--- schema_version: "1" id: 5a1863bd87feacf3ec6884032e4c3a3e1bbfbb17e61ee4cb6ca2e7eb7cff0368 title: DocumentExtractionDef collection: legacydeveloper version: current locale: en-us portal_url: https://docs.salesforce.com/legacydeveloper/current/en-us/health_cloud_object_reference/meta_documentextractiondef.md canonical_url: https://developer.salesforce.com/docs/atlas.en-us.health_cloud_object_reference.meta/health_cloud_object_reference/meta_documentextractiondef.htm source_site: developer.salesforce.com content_type: documentation content_hash: 93b87217a4a0e2538c9b14adef0648fe92263eeff1c68405929328b15eae26e0 description: Represents the metadata definition used to manage and execute document data extraction processes. --- # DocumentExtractionDef Represents the metadata definition used to manage and execute document data extraction processes. ![Important](https://developer.salesforce.com/docs/atlas.en-us.health_cloud_object_reference.meta/health_cloud_object_reference/images/icon_note_important.png) #### Important Where possible, we changed noninclusive terms to align with our company value of Equality. We maintained certain terms to avoid any effect on customer implementations. ## Parent Type This type extends the [Metadata](https://developer.salesforce.com/docs/atlas.en-us.262.0.api_meta.meta/api_meta/metadata.htm) metadata type and inherits its fullName field. ## File Suffix and Directory Location Replace DEVELOPER\_NAME with the developer name of the definition. DocumentExtractionDef values are stored in the DEVELOPER\_NAME.documentExtractionDef file in the documentExtractionDefs directory. ## Version DocumentExtractionDef is available in API version 66.0 and later. ## Fields ### batchProcessingStartTime - **Field Type**: dateTime - **Description**: The date and time when batch processing starts. Files with earlier timestamps are excluded during processing. ### batchUser - **Field Type**: User - **Description**: The user associated with the batch processing. ### description - **Field Type**: string - **Description**: The description of the document extraction definition. ### documentExtractionDefVer - **Field Type**: [DocumentExtractionDefVer](#DocumentExtractionDefVer) - **Description**: An array of specific version settings configuration objects metadata details associated with this definition. ### documentExtrctDefProcFldr - **Field Type**: [DocumentExtrctDefProcFldr](#DocumentExtrctDefProcFldr) - **Description**: The destination or source target file directories utilized for document data intake and execution processing. ### isActive - **Field Type**: boolean - **Description**: Indicates whether the document extraction definition is currently active (true) or inactive (false). ### isReviewRequired - **Field Type**: boolean - **Description**: Indicates whether the extraction requires review before the data is saved (true) post-extraction parsing cycles. ### label - **Field Type**: string - **Description**: The user-facing display label assigned to the DocumentExtractionDef interface reference component entity. ### status - **Field Type**: DocumentExtractionDefStatus (enumeration of type string) - **Description**: The status of the document extraction definition. - **Possible values**: - BatchDefined - BatchActive ### type - **Field Type**: DocumentExtractionDefType (enumeration of type string) - **Description**: The type of document extraction definition, such as standard (pre-defined) or custom. - **Possible values**: - Standard - Custom ## DocumentExtractionDefVer ### confidenceThreshold - **Field Type**: int - **Description**: The minimum target parsing percentage target reliability score limit needed to assume accurate field target identification values. ### contextMappingConfig - **Field Type**: string - **Description**: The contextual data JSON string schema properties layout blueprint rule map definitions metadata block references path tracking array context. ### description - **Field Type**: string - **Description**: A localized detailed log note describing updates modifications structural variation purpose for this unique schema line record definition item. ### documentExtractionDefStep - **Field Type**: [DocumentExtractionDefStep](#DocumentExtractionDefStep) - **Description**: An object collection mapping sub-step definitions tracking exact layout actions scheduled during runtime extraction sequences. ### isActive - **Field Type**: boolean - **Description**: Specifies if this individual instance specification criteria variant is actively queried during systemic runtime analysis operations. ### largeLanguageModel - **Field Type**: string - **Description**: The identifying string name or version designation of the targeted Large Language Model engine pipeline system utilized. ### llmInputPrompt - **Field Type**: string - **Description**: The structural systemic instruction or system prompt template text sequence supplied directly to the parsing large language model platform engine. ### versionNumber - **Field Type**: int - **Description**: The unique sequential revision integer tracked for this layout iteration mapping block profile data records configuration. ## DocumentExtractionDefStep ### executionProcessReference - **Field Type**: string - **Description**: The unique component path developer key string reference matching the automation runtime execution pipeline logic block element engine. ### stepNumber - **Field Type**: int - **Description**: The sorting hierarchy sequencing index tracking the relative ordering path allocation logic map positioning order for execution. ### stepType - **Field Type**: DocExtractReqStepType (enumeration of type string) - **Description**: Defines the operational category action logic behavior module processed through this specific sequenced execution schema element state item. - **Possible values**: - Extract - Transform - PostTransformAction - Save - PostSaveAction - Validation ## DocumentExtrctDefProcFldr ### ContentHubRepositoryId - **Type**: Reference - **Properties**: Create, Filter, Group, Nillable, Sort, Update - **Description**: The Files Connect Repository ID of this Document Extraction Definition Processing Folder. - **Relationship Name**: ContentHubRepository - **Relationship Type**: Lookup - **Refers To**: ContentHubRepository ### folderPath - **Field Type**: string - **Description**: The absolute uniform identifier path url map text pattern resolving locations target destination directory container locations repository asset paths. ### folderType - **Field Type**: DocExtractDefFldrType (enumeration of type string) - **Description**: Identifies the file system interface backend hosting vendor engine target destination configuration format tracking specification metadata blocks. - **Possible values**: - ContentFolder - Amazon - AzureBlob ### lastProcessedTime - **Field Type**: dateTime - **Description**: The date time record mark capturing historical execution sweeps tracking the absolute instance execution runtime cycle. ## Declarative Metadata Sample Definition The following is an example of a DocumentExtractionDef component. true The following is an example package.xml that references the previous definition. \* DocumentExtractionDef 66.0