:00
cpp	MS-436 Delete vectors failed if index created with index_type: IVF_FLAT/IVF_SQ8	2019-08-30 16:39:26 +08:00
docs	…
install	…
pyengine	…
python	…
.dockerignore	…
.gitignore	…
CHANGELOGS.md	…
CONTRIBUTING.md	…
Dockerfile	…
INSTALL.md	…
LICENSE.md	…
README.md	…
environment.yaml	…
requirements.txt	…

README.md

Vecwise Engine Dev Guide

Install via Conda

Install Miniconda first
- bash vecwise_engine/install/miniconda.sh
Create environment
- conda env create -f vecwise_engine/environment.yaml
Test your installation

Install via Docker

Install nvidia-docker
docker build -t cuda9.0/VecEngine .
docker run -it cuda9.0/VecEngine bash

Create Database

Install MySQL
- sudo apt-get update
- sudo apt-get install mariadb-server
Create user and database:
- create user vecwise;
- create database vecdata;
- grant all privileges on vecdata.* to 'vecwise'@'%';
- flush privileges;
Create table:
- cd vecwise_engine/pyengine && python manager.py create_all