About Document AI #
The Document AI module brings AI-powered document analysis into M-Files. It enables automatic processing of documents using a wide range of AI models, enriching M-Files metadata and supporting advanced automation scenarios within existing workflows.
Key Features #
- Automated metadata extraction: Extract structured data from documents and map it directly to M-Files properties, reducing manual effort and errors.
- Document classification: Automatically classify documents based on their content using prebuilt AI models or advanced large language models.
- Trigger-based execution: Run AI processing on object creation, workflow state changes, or on demand.
- Flexible AI model usage: Choose from over 11 000 available AI models or use advanced LLMs depending on your use case.
- Interactive service: The Document AI module includes the M-Files Intelligent Metadata Layer service, which allows Document AI analysis to be triggered directly from the M-Files user interface.
Services #
Document AI follows a bring-your-own-model approach, where access to external AI services is provided in license by either the customer or Unitfly.
Currently supported services are:
Microsoft Foundry
- Provides access to thousands of large language models from multiple providers.
- Enables prompt-based extraction and document classification without the need for model training.
- Supports advanced logic, multi-step processing, and custom AI agent scenarios.
- Uses token-based consumption, allowing flexible control over AI usage and costs.
Azure Document Intelligence
- Offers prebuilt models for common document types such as invoices, receipts, and contracts.
- Delivers high accuracy for standardised and repetitive document formats.
- Returns structured metadata including dates, amounts, suppliers, and document types.
- Well suited for routine, high-volume document processing scenarios.
Accessing Document AI #
After you have successfully installed the application, you should configure Document AI. Enabled services are listed out in module dashboard.
NOTE: Before applying a renewed license or new version of the application, make sure that you restart your vault after.
- Open M-Files Admin.
- In the left-side tree view, expand the desired connection to M-Files Server.
- In the left-side tree view, expand the Document Vaults node.
- Still in the left-side tree view, expand the vault where you installed the connector and select Configurations.
- Expand Other Applications.
- Expand Extension Kit.
- Click on Document AI.
Initial Configuration Steps #
To begin configuring a rule, you need to define four fundamental fields to establish the rule’s essentials. Below, you will find a detailed description of each of these fields:
Name #
This required field designates the unique name for the rule. It should be clear and descriptive, aiding users in understanding the purpose or function of the rule. For example:
- Incoming Invoice – Extraction: A descriptive name for the rule that entails copying an end date from a contract to a related deal.
Description #
This field allows users to briefly describe the rule’s purpose and include any relevant information. Although optional, providing a description is highly recommended to enhance clarity. For example:
- When Incoming Invoice is Created, extract relevant metadata: This description elaborates on the trigger, trigger source, target, and action associated with the rule Incoming Invoice – Extraction.
Enabled #
Specifies whether the rule is active or inactive, providing users with control over its activation status. By default, all rules are enabled for execution. To halt or prevent the rule from executing, you can disable it.
- Yes (default): The rule is enabled and will execute.
- No: The rule is disabled and will not execute.
Configuration mode #
Specifies the mode in which the rule is configured. Depending on the complexity of the rule, users choose one of the options:
- Simple (default): Simple rule configuration options are displayed.
- Advanced: Advanced rule configuration options are displayed, showing additional functionalities. Refer to the advanced rule configuration guide for detailed instructions.
