Last reviewed 2025-09-22 UTC
Use the following architecture guides to design and deploy generative AI applications with retrieval-augmented generation (RAG) in Google Cloud.
| Architecture guide | Description |
|---|---|
| RAG infrastructure for generative AI using Gemini Enterprise and Agent Platform | An agent-driven architecture that uses Gemini Enterprise as a unified platform to orchestrate an end-to-end RAG dataflow for enterprise applications that require real-time data availability and enriched contextual search. |
| RAG infrastructure for generative AI using Agent Platform and Vector Search | A fully managed, serverless architecture that provides optimized, high-performance vector search for large-scale applications. |
| RAG infrastructure for generative AI using Agent Platform and AlloyDB for PostgreSQL | An architecture that stores vector embeddings alongside your operational data in a fully managed database like AlloyDB for PostgreSQL. |
| RAG infrastructure for generative AI using GKE and Cloud SQL | A flexible, container-based architecture that provides maximum control to build custom applications with open source tools such as Ray, Hugging Face, and LangChain. |
| GraphRAG infrastructure for generative AI using Agent Platform and Spanner Graph | An advanced RAG architecture that combines vector search with knowledge graph queries to retrieve interconnected, contextual data, which results in more detailed and relevant generative AI responses. |
| Harness CI/CD pipeline for RAG applications | An architecture for a continuous integration (CI) and continuous deployment (CD) pipeline for a RAG application in Google Cloud. |