All skills
google-cloud-solution-rag-enterprise-search-gke-sqldb
Design a RAG enterprise search architecture on GKE with AlloyDB, including Terraform and deployment guidance.
- Part of google/skills
- 6.4k installs
- AI Engineering · Knowledge bases
When to use it
You have private documents to search and need a vector-enabled SQL store plus open-model inference on Kubernetes, not a managed search service.
For example
You say
Use the google-cloud-solution-rag-enterprise-search-gke-sqldb skill to design a RAG search system for our internal PDF policy library, using AlloyDB and Gemma on GKE.
You get
- Technical decomposition
- Mermaid architecture diagram
- Terraform deployment guidance
How it works
- Requirements discovery and technical decomposition must be approved before any architecture or product recommendations are produced.
- Validation covers vector index checks, retrieval latency and accuracy, and security policies.
Before installing
Grounding the architecture requires the Google Developer Knowledge MCP server.
More Knowledge bases skills
See all- kb-retriever5.8kSearches your local knowledge base folder, reading PDFs and spreadsheets in pieces, and answers questions from it.
- gitnexus-impact-analysis2kChecks what depends on a piece of code and what might break before you change it.
- gitnexus-exploring1.9kExplains how code works, traces execution flows, and shows what calls a function in unfamiliar code.
- rag-engineer1kBuilds retrieval-augmented generation systems covering embeddings, vector databases, chunking and retrieval tuning.
Also in this pack
- cloud-run-basics19.4kDeploys and manages Cloud Run services, jobs and worker pools.
- gemini-api18.8kWrites code that calls Gemini models for text, images, video, audio, embeddings and more across languages.
- google-cloud-recipe-auth17.1kExplains how to authenticate and authorize users and services to Google Cloud APIs, including IAM and ADC.
- google-cloud-recipe-onboarding16.9kWalks a new developer through creating a Google Cloud account, setting up billing and deploying a first resource.