A lightweight distributed vector search engine based on Vald codebase. Vald is an awesome highly scalable distributed vector search engine works on Kubernetes. It has great features such as file-based backup, and metrics-based ordering of Agents. Also, Vald is highly configurable using YAML files. It works without Kubernetes, single binary (less than 30MB), easy to run (can be configured by command-line options), and consists of Agent and Server. alvd has almost the same features as Vald's gateway-lb + discoverer and agent-ngt. alvd depends on Vald codebase, the files came from Vald (such as internal, pkg/vald. They are downloaded when running make command.) are excluded from my license and ownership.
Features
- Works without Kubernetes
- Single binary (less than 30MB)
- Easy to run (can be configured by command-line options)
- Consists of Agent and Server
- alvd has almost same features that Vald's gateway-lb + discoverer and agent-ngt have
- alvd is highly inspired by k3s project
Categories
Vector Search EnginesLicense
Apache License V2.0Follow alvd
Other Useful Business Software
Host LLMs in Production With On-Demand GPUs
Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of alvd!