Skip to main content

AI Tooling

AI Tooling

RAD Platform includes a complete self-hosted generative-AI stack you can deploy into your own Google Cloud project — model serving, chat UIs, agent builders, RAG pipelines, vector databases, gateways, and automation. This page groups those modules so you can assemble a working LLM stack layer by layer.

Every app below follows the same pattern as the rest of the platform: a lab (guided deploy → verify → operate → tear down) and a module reference (configuration guide), on Cloud Run, GKE Autopilot, or both.

Model serving

AppWhat it doesLabModule
OllamaRun open-weight LLMs (Llama, Mistral, Gemma) behind an APILabModule
LiteLLMOne OpenAI-compatible gateway in front of many model providersLabModule

Chat and assistant UIs

AppWhat it doesLabModule
Open WebUISelf-hosted chat UI for local and remote modelsLabModule
LibreChatMulti-provider chat with agents and searchLabModule
AnythingLLMDocument chat workspaces over your own dataLabModule

Agent and workflow builders

AppWhat it doesLabModule
FlowiseVisual builder for LLM flows and agentsLabModule
DifyLLM app platform: assistants, workflows, knowledge basesLabModule
OpenClawMulti-tenant gateway for isolated, persistent AI assistantsLabModule
n8n AIAI-augmented automation workflowsLabModule

RAG pipelines and data

AppWhat it doesLabModule
RAGFlowEnd-to-end retrieval-augmented generation over documentsLabModule
QdrantVector database for embeddingsLabModule
ChromaLightweight embedding store for RAG prototypesLabModule
Crawl4AILLM-friendly web crawling for ingestion pipelinesLabModule
SearXNGPrivate metasearch, a common RAG/agent search backendLabModule

Suggested stack order

  1. Serve a model — deploy Ollama, verify the API.
  2. Put a UI on it — connect Open WebUI.
  3. Add retrieval — stand up Qdrant and ingest with Crawl4AI or RAGFlow.
  4. Build an agent — wire it together in Flowise or Dify, fronted by LiteLLM.

Deploying and operating these services exercises the same skills covered in the certification study paths — GKE Autopilot and Cloud Run operations, networking, IAM, and observability — on infrastructure you assembled yourself.