Context management
Vertex AI RAG Engine (Gemini Enterprise Agent Platform)
Managed RAG framework for context augmentation: ingestion, chunking, embeddings, retrieval, reranking
Commercial
What it is
Our note
RAG Engine is Google's context-augmentation framework rather than a single API: it owns ingestion, transformation, embedding and vector storage, then hands back a retrieval corpus. Because indexing and retrieval run on Spanner, retrieval cost surfaces as database billing, an unusual pricing shape for a RAG product.
At a glance
- Vendor
- Google Cloud
- Business model
- Commercial
- Pricing
- Billed per component: embedding model usage, Spanner/vector database for indexing and retrieval, LLM or Agent Search ranking for reranking; data-source access free pricing page ↗
- Self-hosting
- No, hosted only
- Access
- Vertex AI SDK and REST; RAG-managed vector database or bring-your-own; Agent Search ranking API for reranking
Links and sources
- Official sitecloud.google.com/vertex-ai/generative-ai/docs/rag-engine/rag-overview
- Pricingcloud.google.com/gemini-enterprise-agent-platform/build/rag-engine/rag-engine-billing
Facts verified nov 10, 2026; added nov 10, 2026. Vendor facts come from the vendor’s own pages; benchmark claims are self-reported unless we say otherwise.