Switching between modes

Deployment modes are a project-level configuration. Switching between the two modes doesn't move or delete your data from the other mode. You can use the UpdateRagEngineConfig API to switch between the Serverless and Spanner deployment modes. You can also use this API to set the tier on your Spanner deployment mode or to unprovision your Spanner mode to stop billing. You can use the GetRagEngineConfig API to read your current deployment mode information.

Switching to Serverless mode

The following code samples demonstrate how to switch your RagEngineConfig to Serverless mode:

Console

In the Google Cloud console, go to the RAG Enginepage.
Go to RAG Engine
Select the region in which your Vertex AI RAG Engine is running.
Click the Switch to Serverlessoption. It might not be visible if you're on Serverless mode. You can verify your current mode from the mode label at the top right section of the page.

REST

  PROJECT_ID 
:  
Your  
project  
ID. LOCATION 
:  
The  
region  
to  
process  
the  
request.

 curl  
-X  
PATCH  
 \ 
-H  
 "Content-Type: application/json" 
  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
https:// LOCATION 
-aiplatform.googleapis.com/v1beta1/projects/ PROJECT_ID 
/locations/ LOCATION 
/ragEngineConfig  
-d  
 "{'ragManagedDbConfig': {'serverless': {}}}"

Python

  from 
  
 vertexai.preview 
  
 import 
 rag 
 import 
  
  vertexai 
 
 PROJECT_ID 
 = 
  YOUR_PROJECT_ID 
 
 LOCATION 
 = 
  YOUR_RAG_ENGINE_LOCATION 
 
 # Initialize Vertex AI API once per session 
  vertexai 
 
 . 
 init 
 ( 
 project 
 = 
 PROJECT_ID 
 , 
 location 
 = 
 LOCATION 
 ) 
 rag_engine_config_name 
 = 
 f 
 "projects/ 
 { 
 PROJECT_ID 
 } 
 /locations/ 
 { 
 LOCATION 
 } 
 /ragEngineConfig" 
 new_rag_engine_config 
 = 
 rag 
 . 
 RagEngineConfig 
 ( 
 name 
 = 
 rag_engine_config_name 
 , 
 rag_managed_db_config 
 = 
 rag 
 . 
 RagManagedDbConfig 
 ( 
 mode 
 = 
 rag 
 . 
 Serverless 
 ()), 
 ) 
 updated_rag_engine_config 
 = 
 rag 
 . 
 rag_data 
 . 
 update_rag_engine_config 
 ( 
 rag_engine_config 
 = 
 new_rag_engine_config 
 ) 
 print 
 ( 
 updated_rag_engine_config 
 )

Switching to Spanner mode

The following code samples demonstrate how to switch your RagEngineConfig to Spanner mode. If you've previously used Spanner mode, and have chosen a tier, you don't need to provide it explicitly while switching. If not, refer to the lower code examples on how to switch to Spanner mode while providing a tier.

Console

In the Google Cloud console, go to the RAG Enginepage.
Go to RAG Engine
Select the region in which your Vertex AI RAG Engine is running.
Click the Switch to Spanneroption. It might not be visible if you're on Spanner mode. You can verify your current mode from the mode label.

REST

  PROJECT_ID 
:  
Your  
project  
ID. LOCATION 
:  
The  
region  
to  
process  
the  
request.

 curl  
-X  
PATCH  
 \ 
-H  
 "Content-Type: application/json" 
  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
https:// LOCATION 
-aiplatform.googleapis.com/v1beta1/projects/ PROJECT_ID 
/locations/ LOCATION 
/ragEngineConfig  
-d  
 "{'ragManagedDbConfig': {'spanner': {}}}"

Python

  from 
  
 vertexai.preview 
  
 import 
 rag 
 import 
  
  vertexai 
 
 PROJECT_ID 
 = 
  YOUR_PROJECT_ID 
 
 LOCATION 
 = 
  YOUR_RAG_ENGINE_LOCATION 
 
 # Initialize Vertex AI API once per session 
  vertexai 
 
 . 
 init 
 ( 
 project 
 = 
 PROJECT_ID 
 , 
 location 
 = 
 LOCATION 
 ) 
 rag_engine_config_name 
 = 
 f 
 "projects/ 
 { 
 PROJECT_ID 
 } 
 /locations/ 
 { 
 LOCATION 
 } 
 /ragEngineConfig" 
 new_rag_engine_config 
 = 
 rag 
 . 
 RagEngineConfig 
 ( 
 name 
 = 
 rag_engine_config_name 
 , 
 rag_managed_db_config 
 = 
 rag 
 . 
 RagManagedDbConfig 
 ( 
 mode 
 = 
 rag 
 . 
 Spanner 
 ()), 
 ) 
 updated_rag_engine_config 
 = 
 rag 
 . 
 rag_data 
 . 
 update_rag_engine_config 
 ( 
 rag_engine_config 
 = 
 new_rag_engine_config 
 ) 
 print 
 ( 
 updated_rag_engine_config 
 )

Read your current RagEngineConfig

The following code samples demonstrate how to read your RagEngineConfig to see what mode and tier is chosen:

REST

  PROJECT_ID 
:  
Your  
project  
ID. LOCATION 
:  
The  
region  
to  
process  
the  
request.

 curl  
-X  
GET  
 \ 
-H  
 "Content-Type: application/json" 
  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
https:// LOCATION 
-aiplatform.googleapis.com/v1beta1/projects/ PROJECT_ID 
/locations/ LOCATION 
/ragEngineConfig

Python

  from 
  
 vertexai.preview 
  
 import 
 rag 
 import 
  
  vertexai 
 
 PROJECT_ID 
 = 
  YOUR_PROJECT_ID 
 
 LOCATION 
 = 
  YOUR_RAG_ENGINE_LOCATION 
 
 # Initialize Vertex AI API once per session 
  vertexai 
 
 . 
 init 
 ( 
 project 
 = 
 PROJECT_ID 
 , 
 location 
 = 
 LOCATION 
 ) 
 rag_engine_config 
 = 
 rag 
 . 
 rag_data 
 . 
 get_rag_engine_config 
 ( 
 name 
 = 
 f 
 "projects/ 
 { 
 PROJECT_ID 
 } 
 /locations/ 
 { 
 LOCATION 
 } 
 /ragEngineConfig" 
 ) 
 print 
 ( 
 rag_engine_config 
 )

Update the tier on Spanner mode

The following code samples demonstrate how to update the tier on Spanner mode:

Update your RagEngineConfig to Spanner mode Scaled tier

The following code samples demonstrate how to set the RagEngineConfig to the Spanner mode with Scaled tier:

Console

In the Google Cloud console, go to the RAG Enginepage.
Go to RAG Engine
Select the region in which your Vertex AI RAG Engine is running.
Click the Switch to Spanneroption, if not already on Spanner mode.
Click Configure RAG Engine. The Configure RAG Enginepane appears.
Select the tier with which you want to run your RAG Engine.
Click Save.

REST

  PROJECT_ID 
:  
Your  
project  
ID. LOCATION 
:  
The  
region  
to  
process  
the  
request.

 curl  
-X  
PATCH  
 \ 
-H  
 "Content-Type: application/json" 
  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
https:// LOCATION 
-aiplatform.googleapis.com/v1beta1/projects/ PROJECT_ID 
/locations/ LOCATION 
/ragEngineConfig  
-d  
 "{'ragManagedDbConfig': {'spanner': {'scaled': {}}}}"

Python

  from 
  
 vertexai.preview 
  
 import 
 rag 
 import 
  
  vertexai 
 
 PROJECT_ID 
 = 
  YOUR_PROJECT_ID 
 
 LOCATION 
 = 
  YOUR_RAG_ENGINE_LOCATION 
 
 # Initialize Vertex AI API once per session 
  vertexai 
 
 . 
 init 
 ( 
 project 
 = 
 PROJECT_ID 
 , 
 location 
 = 
 LOCATION 
 ) 
 rag_engine_config_name 
 = 
 f 
 "projects/ 
 { 
 PROJECT_ID 
 } 
 /locations/ 
 { 
 LOCATION 
 } 
 /ragEngineConfig" 
 new_rag_engine_config 
 = 
 rag 
 . 
 RagEngineConfig 
 ( 
 name 
 = 
 rag_engine_config_name 
 , 
 rag_managed_db_config 
 = 
 rag 
 . 
 RagManagedDbConfig 
 ( 
 mode 
 = 
 rag 
 . 
 Spanner 
 ( 
 tier 
 = 
 rag 
 . 
 Scaled 
 ())), 
 ) 
 updated_rag_engine_config 
 = 
 rag 
 . 
 rag_data 
 . 
 update_rag_engine_config 
 ( 
 rag_engine_config 
 = 
 new_rag_engine_config 
 ) 
 print 
 ( 
 updated_rag_engine_config 
 )

Update your RagEngineConfig to Spanner mode with Basic tier

The following code samples demonstrate how to set the RagEngineConfig to the Spanner mode with Basic tier:

Console

In the Google Cloud console, go to the RAG Enginepage.
Go to RAG Engine
Select the region in which your Vertex AI RAG Engine is running.
Click the Switch to Spanneroption, if not already on Spanner mode.
Click Configure RAG Engine. The Configure RAG Enginepane appears.
Select the tier that you want to run your RAG Engine.
Click Save.

REST

  PROJECT_ID 
:  
Your  
project  
ID. LOCATION 
:  
The  
region  
to  
process  
the  
request.

 curl  
-X  
PATCH  
 \ 
-H  
 "Content-Type: application/json" 
  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
https:// LOCATION 
-aiplatform.googleapis.com/v1beta1/projects/ PROJECT_ID 
/locations/ LOCATION 
/ragEngineConfig  
-d  
 "{'ragManagedDbConfig': {'spanner': {'basic': {}}}}"

Python

  from 
  
 vertexai.preview 
  
 import 
 rag 
 import 
  
  vertexai 
 
 PROJECT_ID 
 = 
  YOUR_PROJECT_ID 
 
 LOCATION 
 = 
  YOUR_RAG_ENGINE_LOCATION 
 
 # Initialize Vertex AI API once per session 
  vertexai 
 
 . 
 init 
 ( 
 project 
 = 
 PROJECT_ID 
 , 
 location 
 = 
 LOCATION 
 ) 
 rag_engine_config_name 
 = 
 f 
 "projects/ 
 { 
 PROJECT_ID 
 } 
 /locations/ 
 { 
 LOCATION 
 } 
 /ragEngineConfig" 
 new_rag_engine_config 
 = 
 rag 
 . 
 RagEngineConfig 
 ( 
 name 
 = 
 rag_engine_config_name 
 , 
 rag_managed_db_config 
 = 
 rag 
 . 
 RagManagedDbConfig 
 ( 
 mode 
 = 
 rag 
 . 
 Spanner 
 ( 
 tier 
 = 
 rag 
 . 
 Basic 
 ())), 
 ) 
 updated_rag_engine_config 
 = 
 rag 
 . 
 rag_data 
 . 
 update_rag_engine_config 
 ( 
 rag_engine_config 
 = 
 new_rag_engine_config 
 ) 
 print 
 ( 
 updated_rag_engine_config 
 )

Update your RagEngineConfig to Unprovisioned tier

The following code samples demonstrate how to set the RagEngineConfig to the Spanner mode with Unprovisioned tier. This will permanently delete all the data from your Spanner deployment mode and halt billing expenses arising from it.

Console

In the Google Cloud console, go to the RAG Enginepage.
Go to RAG Engine
Select the region in which your Vertex AI RAG Engine is running.
Click the Switch to Spanneroption, if not already on Spanner mode.
Click Delete RAG Engine. A confirmation dialog appears.
Verify that you're about to delete your data in Vertex AI RAG Engine by entering delete.
Click Confirm.
Click Save.

REST

  PROJECT_ID 
:  
Your  
project  
ID. LOCATION 
:  
The  
region  
to  
process  
the  
request.

 curl  
-X  
PATCH  
 \ 
-H  
 "Content-Type: application/json" 
  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
https:// LOCATION 
-aiplatform.googleapis.com/v1beta1/projects/ PROJECT_ID 
/locations/ LOCATION 
/ragEngineConfig  
-d  
 "{'ragManagedDbConfig': {'spanner': {'unprovisioned': {}}}}"

Python

  from 
  
 vertexai.preview 
  
 import 
 rag 
 import 
  
  vertexai 
 
 PROJECT_ID 
 = 
  YOUR_PROJECT_ID 
 
 LOCATION 
 = 
  YOUR_RAG_ENGINE_LOCATION 
 
 # Initialize Vertex AI API once per session 
  vertexai 
 
 . 
 init 
 ( 
 project 
 = 
 PROJECT_ID 
 , 
 location 
 = 
 LOCATION 
 ) 
 rag_engine_config_name 
 = 
 f 
 "projects/ 
 { 
 PROJECT_ID 
 } 
 /locations/ 
 { 
 LOCATION 
 } 
 /ragEngineConfig" 
 new_rag_engine_config 
 = 
 rag 
 . 
 RagEngineConfig 
 ( 
 name 
 = 
 rag_engine_config_name 
 , 
 rag_managed_db_config 
 = 
 rag 
 . 
 RagManagedDbConfig 
 ( 
 mode 
 = 
 rag 
 . 
 Spanner 
 ( 
 tier 
 = 
 rag 
 . 
 Unprovisioned 
 ())), 
 ) 
 updated_rag_engine_config 
 = 
 rag 
 . 
 rag_data 
 . 
 update_rag_engine_config 
 ( 
 rag_engine_config 
 = 
 new_rag_engine_config 
 ) 
 print 
 ( 
 updated_rag_engine_config 
 )

Switching between modes Stay organized with collections Save and categorize content based on your preferences.

Switching to Serverless mode

Console

REST

Python

Switching to Spanner mode

Console

REST

Python

Read your current RagEngineConfig

REST

Python

Update the tier on Spanner mode

Update your RagEngineConfig to Spanner mode Scaled tier

Console

REST

Python

Update your RagEngineConfig to Spanner mode with Basic tier

Console

REST

Python

Update your RagEngineConfig to Unprovisioned tier

Console

REST

Python

Switching between modes