skills.rest
r2d2helm
r2d2helmCOMMUNITY
Explore all skills by this author →
GitHub

ai-infra-skill

Orchestrate multi-VM AI infrastructure with LiteLLM, Langfuse, and pgvector.

Updated Aug 23, 2026
Search Tags:#deployment#llm#rag#observability#vector-store#ai-infra
One-click install
npx skills add https://github.com/r2d2helm/claude-code-system --skill ai-infra-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-infra-skill
Source: https://github.com/r2d2helm/claude-code-system/tree/main/skills/ai-infra-skill
Command: npx skills add https://github.com/r2d2helm/claude-code-system --skill ai-infra-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Infrastructure for AI is complex to deploy and maintain; this skill provides a blueprint to run LiteLLM, Langfuse, RAG pipelines, and vector stores with observability in a homelab or production environment.

Core Features & Use Cases

  • LiteLLM proxying for unified access to multiple providers and models
  • Langfuse-based observability, tracing, and prompts management
  • RAG indexing and vector search with pgvector
  • End-to-end deployment, evaluation, and maintenance workflows
  • Use Case: Deploy an AI assistant that mixes local and cloud models with end-to-end monitoring and cost awareness

Quick Start

Set up LiteLLM, Langfuse, and pgvector on the target VMs and run a basic health check.

Frequently Asked Questions about ai-infra-skill

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

FAQPage Schema
How do I deploy LiteLLM proxy and Langfuse for LLM observability?▼

To deploy LiteLLM and Langfuse for LLM observability, you apply deterministic deployment scripts to target VMs, configuring the proxy and observability stack before running a basic health check endpoint.

What is the best way to set up a RAG pipeline with pgvector on multiple VMs?▼

Setting up a RAG pipeline with pgvector involves orchestrating multi-VM deployments to ensure vector store readiness, integrating indexing workflows, and validating search connectivity through safe external API integration.

Can I use this AI infrastructure deployment approach for a homelab environment?▼

Yes, this AI infrastructure deployment approach supports both homelab and production scenarios, applying deterministic deployment scripts to establish LiteLLM, Langfuse, and vector storage on target VMs.

Does LiteLLM proxying support unified access to multiple LLM providers?▼

LiteLLM proxying enables unified access to multiple providers and models, allowing you to mix local and cloud models while maintaining cost awareness and end-to-end monitoring through Langfuse.

How do I validate vector store readiness and health endpoints after deployment?▼

You validate vector store readiness and health endpoints by running a basic health check after setting up pgvector, LiteLLM, and Langfuse on the target VMs to ensure deterministic infrastructure stability.

Why does AI infrastructure deployment require deterministic scripts for LLM access?▼

AI infrastructure deployment requires deterministic scripts to orchestrate reliable LLM access, ensuring safe external API integration, consistent multi-VM configurations, and predictable health endpoint validation.

Related Skills

Explore More Software Engineering Skills→
shahmirerrorshahmirerror

deployment

Configures deployment targets and publishing workflows for software projects.

Community
Intermediate
0xmariowu0xmariowu
4

health

Run local deterministic health checks on the Builder Data Collection system.

Community
Basic
jg-chalk-iojg-chalk-io

moai-ml-rag

Build RAG pipelines with vector databases, embeddings, and LLM generation.

Community
Advanced
Renzo-TognellaRenzo-Tognella

Docker & Infrastructure

Automate Neo4j and Qdrant container setup with Docker Compose.

Community
Intermediate