使用 Vertex AI RAG 引擎擷取資料

API_KEY_SECRET_VERSION=SLACK_API_KEY_SECRET_VERSION
CHANNEL_ID=SLACK_CHANNEL_ID
PROJECT_ID=us-central1

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${ ENDPOINT }/v1beta1/projects/${ PROJECT_ID }/locations/${ PROJECT_ID }/ragCorpora/${ RAG_CORPUS_ID }/ragFiles:import \
-d '{
  "import_rag_files_config": {
    "slack_source": {
      "channels": [
        {
          "apiKeyConfig": {
            "apiKeySecretVersion": "'"${ API_KEY_SECRET_VERSION }"'"
          },
          "channels": [
            {
              "channel_id": "'"${ CHANNEL_ID }"'"
            }
          ]
        }
      ]
    }
  }
}'

    # Slack example
    start_time = protobuf.timestamp_pb2.Timestamp()
    start_time.GetCurrentTime()
    end_time = protobuf.timestamp_pb2.Timestamp()
    end_time.GetCurrentTime()
    source = rag.SlackChannelsSource(
        channels = [
            SlackChannel("CHANNEL1", "api_key1"),
            SlackChannel("CHANNEL2", "api_key2", START_TIME, END_TIME)
        ],
    )

    response = rag.import_files(
        corpus_name="projects/my-project/locations/us-central1/ragCorpora/my-corpus-1",
        source=source,
        chunk_size=512,
        chunk_overlap=100,
    )

EMAIL=JIRA_EMAIL
API_KEY_SECRET_VERSION=JIRA_API_KEY_SECRET_VERSION
SERVER_URI=JIRA_SERVER_URI
CUSTOM_QUERY=JIRA_CUSTOM_QUERY
PROJECT_ID=JIRA_PROJECT
REGION= "us-central1"

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${ ENDPOINT }/v1beta1/projects/${ PROJECT_ID }/locations/REGION>/ragCorpora/${ RAG_CORPUS_ID }/ragFiles:import \
-d '{
  "import_rag_files_config": {
    "jiraSource": {
      "jiraQueries": [{
        "projects": ["'"${ PROJECT_ID }"'"],
        "customQueries": ["'"${ CUSTOM_QUERY }"'"],
        "email": "'"${ EMAIL }"'",
        "serverUri": "'"${ SERVER_URI }"'",
        "apiKeyConfig": {
          "apiKeySecretVersion": "'"${ API_KEY_SECRET_VERSION }"'"
        }
      }]
    }
  }
}'

    # Jira Example
    jira_query = rag.JiraQuery(
        email="xxx@yyy.com",
        jira_projects=["project1", "project2"],
        custom_queries=["query1", "query2"],
        api_key="api_key",
        server_uri="server.atlassian.net"
    )
    source = rag.JiraSource(
        queries=[jira_query],
    )

    response = rag.import_files(
        corpus_name="projects/my-project/locations/REGION/ragCorpora/my-corpus-1",
        source=source,
        chunk_size=512,
        chunk_overlap=100,
    )

CLIENT_ID=SHAREPOINT_CLIENT_ID
API_KEY_SECRET_VERSION=SHAREPOINT_API_KEY_SECRET_VERSION
TENANT_ID=SHAREPOINT_TENANT_ID
SITE_NAME=SHAREPOINT_SITE_NAME
FOLDER_PATH=SHAREPOINT_FOLDER_PATH
DRIVE_NAME=SHAREPOINT_DRIVE_NAME

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${ ENDPOINT }/v1beta1/projects/${ PROJECT_ID }/locations/REGION>/ragCorpora/${ RAG_CORPUS_ID }/ragFiles:import \
-d '{
  "import_rag_files_config": {
    "sharePointSources": {
      "sharePointSource": [{
        "clientId": "'"${ CLIENT_ID }"'",
        "apiKeyConfig": {
          "apiKeySecretVersion": "'"${ API_KEY_SECRET_VERSION }"'"
        },
        "tenantId": "'"${ TENANT_ID }"'",
        "sharepointSiteName": "'"${ SITE_NAME }"'",
        "sharepointFolderPath": "'"${ FOLDER_PATH }"'",
        "driveName": "'"${ DRIVE_NAME }"'"
      }]
    }
  }
}'

    from vertexai.preview import rag
    from vertexai.preview.rag.utils import resources

    CLIENT_ID="SHAREPOINT_CLIENT_ID"
    API_KEY_SECRET_VERSION="SHAREPOINT_API_KEY_SECRET_VERSION"
    TENANT_ID="SHAREPOINT_TENANT_ID"
    SITE_NAME="SHAREPOINT_SITE_NAME"
    FOLDER_PATH="SHAREPOINT_FOLDER_PATH"
    DRIVE_NAME="SHAREPOINT_DRIVE_NAME"

    # SharePoint Example.
    source = resources.SharePointSources(
        share_point_sources=[
            resources.SharePointSource(
                client_id=CLIENT_ID,
                client_secret=API_KEY_SECRET_VERSION,
                tenant_id=TENANT_ID,
                sharepoint_site_name=SITE_NAME,
                folder_path=FOLDER_PATH,
                drive_id=DRIVE_ID,
            )
        ]
    )

    response = rag.import_files(
        corpus_name="projects/my-project/locations/REGION/ragCorpora/my-corpus-1",
        source=source,
        chunk_size=512,
        chunk_overlap=100,
    )