Beralih antar-mode

Mode deployment adalah konfigurasi tingkat project. Beralih antara kedua mode tidak akan memindahkan atau menghapus data Anda dari mode lainnya. Anda dapat menggunakan UpdateRagEngineConfig API untuk beralih antara mode deployment Serverless dan Spanner. Anda juga dapat menggunakan API ini untuk menetapkan paket pada mode deployment Spanner atau untuk menghentikan penyediaan mode Spanner guna menghentikan penagihan. Anda dapat menggunakan GetRagEngineConfig API untuk membaca informasi mode deployment saat ini.

Beralih ke mode Serverless

Contoh kode berikut menunjukkan cara mengalihkan RagEngineConfig ke mode Serverless:

Konsol

  1. Di Google Cloud konsol, buka halaman RAG Engine.

    Buka RAG Engine

  2. Pilih region tempat Vertex AI RAG Engine Anda berjalan.
  3. Klik opsi Switch to Serverless. Opsi ini mungkin tidak terlihat jika Anda menggunakan mode Serverless. Anda dapat memverifikasi mode saat ini dari label mode di bagian kanan atas halaman.

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)

Beralih ke mode Spanner

Contoh kode berikut menunjukkan cara mengalihkan RagEngineConfig ke mode Spanner. Jika sebelumnya Anda telah menggunakan mode Spanner, dan telah memilih paket, Anda tidak perlu memberikannya secara eksplisit saat beralih. Jika tidak, lihat contoh kode yang lebih rendah tentang cara beralih ke mode Spanner sambil memberikan paket.

Konsol

  1. Di Google Cloud konsol, buka halaman RAG Engine.

    Buka RAG Engine

  2. Pilih region tempat Vertex AI RAG Engine Anda berjalan.
  3. Klik opsi Switch to Spanner. Opsi ini mungkin tidak terlihat jika Anda menggunakan mode Spanner. Anda dapat memverifikasi mode saat ini dari label mode.

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)

Membaca RagEngineConfig saat ini

Contoh kode berikut menunjukkan cara membaca RagEngineConfig untuk melihat mode dan paket yang dipilih:

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)

Memperbarui paket pada mode Spanner

Contoh kode berikut menunjukkan cara memperbarui paket pada mode Spanner:

Memperbarui RagEngineConfig ke mode Spanner dengan paket Skala

Contoh kode berikut menunjukkan cara menetapkan RagEngineConfig ke mode Spanner dengan paket Skala:

Konsol

  1. Di Google Cloud konsol, buka halaman RAG Engine.

    Buka RAG Engine

  2. Pilih region tempat Vertex AI RAG Engine Anda berjalan.
  3. Klik opsi Switch to Spanner jika belum menggunakan mode Spanner.
  4. Klik Configure RAG Engine. Panel Configure RAG Engine akan muncul.
  5. Pilih paket yang ingin Anda gunakan untuk menjalankan RAG Engine.
  6. Klik 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)

Memperbarui RagEngineConfig ke mode Spanner dengan paket Dasar

Contoh kode berikut menunjukkan cara menetapkan RagEngineConfig ke mode Spanner dengan paket Dasar:

Konsol

  1. Di Google Cloud konsol, buka halaman RAG Engine.

    Buka RAG Engine

  2. Pilih region tempat Vertex AI RAG Engine Anda berjalan.
  3. Klik opsi Switch to Spanner jika belum menggunakan mode Spanner.
  4. Klik Configure RAG Engine. Panel Configure RAG Engine akan muncul.
  5. Pilih paket yang ingin Anda gunakan untuk menjalankan RAG Engine.
  6. Klik 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)

Memperbarui RagEngineConfig ke paket Tidak Disediakan

Contoh kode berikut menunjukkan cara menetapkan RagEngineConfig ke mode Spanner dengan paket Tidak Disediakan. Tindakan ini akan menghapus semua data dari mode deployment Spanner Anda secara permanen dan menghentikan biaya penagihan yang timbul darinya.

Konsol

  1. Di Google Cloud konsol, buka halaman RAG Engine.

    Buka RAG Engine

  2. Pilih region tempat Vertex AI RAG Engine Anda berjalan.
  3. Klik opsi Switch to Spanner jika belum menggunakan mode Spanner.
  4. Klik Delete RAG Engine. Dialog konfirmasi akan muncul.
  5. Verifikasi bahwa Anda akan menghapus data di Vertex AI RAG Engine dengan memasukkan delete.
  6. Klik Confirm.
  7. Klik 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)