weave-stack

Deploy and manage RAG infrastructure stacks with weave-cli across local and cloud runtimes.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/Maximilien-ai/weave-cli-skills --skill weave-stack
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: weave-stack
Source: https://github.com/Maximilien-ai/weave-cli-skills/tree/main/skills/weave-stack
Command: npx skills add https://github.com/Maximilien-ai/weave-cli-skills --skill weave-stack

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deploy and operate complete RAG infrastructure stacks to provision, manage, and monitor end-to-end data pipelines, vector databases, and dashboards with a single, cohesive workflow.

Core Features & Use Cases

  • Stack initialization: generate weave-stack.yaml and configure runtime, vector DB, and ingestion settings.
  • Deployment & operations: deploy to local or cloud runtimes (Kind, Minikube, EKS, GKE), monitor health, and perform day-2 ops (backup, scaling, security patches).
  • Dashboard and observability: manage the weave dashboard UI for centralized control and monitoring.
  • Use Case: A data team needs a production-ready RAG stack with Milvus for vector storage, MinIO for object storage, and a unified dashboard, which this skill provides from setup to ongoing maintenance.

Quick Start

Initialize weave-stack.yaml, configure resources, and deploy the complete RAG infrastructure with weave stack up.

Frequently Asked Questions about weave-stack

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy a complete RAG infrastructure stack to Kubernetes?

You can deploy a RAG stack to local or cloud Kubernetes runtimes including Kind, Minikube, EKS, and GKE. The skill manages the infrastructure lifecycle, allowing you to deploy and monitor pipelines across these environments.

What is the best way to manage day-2 operations for a RAG stack?

Day-2 operations for a RAG stack are managed through built-in lifecycle commands that handle health monitoring, backups, scaling, and security patches, ensuring production-grade reliability after the initial deployment.

Can I use Milvus for vector storage when deploying a production RAG stack?

Yes, Milvus is supported for vector storage in production RAG stacks. The skill configures Milvus alongside object storage and a unified dashboard to manage the complete pipeline.

Does this RAG stack deployment tool support centralized monitoring dashboards?

Yes, the RAG stack deployment includes a centralized dashboard UI for observability. This dashboard provides unified control and monitoring capabilities for all components within the deployed infrastructure.

How do I validate a RAG stack configuration before deploying to cloud runtimes?

You validate a RAG stack configuration using a dedicated validate command that checks your weave-stack.yaml file. This ensures your runtime, vector DB, and ingestion settings are correctly defined before executing the deployment.

What do I need to initialize a RAG stack with vector database and ingestion settings?

Initializing a RAG stack requires generating a weave-stack.yaml file where you define your runtime environment, vector database, and ingestion settings. This configuration serves as the blueprint for the complete deployment.