Create Grounded 모델 연결 with Google Vertex AI RAG capability

Use the Google Vertex AI RAG (Retrieval Augmented Generation) capability to create 데이터 저장소에 기반함 모델 연결 to generate accurate and contextually relevant information referenced from Google 데이터 소스.

주:

Google Vertex AI 데이터 저장소에 기반함 모델 연결 is now available in Automation 360 v34 release on 클라우드 as well. You can use this feature in 클라우드 and 온프레미스.

Google 데이터 스토어 with document chunking is now supported to ensure optimal results in automation executions. You can enable document chunking in the Google 데이터 스토어 for using Google Vertex AI Grounded models in AI Agent Studio.

We are now offering you the option to create 데이터 저장소에 기반함 모델 연결 using the Google 에이전트 빌더 service. A search query on the Google 데이터 스토어 retrieves relevant content from large-data-sets and feeds it to the model to generate accurate response.

During an automation execution, using 모델 연결 created with 데이터 저장소에 기반함 retrieves the response by referencing the Google 데이터 소스 in Google 데이터 스토어. This ensures an optimized response from the relevant content with higher accuracy. Grounding is an important aspect of using a foundational model as it returns grounded responses against organizational data and prevents response inaccuracies and model hallucinations.
주: To use the Google Vertex AI RAG capability in AI Agent Studio, you would first create a data source in Google 에이전트 빌더. Then create a 모델 연결 using the 데이터 저장소에 기반함 option.

See: Data stores in Google Vertex AI.

전제 조건

The Automation Admin requires these roles and permissions to create and manage 모델 연결 for their business organization.
  • Role: AAE_Basic, Automation Admin custom role
  • Permission: Attended Bot Runner
  • Settings: AI Data Management must be enabled by the Automation Admin and the check box selected for Allow users to disable logs on AI Skills option.

See AI 도구에 대한 역할과 권한 for the Automation Admin custom role permissions.

Other requirements:
  • As mentioned earlier, you would first create a Google 데이터 소스 to create a 데이터 저장소에 기반함 모델 연결 and use it successfully in an AI 기술:.
  • If you want to store authentication details in a credential vault, have that information handy. See Credential Vault를 통한 안전한 자격증명 저장소.
  • To test a 모델 연결, you must be connected to a Bot 에이전트 22.60.10 and later. As part of the test, you would have to run the 봇 on your desktop. Hence ensure the Bot 에이전트 is configured to your user. For this task, if you have to switch connection to a different Control Room, see: Control Room 인스턴스 간 기기 등록 전환.
  • You would need access to the 레코더 package and the AI Skill: package to test the connection successfully. A test 프롬프트 would be executed to test the 모델 연결.

프로시저

  1. In your Control Room environment, navigate to AI > Model connections > Create model connection.
  2. In the Create model connection screen you would configure these Connection settings:
    Create Grounded 모델 연결 with Google Vertex AI RAG capability
    You can manually enter the model name in the Choose a model or create a custom one field. The name you enter will be used for creating the 모델 연결.
    1. Model connection name: Provide a name for easy identification of the 모델 연결.
    2. Description (optional): Add a meaningful short description defining the connection.
    3. Choose a vendor: Choose a foundational model vendor from the supported list of vendors. For creating a 데이터 저장소에 기반함 모델 연결 with Google Vertex AI, select Google Vertex AI from the drop-down list.
    4. Choose a type: Choose 데이터 저장소에 기반함 for using the RAG capability for Google Vertex AI.
    5. Choose a model or create a custom one: Choose a model from the drop-down list.
      Additionally, we also support other models available from Google 데이터 스토어, which are not available in the drop-down list. If you want to add a model from the Google 데이터 스토어, you would have to enter the model name and version with the complete URI of the model. For example: If the model is Gemini 1.5 Flash 001, the format would be gemini-1.5-001/answer_gen/v1.
      For a complete list of supported models for each foundational model vendor, see AI Agent Studio FAQ.
    6. Click Next to proceed to the Authentication details section.
  3. In the Authentication details section, configure these settings:
    1. Project Name: This is the Google Cloud account project.
    2. Region: Select a region from the drop-down list to connect for authenticating the 모델 연결. You can also add your own region that you configured when you created a data source in Google 에이전트 빌더.
      See Create a data store.
    3. Control Room OAuth Connection: Create an OAuth 2.0 Client ID. A client ID is used to identify a single application to Google's OAuth Servers.
    4. After setting up the authentication details, confirm and click Next to proceed to the Test connection section to test the 모델 연결.
    주: For details on setting up the Google Cloud Project and Control Room OAuth Connection for Google Vertex AI, see Vertex AI: 연결 작업
  4. Click Test connection to make sure all connection details have been defined correctly and check if the connection is working.
    This is a desktop operation using a Bot 에이전트. Use Bot 에이전트 22.60.10 and later for successful testing.
    • If the connection works as expected, the system will process the request and you will get a system generated success message.
    • If the connection does not work as expected, you will get a system-generated message stating the reason for the connection failure. For example, if you have not downloaded the supported foundational model package to your workspace, you would get an error message. You would have to download the package and then retest the 모델 연결.
    • If the testing a 모델 연결 is unsuccessful or if you leave the task incomplete, the 모델 연결 will not get saved and you will have to restart the process of creating the 모델 연결.
  5. Click Next to proceed to the Invite roles section to begin assigning custom roles to users.
    The Automation Admin would create custom roles and assign the 모델 연결 to the role, which can then be assigned to users. Only users assigned to this custom role can use this 모델 연결.
  6. Assign the 모델 연결 to the custom role (using RBAC) so users assigned to the role can access it.
  7. Click Create model connection to complete creating the 모델 연결.
    After successfully creating the 모델 연결, the Pro Developer would use it to create an AI 기술:.

    See: Create AI Skill: with 데이터 저장소에 기반함 모델 연결

    .

다음 단계

After creating and testing the 모델 연결, you would assign it to the Pro Developers, who would use this connection to create AI Skill:.

As the next step in your sequence of tasks, go to Create AI Skill: with 데이터 저장소에 기반함 모델 연결 and create an AI 기술: and connect to a 데이터 저장소에 기반함 모델 연결 to use it in an automation.