Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/vdaas/vald
Vald. A Highly Scalable Distributed Vector Search Engine
https://github.com/vdaas/vald
anng approximate-nearest-neighbor-search cloud cloud-native distributed-systems golang high-dimensional-data high-performance image-search image-search-engine kubernetes microservices nearest-neighbor-search ngt similarity-search vald vector vector-search-engine
Last synced: 14 days ago
JSON representation
Vald. A Highly Scalable Distributed Vector Search Engine
- Host: GitHub
- URL: https://github.com/vdaas/vald
- Owner: vdaas
- License: apache-2.0
- Created: 2019-07-07T06:42:22.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2024-05-01T01:45:48.000Z (6 months ago)
- Last Synced: 2024-05-01T13:51:04.249Z (6 months ago)
- Topics: anng, approximate-nearest-neighbor-search, cloud, cloud-native, distributed-systems, golang, high-dimensional-data, high-performance, image-search, image-search-engine, kubernetes, microservices, nearest-neighbor-search, ngt, similarity-search, vald, vector, vector-search-engine
- Language: Go
- Homepage: https://vald.vdaas.org
- Size: 71.5 MB
- Stars: 1,463
- Watchers: 18
- Forks: 71
- Open Issues: 15
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
- Support: docs/support/contacts.md
Awesome Lists containing this project
- Awesome-LLM-Productization - Vald - A Highly Scalable Distributed Vector Search Engine (Go based) (Models and Tools / Vector Store)
- awesome-vector-search - Vald - A Highly Scalable Distributed Vector Search Engine
- awesome-llmops - Vald - square) | (Search / Vector search)
- StarryDivineSky - vdaas/vald
README
[](https://opensource.org/licenses/Apache-2.0)
[](https://github.com/vdaas/vald/releases/latest)
[](https://landscape.cncf.io/?item=app-definition-and-development--database--vald)
[](https://pkg.go.dev/github.com/vdaas/vald)
[](https://www.codacy.com/app/i.can.feel.gravity/vald?utm_source=github.com&utm_medium=referral&utm_content=vdaas/vald&utm_campaign=Badge_Grade)
[](https://goreportcard.com/report/github.com/vdaas/vald)
[](https://depshield.github.io)
[](https://app.fossa.com/projects/custom%2B21465%2Fvald?ref=badge_small)
[](https://deepsource.io/gh/vdaas/vald/?ref=repository-badge)
[](https://deepsource.io/gh/vdaas/vald/?ref=repository-badge)
[](https://cla-assistant.io/vdaas/vald)
[](https://artifacthub.io/packages/chart/vald/vald)
[](https://join.slack.com/t/vald-community/shared_invite/zt-db2ky9o4-R_9p2sVp8xRwztVa8gfnPA)
[](https://twitter.com/vdaas_vald)
## What is Vald?
Vald is a highly scalable distributed fast approximate nearest neighbor (ANN) dense vector search engine.
Vald is designed and implemented based on Cloud-Native architecture.
Vald has automatic vector indexing and index backup, and horizontal scaling which made for searching from billions of feature vector data.
Vald is easy to use, feature-rich and highly customizable as you needed.
It uses the fastest ANN Algorithm [NGT](https://github.com/yahoojapan/NGT) to search neighbors.
(If you are interested in ANN benchmarks, please refer to [ann-benchmarks.com](https://ann-benchmarks.com/).)
For more information, please refer to [Official Web Site](https://vald.vdaas.org).
Vald can handle any object data, image, audio processing, video, text, binary, or etc., if converting to the vector, and be used for:
- Recognition
- Recommendation
- Detecting
- Grammar checker
- Real-time translator
- anything you want to do!
## Requirements
- Kubernetes 1.19~
- AVX2 instructions (required by Vald Agent NGT)
## Get Started
Go to [Get Started](https://vald.vdaas.org/docs/tutorial/get-started) page to try out Vald !
## Installation
### Using Helm
```shell
helm repo add vald https://vald.vdaas.org/charts
helm install vald-cluster vald/vald
```
If you use the default values.yaml, the `nightly` images will be installed.
### Using Helm-operator
Please refer to [vald-helm-operator](https://github.com/vdaas/vald/blob/main/charts/vald-helm-operator).
## Components
Component
Docker image
latest image
nightly image
Agent NGT
Agent Sidecar
Discoverer
Gateways
Index Manager
Helm Operator
Docker images tagging policy:
- `nightly` ... latest build of main branch
- `vX.X.X` ... released versions
- `latest` ... latest build of release versions
- `stable` ... latest long-term supported version
## Tools
- [SDK](https://vald.vdaas.org/docs/user-guides/sdks/): Official client libraries
- [Demo](https://github.com/vdaas/vald-demo): Demo repository using sample data
## Vald Users
## Contribution
Please read the [contribution guide](https://vald.vdaas.org/docs/contributing/contributing-guide).
Before your first commit to this repository, it is strongly recommended to run the commands below.
```shell
git clone https://github.com/vdaas/vald && cd vald
make init
```
## Contributors
[](#contributors)
Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):
Yusuke Kato
💻 🎨 🚧 📆
Rintaro Okamura
💻 📖 🚧 📦
Kosuke Morimoto
💻 💡 🔧 ⚠️
Kiichiro YUKAWA
📖 🚧 ⚠️ ✅
datelier
💻 🤔
Kevin Diu
📖 💡 ⚠️ ✅
Hiroto Funakoshi
📖 🔧 ⚠️ ✅
taisho
🎨 📖 💡
Pierre Grimaud
📖
Omer Katz
📖 ✅
Koichi Shiraishi
️️️️♿️
Siyuan Liu
️️️️♿️ 💡
David Calvert
📖
takuyaymd
🐛 💻 🚧
junsei-ando
📖
Yusuke Kadowaki
💻 ⚠️
aknishid
💻 🚧 📖
Hrichik Mazumder
📖
Shunya Morihira (森平 隼矢)
🔧 💻
miyamoto
💻 🔬
s-shiraki
⚠️
## LICENSE
Vald released under Apache 2.0 license, refer [LICENSE](https://github.com/vdaas/vald/blob/main/LICENSE) file.
[](https://app.fossa.com/projects/custom%2B21465%2Fvald?ref=badge_large)