Vertex AI RAG Engine quotas

The VPC-SC security control is supported by RAG Engine. Data residency, CMEK, and AXT security controls aren't supported.

For each service to perform retrieval-augmented generation (RAG) using RAG Engine, the following quotas apply, with the quota measured as requests per minute (RPM).

Service	Quota	Metric
RAG Engine data management APIs	60 RPM	VertexRagDataService requests per minute per region
RetrievalContexts API	1,500 RPM	VertexRagService retrieve requests per minute per region
base_model: textembedding-gecko	1,500 RPM	Online prediction requests per base model per minute per region per base_model An additional filter for you to specify is base_model: textembedding-gecko

The following limits apply:

Service	Limit	Metric
Concurrent ImportRagFiles requests	3 RPM	VertexRagService concurrent import requests per region
Maximum number of files per ImportRagFiles request	10,000	VertexRagService import rag files requests per region

For more rate limits and quotas, see Generative AI on Vertex AI rate limits.

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 about the differences between RAG and grounding, see Ground responses using RAG.
• 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.