Document AI decommission (Pending)

Snowflake is deprecating and will eventually decommission the Document AI UI experience and the <model_build_name>!PREDICT method, and is transitioning to the AI_EXTRACT function for document extraction, which is a next-generation document extraction solution powered by the arctic-extract model. This model offers better scalability and accuracy, faster inference, and enhanced features such as longer output token limits and the ability to extract entities, lists, and tables in a single API call.

Important

The Document AI UI and the <model_build_name>!PREDICT method will be decommissioned on February 28th, 2026. After the decommission you will no longer have access to your existing model builds in the Document AI UI. The Document AI UI and the <model_build_name>!PREDICT method won’t be accessible after the decommission date, and existing Document AI models that were not migrated to the Snowflake Model Registry won’t be available for inference after the decommission date.

To continue running inference on your existing Document AI models, follow the steps in Actions required.

Behavior change

Before the change

The workflow for extracting data from documents is as follows:

  1. Create a model build.

    You create model builds in a dedicated Document AI UI, where you also upload documents, define values for extraction, and verify the answers that the model provides.

  2. Optional: Fine-tune the model.

    You can fine-tune the model in the Document AI UI if the results provided by the Snowflake Arctic-TILT model are not satisfactory.

  3. Run inference.

    You use the <model_build_name>!PREDICT method and the model build created in the Document AI UI to extract information from documents.

Note

You can view the Document AI models in the Document AI UI and in the Snowflake Model Registry.

After the change

The workflow for extracting data from documents is as follows:

  • You use the AI_EXTRACT function to define values for extraction and extract information from documents. You no longer create model builds in the Document AI UI.

Previously, you had to complete a three-step workflow that involved creating model builds, but now this process is simplified to a single step which is using the AI_EXTRACT function.

Note

The models that were previously created and/or fine-tuned in the Document AI UI can be viewed in the Snowflake Model Registry if you migrated the models (see Actions required).

You can use the fine-tuned model for inference, but you can’t fine-tune the new version of the model.

Important

AI_EXTRACT uses token-based billing. For more information, see the Snowflake Service Consumption Table.

Actions required

To continue running inference on the existing models that you created in Document AI, you must complete the following steps before February 28, 2026:

  1. Migrate your existing Document AI models (both published and trained) to the Snowflake Model Registry. When prompted in the Document AI UI, to integrate the existing models into the Model Registry, follow the instructions on the integration banner.

    For information on how to copy Document AI models between databases or schemas in the same account or between different accounts in the same organization, see Copy Document AI models between databases, schemas, and accounts.

  2. Update your extraction pipelines to use the AI_EXTRACT function for inference of Document AI legacy models.

    This ensures uninterrupted inference in production. For more information on using AI_EXTRACT with legacy Document AI models, see AI_EXTRACT (Document AI legacy models).

  3. Recommended: To continue using the Document AI data, export all of your existing Document AI model builds (which contain documents, prompts, and annotations) to a target internal stage.

    For information on how to export model builds, see Export Document AI model builds.

Ref: 2156

Language: English