Salesforce Docs Portal

Document AI

Document AI in Data 360 uses large language models (LLMs) to extract structured data from unstructured documents such as invoices, resumes, lab reports, and purchase orders.

Document AI supports two processing modes.

  • Real-time (Transactional) Mode: Invoke Document AI APIs directly for documents stored in Salesforce or the documents sent at run time. You don't need to create unstructured data model objects (UDMOs).
  • Batch Mode: To process large volumes of documents from external sources, create unstructured data model objects (UDMO) that reference the files. Data 360 has several connectors built to ingest unstructured data from third-party sources. Document AI extracts data from documents into Data Lake Objects (DLO), which represent schemas for the extracted data. Then, your data is available for search index processing and retrieval from automation flows or AI agent actions.

Document AI Requirements

Example Use Cases for Document AI

Explore how teams working in various clouds can use Document AI to create draft configurations, refine document schemas, and publish them for production use.

Cloud Use Case
Sales Cloud Ingest contract documents and proposals in Microsoft Word files and link them to customer profiles to centralize all contract data.
Sales Cloud Ingest invoices, workbook quote templates, or pricing sheets to compare them against data extracted from related loan applications.
Service Cloud Ingest guest survey data and business review presentations delivered as Microsoft PowerPoint files. Create customer records and follow-up for future opportunities.
Employee Service Ingest tax return documents and HR forms in spreadsheet-format, such as timesheet reports and benefit enrollment sheets. Link them to employee records without rigid cell-mapping configuration.
Health Cloud Extract data from patient lab reports in a range of formats, including PDFs, system-generated images, or images of hand-written notes.

Supported Large Language Models (LLMs)

Document AI supports these LLMs.

Supported LLMs
Model Provider Model Family
OpenAI GPT 5.4 (OpenAI GPT-4o*)
Vertex AI (Google) Gemini 2.5 Flash, Gemini 3 Flash
Anthropic Claude Sonnet 4.6

*Document AI in Government Cloud supports only the OpenAI GPT-4o model hosted in Microsoft Azure. For more information, review Agentforce in Government Cloud.

Supported File Types

Document AI supports these file formats.

  • PDF files (.pdf)
  • Images (.png, .jpeg)
  • Microsoft Word documents (.docx)
  • Microsoft PowerPoint presentations (.pptx)
  • Microsoft Excel single-sheet workbooks (.xlsx)

See the Document AI table on Data Cloud Limits and Guidelines for specific limits.

Document AI in Connect API

You can use the Data Cloud Connect API to create Document AI configurations. See the Connect API reference for more.

Billing Considerations for Document AI

Use of Document AI has billing implications. For more information, see Billing Considerations for Document AI.

  • Create a Document Schema Config (Auto-extraction)
    Configure a document schema to represent data extracted from your source files into a Data Lake Object (DLO). Use the auto-extraction option in the document schema builder to have an LLM define the structure of the document schema. The builder auto-populates all fields, tables, and columns.
  • Create a Document Schema Config (Manually)
    Configure a document schema to represent data extracted from your source files into a Data Lake Object (DLO). Use the document schema builder to manually define the structure of the document schema by adding fields and tables.
  • Create a Document Schema Config (Without Source)
    Configure a document schema to use in programmatic API workflows. Use the document schema builder to define a new document schema.
  • Manage Document AI Configurations
    View, edit, publish, export, and rebuild Document AI configurations. Package Document AI configurations in data kits. Save Document AI configurations as drafts, and refine your extraction schemas over multiple sessions.
  • Document AI Example Schemas
    The following prompts are JSON-formatted schemas that you can use when creating an Document AI configuration in Data 360. Use these examples as starting points, or modify them for your specific use cases.
  • Billing Considerations for Document AI
    Document AI uses Data 360 to extract structured data from unstructured documents and Flex Credits to call generative AI. Use of Document AI impacts the consumption of credits in these usage types.

See Also