设置 Openflow Connector for Box¶

示例设置¶

--The following script assumes you'll need to create all required roles, users, and objects.
--However, you may want to reuse some that are already in existence.

--Create a Snowflake service user to manage the connector
USE ROLE USERADMIN;
CREATE USER <openflow_service_user> TYPE=SERVICE COMMENT='Service user for Openflow automation';

--Create a pair of secure keys (public and private). For more information, see
--key-pair authentication. Store the private key for the user in a file to supply
--to the connector’s configuration. Assign the public key to the Snowflake service user:
ALTER USER <openflow_service_user> SET RSA_PUBLIC_KEY = '<pubkey>';


--Create a role to manage the connector and the associated data and
--grant it to that user
USE ROLE SECURITYADMIN;
CREATE ROLE <openflow_connector_admin_role>;
GRANT ROLE <openflow_connector_admin_role> TO USER <openflow_service_user>;


--The following block is for the use case: Ingest files and perform processing with Cortex
--Create a role for read access to the cortex search service created by this connector.
--This role should be granted to any role that will use the service
CREATE ROLE <cortex_search_service_read_only_role>;
GRANT ROLE <cortex_search_service_read_only_role> TO ROLE <whatever_roles_will_access_search_service>;

--Create the database the data will be stored in and grant usage to the roles created
USE ROLE ACCOUNTADMIN; --use whatever role you want to own your DB
CREATE DATABASE IF NOT EXISTS <destination_database>;
GRANT USAGE ON DATABASE <destination_database> TO ROLE <openflow_connector_admin_role>;

--Create the schema the data will be stored in and grant the necessary privileges
--on that schema to the connector admin role:
USE DATABASE <destination_database>;
CREATE SCHEMA IF NOT EXISTS <destination_schema>;
GRANT USAGE ON SCHEMA <destination_schema> TO ROLE <openflow_connector_admin_role>;
GRANT CREATE TABLE, CREATE DYNAMIC TABLE, CREATE STAGE, CREATE SEQUENCE, CREATE CORTEX
SEARCH SERVICE ON SCHEMA <destination_schema> TO ROLE <openflow_connector_admin_role>;

--The following block is for use case: Ingest files and perform processing with Cortex
--Grant the Cortex read-only role access to the database and schema
GRANT USAGE ON DATABASE <destination_database> TO ROLE <cortex_search_service_read_only_role>;
GRANT USAGE ON SCHEMA <destination_schema> TO ROLE <cortex_search_service_read_only_role>;

--Create the warehouse this connector will use if it doesn't already exist. Grant the
--appropriate privileges to the connector admin role. Adjust the size according to your needs.
CREATE WAREHOUSE <openflow_warehouse>
WITH
   WAREHOUSE_SIZE = 'MEDIUM'
   AUTO_SUSPEND = 300
   AUTO_RESUME = TRUE;
GRANT USAGE, OPERATE ON WAREHOUSE <openflow_warehouse> TO ROLE <openflow_connector_admin_role>;

Copy

仅引入文件¶

使用连接器定义可执行以下操作：

• 使用 Document AI 处理引入的文件。

• 对引入的文件执行自定义处理。

引入文件并使用 Cortex 执行处理¶

使用连接器定义可执行以下操作：

• 为组织 Box 企业内的公共文档创建 AI 助手

• 使您的 AI 助手遵守组织 Box 企业中指定的访问控制

SELECT PARSE_JSON(
  SNOWFLAKE.CORTEX.SEARCH_PREVIEW(
    '<application_instance_name>.cortex.search_service',
      '{
        "query": "<your_question>",
         "columns": ["chunk", "web_url"],
         "filter": {"@contains": {"user_emails": "<user_emailID>"} },
         "limit": <number_of_results>
       }'
   )
)['results'] AS results

SELECT PARSE_JSON(
     SNOWFLAKE.CORTEX.SEARCH_PREVIEW(
          '<application_instance_name>.cortex.search_service',
          '{
             "query": "What is my vacation carryover policy?",
             "columns": ["chunk", "web_url"],
             "filter": {"@contains": {"user_emails": "<user_emailID>"} },
             "limit": 1
          }'
     )
 )['results'] AS results

import snowflake.snowpark as snowpark
from snowflake.snowpark import Session
from snowflake.core import Root

def main(session: snowpark.Session):

   root = Root(session)

   # fetch service
   my_service = (root
     .databases["<application_instance_name>"]
     .schemas["cortex"]
     .cortex_search_services["search_service"]
   )

   # query service
   resp = my_service.search(
     query="What is my vacation carryover policy?",
     columns = ["chunk", "web_url"],
     filter = {"@contains": {"user_emails": "<user_emailID>"} },
     limit=1
   )
   return (resp.to_json())

curl --location "https://<account_url>/api/v2/databases/<application_instance_name>/schemas/cortex/cortex-search-services/search_service" \
     --header 'Content-Type: application/json' \
     --header 'Accept: application/json' \
     --header "Authorization: Bearer <CORTEX_SEARCH_JWT>" \
     --data '{
         "query": "What is my vacation carryover policy?",
         "columns": ["chunk", "web_url"],
         "limit": 1
     }'

{
  "results" : [ {
  "web_url" : "https://<domain>.box.com/sites/<site_name>/<path_to_file>",
  "chunk" : "Answer to the question asked."
  } ]
}

使用 Box AI 提取 Box 元数据并将其引入到 Snowflake 表中¶

使用连接器定义可执行以下操作：

• 提取有关 Box 文件的元数据并将其引入到 Snowflake 表中

• 对存储在 Box 中的文件的元数据执行操作

CREATE OR REPLACE TABLE OPENFLOW.BOX_METADATA_SCHEMA.LOAN_AGREEMENT_METADATA (
  BOX_FILE_ID               VARCHAR    COMMENT 'Box file identifier column',
  LOAN_ID                   STRING     COMMENT 'Unique loan agreement identifier (e.g. L-2025-0001)',
  BORROWER_NAME             STRING     COMMENT 'Name of the borrower entity or individual',
  LENDER_NAME               STRING     COMMENT 'Name of the lending institution',
  LOAN_AMOUNT               DOUBLE     COMMENT 'Principal amount of the loan (in USD)',
  INTEREST_RATE             FLOAT      COMMENT 'Annual interest rate (%)',
  EFFECTIVE_DATE            DATE       COMMENT 'Date on which the loan becomes effective',
  MATURITY_DATE             DATE       COMMENT 'Scheduled loan maturity date',
  LOAN_TERM_MONTHS          FLOAT      COMMENT 'Original term length in months',
  COLLATERAL_DESCRIPTION    TEXT       COMMENT 'Description of collateral securing the loan',
  CREDIT_SCORE              FLOAT      COMMENT 'Borrower credit score',
  JURISDICTION              STRING     COMMENT 'Governing law jurisdiction (e.g. NY, CA)'
);

将 Box 文件元数据实例与 Snowflake 表同步¶

使用连接器定义对 Snowflake 表中 Box 的元数据执行数据转换，并将更改添加回 Box 元数据实例。