Tutorial: Create a document processing pipeline with Document AI¶

What you will learn¶

In this tutorial, you will learn how to:

• Set up the objects and privileges required to work with Document AI.

• Prepare a Document AI model build using Document AI user interface in Snowsight to extract data from unstructured documents.

• Create a pipeline for continuous processing of new documents in stage, using a Document AI model build, and streams and tasks.

Prerequisites¶

The following prerequisites are required to complete this tutorial:

• You must connect as a user that has the ACCOUNTADMIN role which is used to create a custom role used in this tutorial and grant the new role required privileges.

• You must have a Snowflake account in either AWS or a Microsoft Azure commercial region, with the exception of:

  • AWS Asia Pacific (Singapore)

  • AWS Asia Pacific (Osaka)

  • AWS EU (Paris)

  • Microsoft Azure Switzerland North (Zurich)

• You must have a warehouse ready to use with Document AI. For more information about selecting a warehouse, see Determining optimal warehouse size for Document AI.

Create a database, schema, and custom role¶

To create a database, schema, and a role to work with Document AI, do the following:

1. Create a database and schema in which to create a Document AI model build:

   CREATE DATABASE doc_ai_db;
   CREATE SCHEMA doc_ai_db.doc_ai_schema;
   

   Copy

2. Create custom role doc_ai_role to prepare the Document AI model build and to create processing pipelines:

   USE ROLE ACCOUNTADMIN;
   
   CREATE ROLE doc_ai_role;
   

   Copy

Grant the required privileges¶

To grant the privileges required to work with Document AI, do the following:

1. Grant the SNOWFLAKE.DOCUMENT_INTELLIGENCE_CREATOR database role to the doc_ai_role role:

   GRANT DATABASE ROLE SNOWFLAKE.DOCUMENT_INTELLIGENCE_CREATOR TO ROLE doc_ai_role;
   

   Copy

2. Grant warehouse usage and operating privileges to the doc_ai_role role:

   GRANT USAGE, OPERATE ON WAREHOUSE <your_warehouse> TO ROLE doc_ai_role;
   

   Copy

3. Grant the privileges to use the database and schema you created to the doc_ai_role:

   GRANT USAGE ON DATABASE doc_ai_db TO ROLE doc_ai_role;
   GRANT USAGE ON SCHEMA doc_ai_db.doc_ai_schema TO ROLE doc_ai_role;
   

   Copy

4. Grant the create stage privilege on the schema to the doc_ai_role role to store the documents for extraction:

   GRANT CREATE STAGE ON SCHEMA doc_ai_db.doc_ai_schema TO ROLE doc_ai_role;
   

   Copy

5. Grant the privilege to create model builds (instances of the DOCUMENT_INTELLIGENCE class) to the doc_ai_role role:

   GRANT CREATE SNOWFLAKE.ML.DOCUMENT_INTELLIGENCE ON SCHEMA doc_ai_db.doc_ai_schema TO ROLE doc_ai_role;
   

   Copy

6. Grant the privileges required to create a processing pipeline using streams and tasks to the doc_ai_role role:

   GRANT CREATE STREAM, CREATE TABLE, CREATE TASK, CREATE VIEW ON SCHEMA doc_ai_db.doc_ai_schema TO ROLE doc_ai_role;
   GRANT EXECUTE TASK ON ACCOUNT TO ROLE doc_ai_role;
   

   Copy

7. Grant the doc_ai_role to tutorial user for use in the next steps of the tutorial:

   GRANT ROLE doc_ai_role TO USER <your_user_name>;
   

   Copy

What you learned in this section¶

In this section you learned how to:

• Create the database and schema to contain a Document AI model build.

• Create the doc_ai_role custom role.

• Grant required privileges to the doc_ai_role role, and grant that role to the tutorial user.

Create a Document AI model build¶

To create a Document AI model build, do the following:

1. Sign in to Snowsight.

2. In the navigation menu, select AI & ML » Document AI.

3. Select a warehouse.

4. Select + Build.

5. In the dialog that appears, enter inspection_reviews as a name for your model build, and select the location (doc_ai_db database and doc_ai_schema schema).

6. Select Create.

Upload documents to the Document AI model build¶

To upload documents to the newly created Document AI model build, do the following:

1. To obtain the documents required for the tutorial to test the model build, download the zip file to your local file system.

2. Unzip the content, which includes PDF documents.

3. In the inspection_reviews model build, select the Build Details tab.

4. Select Upload documents.

5. Select Browse or drag the documents you downloaded.

6. Select Upload.

What you learned in this section¶

In this section you learned how to:

• Create a Document AI model build.

• Upload documents to test the Document AI model build.

What you learned in this section¶

In this section you learned how to:

• Define data values to extract by asking the model questions in natural language.

• Review results by confirming or correcting the answers that the model provided.

What you learned in this section¶

In this section you published the Document AI model build to use the model build for extraction in processing pipelines.

Set up the processing pipeline¶

1. Create an internal my_pdf_stage stage to store the documents:

   CREATE OR REPLACE STAGE my_pdf_stage
     DIRECTORY = (ENABLE = TRUE)
     ENCRYPTION = (TYPE = 'SNOWFLAKE_SSE');
   

   Copy

2. Create a my_pdf_stream stream on a my_pdf_stage stage:

   CREATE STREAM my_pdf_stream ON STAGE my_pdf_stage;
   

   Copy

3. Refresh the metadata of the directory table that will store the staged document files:

   ALTER STAGE my_pdf_stage REFRESH;
   

   Copy

4. Specify the database and schema:

   USE DATABASE doc_ai_db;
   USE SCHEMA doc_ai_schema;
   

   Copy

5. Create a pdf_reviews table to store the information about the documents (such as file_name) and the data to be extracted from the PDF documents:

   CREATE OR REPLACE TABLE pdf_reviews (
     file_name VARCHAR,
     file_size VARIANT,
     last_modified VARCHAR,
     snowflake_file_url VARCHAR,
     json_content VARCHAR
   );
   

   Copy

   The json_content column will include the extracted information in JSON format.

6. Create a load_new_file_data task to process new documents in the stage:

   CREATE OR REPLACE TASK load_new_file_data
     WAREHOUSE = <your_warehouse>
     SCHEDULE = '1 minute'
     COMMENT = 'Process new files in the stage and insert data into the pdf_reviews table.'
   WHEN SYSTEM$STREAM_HAS_DATA('my_pdf_stream')
   AS
   INSERT INTO pdf_reviews (
     SELECT
       RELATIVE_PATH AS file_name,
       size AS file_size,
       last_modified,
       file_url AS snowflake_file_url,
       inspection_reviews!PREDICT(GET_PRESIGNED_URL('@my_pdf_stage', RELATIVE_PATH), 1) AS json_content
     FROM my_pdf_stream
     WHERE METADATA$ACTION = 'INSERT'
   );
   

   Copy

   Note that newly created tasks are automatically suspended.

7. Start the newly created task:

   ALTER TASK load_new_file_data RESUME;
   

   Copy

Upload new documents to an internal stage¶

1. To obtain the documents required for the tutorial, download the zip file to your local file system.

2. Unzip the content, which includes PDF files.

3. In Snowsight, select Data » Databases.

4. Select the doc_ai_db database, the doc_ai_schema, and the my_pdf_stage stage.

5. Select + Files.

6. In the Upload Your Files dialog that appears, select the files you just downloaded.

7. Select Upload.

View the extracted information¶

1. After uploading the documents to the stage, view the information extracted from new documents:

   SELECT * FROM pdf_reviews;
   

   Copy

2. Create a pdf_reviews_2 table to analyze the extracted information in separate columns:

   CREATE OR REPLACE TABLE doc_ai_db.doc_ai_schema.pdf_reviews_2 AS (
    WITH temp AS (
      SELECT
        RELATIVE_PATH AS file_name,
        size AS file_size,
        last_modified,
        file_url AS snowflake_file_url,
        inspection_reviews!PREDICT(get_presigned_url('@my_pdf_stage', RELATIVE_PATH), 1) AS json_content
      FROM directory(@my_pdf_stage)
    )
   
    SELECT
      file_name,
      file_size,
      last_modified,
      snowflake_file_url,
      json_content:__documentMetadata.ocrScore::FLOAT AS ocrScore,
      f.value:score::FLOAT AS inspection_date_score,
      f.value:value::STRING AS inspection_date_value,
      g.value:score::FLOAT AS inspection_grade_score,
      g.value:value::STRING AS inspection_grade_value,
      i.value:score::FLOAT AS inspector_score,
      i.value:value::STRING AS inspector_value,
      ARRAY_TO_STRING(ARRAY_AGG(j.value:value::STRING), ', ') AS list_of_units
    FROM temp,
      LATERAL FLATTEN(INPUT => json_content:inspection_date) f,
      LATERAL FLATTEN(INPUT => json_content:inspection_grade) g,
      LATERAL FLATTEN(INPUT => json_content:inspector) i,
      LATERAL FLATTEN(INPUT => json_content:list_of_units) j
    GROUP BY ALL
   );
   

   Copy

3. View the output:

   SELECT * FROM pdf_reviews_2;
   

   Copy

The table uses the FLATTEN function to parse the json_content JSON into separate columns for easier viewing.

The table contains the data values (such as inspection_grade_value, inspection_date_value) that were defined when the model build was prepared for inspection documents, and the corresponding confidence scores (inspection_grade_score, inspection_date_score).

What you learned in this section¶

In this section you learned how to:

• Create an internal stage to store new documents.

• Create a stream and a task required to prepare a processing pipeline.

• Upload documents to an internal stage.

• View the extracted information in a table.

Additional resources¶

Continue learning using the following resources:

• Working with Document AI

• Question optimization for extracting information with Document AI

• Prepare your documents for Document AI

• Introduction to Streams

• Introduction to tasks

• Stream and task commands