Cloud Renames Contribute
RenamedAI & AgentsGoogle Cloud

Vertex AI RAG Engine RAG Engine

Legacy names Vertex AI RAG Engine, LlamaIndex on Vertex AI

Managed data ingestion, chunking, embedding, and corpus retrieval framework for context-augmented LLM applications.

Open in interactive timeline ↗All Google Cloud renamesHome

Naming timeline

  1. LlamaIndex on Vertex AI / Vertex AI RAG Engine

    · Google Cloud Next '24 (Preview; GA Dec 20, 2024)

    Launched in Preview at Google Cloud Next '24 (initially introduced alongside LlamaIndex on Vertex AI) and reached General Availability as Vertex AI RAG Engine on December 20, 2024.

  2. RAG EngineCurrent name

    · Gemini Enterprise Launch (Release Notes Table Apr 22, 2026)

    Renamed from Vertex AI RAG Engine to RAG Engine (RAG Engine on Gemini Enterprise Agent Platform / Agent Platform RAG Engine).

What is Vertex AI RAG Engine called now?

Vertex AI RAG Engine is now called RAG Engine, with the latest change in October 2025 (Gemini Enterprise Launch (Release Notes Table Apr 22, 2026)). Earlier names covered by this entry also include LlamaIndex on Vertex AI. Managed data ingestion, chunking, embedding, and corpus retrieval framework for context-augmented LLM applications. Only the customer-facing name changed; the underlying technical identifiers remain backward compatible.

Also known as

  • RAG Engine on Gemini Enterprise Agent Platform
  • Agent Platform RAG Engine

Technical identifiers

Technical identifiers unchanged. Only the customer-facing product name changed; the APIs, CLI commands, IAM roles and Terraform resources below keep their legacy identifiers for backward compatibility.

REST / gRPC APIsaiplatform.googleapis.com
gcloud / CLI Commandsgcloud ai
IAM Predefined Rolesroles/aiplatform.*

Uses ragCorpora and ragFiles REST/gRPC resources on aiplatform.googleapis.com.

Notes & disambiguation

  • Per the April 22, 2026 Agent Platform release notes naming table, 'Vertex AI RAG Engine' dropped the 'Vertex AI' prefix to become 'RAG Engine' (and is titled 'RAG Engine on Gemini Enterprise Agent Platform' / 'Agent Platform RAG Engine' in documentation).
  • Distinct from turnkey 'Agent Search' (discoveryengine.googleapis.com): RAG Engine runs on aiplatform.googleapis.com (ragCorpora and ragFiles resources) as a developer-managed orchestration layer that can use Vector Search, Agent Retrieval, Vertex AI Search, or managed Spanner as its vector backend.

Sources & official documentation

Catalog last updated . Spotted an error? Suggest an edit