Vertex AI RAG Engine overview

The VPC-SC security controls and CMEK are supported by Vertex AI RAG Engine. Data residency and AXT security controls aren't supported.

You must be added to the allowlist to access Vertex AI RAG Engine in us-central1. For users with existing projects, there is no impact. For users with new projects, you can try other regions, or contact [e-mail] to onboard to us-central1.

This page describes what Vertex AI RAG Engine is and how it works.

Description	Console
To learn how to use the Vertex AI SDK to run Vertex AI RAG Engine tasks, see the RAG quickstart for Python.	Try Vertex AI RAG Engine

Overview

Vertex AI RAG Engine, a component of the Vertex AI Platform, facilitates Retrieval-Augmented Generation (RAG). Vertex AI RAG Engine is also a data framework for developing context-augmented large language model (LLM) applications. Context augmentation occurs when you apply an LLM to your data. This implements retrieval-augmented generation (RAG).

A common problem with LLMs is that they don't understand private knowledge, that is, your organization's data. With Vertex AI RAG Engine, you can enrich the LLM context with additional private information, because the model can reduce hallucination and answer questions more accurately.

By combining additional knowledge sources with the existing knowledge that LLMs have, a better context is provided. The improved context along with the query enhances the quality of the LLM's response.

The following image illustrates the key concepts to understanding Vertex AI RAG Engine.

These concepts are listed in the order of the retrieval-augmented generation (RAG) process.

1. Data ingestion: Intake data from different data sources. For example, local files, Cloud Storage, and Google Drive.

2. Data transformation: Conversion of the data in preparation for indexing. For example, data is split into chunks.

3. Embedding: Numerical representations of words or pieces of text. These numbers capture the semantic meaning and context of the text. Similar or related words or text tend to have similar embeddings, which means they are closer together in the high-dimensional vector space.

4. Data indexing: Vertex AI RAG Engine creates an index called a corpus. The index structures the knowledge base so it's optimized for searching. For example, the index is like a detailed table of contents for a massive reference book.

5. Retrieval: When a user asks a question or provides a prompt, the retrieval component in Vertex AI RAG Engine searches through its knowledge base to find information that is relevant to the query.

6. Generation: The retrieved information becomes the context added to the original user query as a guide for the generative AI model to generate factually grounded and relevant responses.

Supported regions

Vertex AI RAG Engine is supported in the following regions:

Region	Location	Description	Launch stage
us-central1	Iowa	v1 and v1beta1 versions are supported.	Allowlist
us-east4	Virginia	v1 and v1beta1 versions are supported.	GA
europe-west3	Frankfurt, Germany	v1 and v1beta1 versions are supported.	GA
europe-west4	Eemshaven, Netherlands	v1 and v1beta1 versions are supported.	GA

• us-central1 is changed to Allowlist. If you'd like to experiment with Vertex AI RAG Engine, try other regions. If you plan to onboard your production traffic to us-central1, contact [e-mail].

Submit feedback

To chat with Google support, go to the Vertex AI RAG Engine support group.

To send an email, use the email address [e-mail].

What's next

• To learn how to use the Vertex AI SDK to run Vertex AI RAG Engine tasks, see RAG quickstart for Python.
• To learn about grounding, see Grounding overview.
• To learn more about the responses from RAG, see Retrieval and Generation Output of Vertex AI RAG Engine.
• To learn about the RAG architecture:
  • Infrastructure for a RAG-capable generative AI application using Vertex AI and Vector Search
  • Infrastructure for a RAG-capable generative AI application using Vertex AI and AlloyDB for PostgreSQL.