部署模式是專案層級的設定。切換模式時，系統不會移動或刪除其他模式的資料。您可以使用 UpdateRagEngineConfig API 在無伺服器和 Spanner 部署模式之間切換，也可以使用這個 API 設定 Spanner 部署模式的層級，或取消佈建 Spanner 模式以停止計費。您可以使用 GetRagEngineConfig API 讀取目前的部署模式資訊。
切換為無伺服器模式
下列程式碼範例示範如何將 RagEngineConfig 切換為無伺服器模式：
控制台
- 前往 Google Cloud 控制台的「RAG Engine」頁面。
- 選取 RAG Engine 的執行區域。
- 按一下「切換至無伺服器」選項。如果您目前處於無伺服器模式，可能不會看到這個選項。如要確認目前的模式，請查看頁面右上方的模式標籤。
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 Agent Platform 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)
正在切換為 Spanner 模式
下列程式碼範例示範如何將 RagEngineConfig 切換至 Spanner 模式。如果您先前使用過 Spanner 模式並選擇了層級，切換時就不需要明確提供層級。如果沒有，請參閱下方程式碼範例，瞭解如何在提供層級的同時切換至 Spanner 模式。
控制台
- 前往 Google Cloud 控制台的「RAG Engine」頁面。
- 選取 RAG Engine 的執行區域。
- 按一下「切換至 Spanner」選項。如果處於 Spanner 模式，可能不會看到這個選項。你可以從模式標籤確認目前的模式。
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 Agent Platform 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)
讀取目前的 RagEngineConfig
下列程式碼範例示範如何讀取 RagEngineConfig，查看所選模式和層級：
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 Agent Platform 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)
更新 Spanner 模式的層級
下列程式碼範例示範如何更新 Spanner 模式的層級：
將 RagEngineConfig 更新為 Spanner 模式的 Scaled 層級
下列程式碼範例說明如何將 RagEngineConfig 設為 Spanner 模式，並使用「已縮放」層級：
控制台
- 前往 Google Cloud 控制台的「RAG Engine」頁面。
- 選取 RAG Engine 的執行區域。
- 如果尚未切換至 Spanner 模式，請點選「Switch to Spanner」(切換至 Spanner) 選項。
- 按一下「設定 RAG Engine」，隨即顯示「設定 RAG Engine」窗格。
- 選取要執行 RAG Engine 的層級。
- 按一下 [儲存]。
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 Agent Platform 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)
將 RagEngineConfig 更新為 Spanner 模式，並使用 Basic 層級
下列程式碼範例說明如何將 RagEngineConfig 設為 Spanner 模式 (基本層級)：
控制台
- 前往 Google Cloud 控制台的「RAG Engine」頁面。
- 選取 RAG Engine 的執行區域。
- 如果尚未切換至 Spanner 模式，請點選「Switch to Spanner」(切換至 Spanner) 選項。
- 按一下「設定 RAG Engine」，隨即顯示「設定 RAG Engine」窗格。
- 選取要執行 RAG Engine 的層級。
- 按一下 [儲存]。
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 Agent Platform 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)
將 RagEngineConfig 更新為「未佈建」層級
下列程式碼範例說明如何將 RagEngineConfig 設為 Spanner 模式 (未佈建層級)。這會永久刪除 Spanner 部署模式中的所有資料，並停止產生相關費用。
控制台
- 前往 Google Cloud 控制台的「RAG Engine」頁面。
- 選取 RAG Engine 的執行區域。
- 如果尚未切換至 Spanner 模式，請點選「Switch to Spanner」(切換至 Spanner) 選項。
- 按一下「刪除 RAG Engine」。即會顯示確認對話方塊。
- 輸入 delete，確認要刪除 RAG 引擎中的資料。
- 按一下「確認」。
- 按一下 [儲存]。
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 Agent Platform 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)