DocuPipe · Schema
WorkflowOnSubmitDocumentRequest
Artificial IntelligenceDocument ExtractionDocument IntelligenceIntelligent Document ProcessingOCRDocument AI
Properties
| Name | Type | Description |
|---|---|---|
| standardizeStep | object | This step will always standardize the submitted document through one or more schemas you specify. |
| standardizeReviewStep | object | This step standardizes the document and immediately reviews every resulting standardization. |
| classifyStandardizeStep | object | This step allows you to decide on a list of class IDs to classify into, and define which schemas to standardize by, conditional on the classification result. You may choose to only standardize some of |
| classifyStandardizeTransformStep | object | This step behaves exactly like `classifyStandardizeStep`, and additionally applies an ordered list of transformations to each standardization once it is saved, per `schemaToTransformations`. The raw s |
| splitStandardizeStep | object | This step first runs a split operation on the submitted document, then standardizes every resulting sub-document using all schemas provided in `schemaIds`. |
| splitClassifyStandardizeStep | object | This step runs a split operation on the submitted document, then classifies each resulting sub-document, and finally standardizes any sub-document whose classification matches a provided class-to-sche |
| workflowName | string | Optionally name your workflow |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/docupanda/json-schema/docupanda-workflow-on-submit-document-request-schema.json",
"title": "WorkflowOnSubmitDocumentRequest",
"x-generated": "2026-11-10",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/docupanda-workflow-api-openapi.yml#/components/schemas/WorkflowOnSubmitDocumentRequest",
"properties": {
"standardizeStep": {
"$ref": "#/$defs/StandardizeStep",
"title": "Standardize Step",
"description": "This step will always standardize the submitted document through one or more schemas you specify."
},
"standardizeReviewStep": {
"$ref": "#/$defs/StandardizeReviewStep",
"title": "Standardize and Review Step",
"description": "This step standardizes the document and immediately reviews every resulting standardization."
},
"classifyStandardizeStep": {
"$ref": "#/$defs/ClassifyStandardizeStep",
"title": "Classify and Standardize Step",
"description": "This step allows you to decide on a list of class IDs to classify into, and define which schemas to standardize by, conditional on the classification result. You may choose to only standardize some of the classes, or standardize the same class by multiple schemas."
},
"classifyStandardizeTransformStep": {
"$ref": "#/$defs/ClassifyStandardizeTransformStep",
"title": "Classify, Standardize, and Transform Step",
"description": "This step behaves exactly like `classifyStandardizeStep`, and additionally applies an ordered list of transformations to each standardization once it is saved, per `schemaToTransformations`. The raw standardization is always saved and reported first; a transformation failure never invalidates it."
},
"splitStandardizeStep": {
"$ref": "#/$defs/SplitStandardizeStep",
"title": "Split and Standardize Step",
"description": "This step first runs a split operation on the submitted document, then standardizes every resulting sub-document using all schemas provided in `schemaIds`."
},
"splitClassifyStandardizeStep": {
"$ref": "#/$defs/SplitClassifyStandardizeStep",
"title": "Split, Classify, and Standardize Step",
"description": "This step runs a split operation on the submitted document, then classifies each resulting sub-document, and finally standardizes any sub-document whose classification matches a provided class-to-schema mapping."
},
"workflowName": {
"type": "string",
"title": "Workflowname",
"description": "Optionally name your workflow"
}
},
"type": "object",
"$defs": {
"ClassifyStandardizeStep": {
"properties": {
"classIds": {
"items": {
"type": "string"
},
"type": "array",
"title": "Classids",
"description": "The ids of the classes to classify the data to. If omitted or empty list, use all classes."
},
"multiClass": {
"type": "boolean",
"title": "Multi-Class",
"description": "Whether the classification is multi-class or not."
},
"includeUnknown": {
"type": "boolean",
"title": "Include Unknown",
"description": "Whether to include the 'unknown' class in the classification. Only relevant for if multiClass is false and classIds is not provided."
},
"instructions": {
"type": "string",
"title": "Instructions",
"description": "Instructions for the AI on how to classify the document."
},
"classifyVersion": {
"$ref": "#/$defs/ClassifyVersion",
"title": "Classify Version",
"description": "Version of the classify behavior. Supported values: 1.0, 1.1."
},
"classToSchema": {
"additionalProperties": {
"type": "string"
},
"type": "object",
"title": "Classtoschema",
"description": "A mapping of class ID to a schema that we should standardize into. Note that not every class must be mapped to a schema, if you do not wish to standardize certain classes. Any schemas mentioned will trigger a standardize action based on the schemaId provided."
},
"stdVersion": {
"$ref": "#/$defs/StdVersion",
"title": "Stdversion",
"description": "The version of the standardization engine. Supported values: [2.0, 2.1, 2.2, 2.3, 3.0, 3.1, 3.2]. This is the only version field you need to set."
},
"stdReleaseVersion": {
"$ref": "#/$defs/StdReleaseVersion",
"description": "Deprecated - set `stdVersion` instead and this will be inferred automatically (e.g. `stdVersion=3.0` infers release 3). Kept for backwards compatibility. Supported values: [1, 2, 3].",
"deprecated": true
},
"guidelines": {
"type": "string",
"title": "Guidelines",
"description": "Guidelines for the AI on how to standardize the documents. If omitted, use the schema's guidelines."
},
"useMetadata": {
"type": "boolean",
"title": "Use Metadata",
"description": "Whether to use metadata during standardization."
},
"citations": {
"type": "boolean",
"title": "Citations",
"description": "V3 only. If true, every extracted value is cited to its place on the page (bounding box + confidence in fieldMetadata) and a Review object is created per standardization. Runs at standard effort (effortLevel is ignored) and costs 1 extra credits per page."
},
"displayMode": {
"$ref": "#/$defs/DisplayMode",
"title": "Displaymode",
"description": "The display mode of the standardization. For V1, this is called `standardizationMode`. The options are: `auto`, `spatial`, `sections`."
},
"splitMode": {
"$ref": "#/$defs/SplitMode",
"title": "Splitmode",
"description": "The split mode of the standardization. The options are: `auto`, `never`, `all`."
},
"effortLevel": {
"$ref": "#/$defs/EffortLevel",
"title": "Effortlevel",
"description": "The effort level of the standardization. The options are: `standard`, `high`."
},
"schemaToEffort": {
"additionalProperties": {
"$ref": "#/$defs/EffortLevel"
},
"type": "object",
"title": "Schematoeffort",
"description": "Optional per-schema effort override, keyed by schema ID. Keys must appear in `classToSchema`. Any schema not listed here runs at `effortLevel`. Use this when one route needs a heavier read than the rest - e.g. a dense price-matrix schema at `high` while a simple flat-list schema stays at `standard`."
},
"classifyUseMetadata": {
"type": "boolean",
"title": "Classifyusemetadata",
"description": "Whether to show the document's metadata to the AI during the CLASSIFY step. Separate from `useMetadata`, which governs the standardize step only, so turning one on does not change the other."
},
"standardizeTimeout": {
"type": "integer",
"title": "Standardizetimeout",
"description": "The timeout in seconds for the standardization operation for webhook error reporting"
},
"pages": {
"additionalProperties": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "object",
"title": "Pages",
"description": "Optional per-class page restriction, keyed by classId. Keys must be a subset of `classToSchema` keys. Values are non-empty lists of zero indexed page numbers with no duplicates. Any classId not present in this dict standardizes the full document. Out-of-range pages are silently filtered out at execution time. For XLS/XLSX files, each number selects a worksheet by its zero indexed position. Page targeting is ignored for CSV, TXT, XML, and JSON files, which are always standardized in full."
}
},
"type": "object",
"required": [
"classToSchema"
],
"title": "ClassifyStandardizeStep"
},
"ClassifyStandardizeTransformStep": {
"properties": {
"classIds": {
"items": {
"type": "string"
},
"type": "array",
"title": "Classids",
"description": "The ids of the classes to classify the data to. If omitted or empty list, use all classes."
},
"multiClass": {
"type": "boolean",
"title": "Multi-Class",
"description": "Whether the classification is multi-class or not.",
"default": false
},
"includeUnknown": {
"type": "boolean",
"title": "Include Unknown",
"description": "Whether to include the 'unknown' class in the classification. Only relevant for if multiClass is false and classIds is not provided.",
"default": true
},
"instructions": {
"type": "string",
"title": "Instructions",
"description": "Instructions for the AI on how to classify the document."
},
"classifyVersion": {
"$ref": "#/$defs/ClassifyVersion",
"title": "Classify Version",
"description": "Version of the classify behavior. Supported values: 1.0, 1.1.",
"default": 1.1
},
"classToSchema": {
"additionalProperties": {
"type": "string"
},
"type": "object",
"title": "Classtoschema",
"description": "A mapping of class ID to a schema that we should standardize into. Note that not every class must be mapped to a schema, if you do not wish to standardize certain classes. Any schemas mentioned will trigger a standardize action based on the schemaId provided."
},
"stdVersion": {
"$ref": "#/$defs/StdVersion",
"title": "Stdversion",
"description": "The version of the standardization engine. Supported values: [2.0, 2.1, 2.2, 2.3, 3.0, 3.1, 3.2]. This is the only version field you need to set.",
"default": 3.2
},
"stdReleaseVersion": {
"$ref": "#/$defs/StdReleaseVersion",
"description": "Deprecated - set `stdVersion` instead and this will be inferred automatically (e.g. `stdVersion=3.0` infers release 3). Kept for backwards compatibility. Supported values: [1, 2, 3].",
"default": 2,
"deprecated": true
},
"guidelines": {
"type": "string",
"title": "Guidelines",
"description": "Guidelines for the AI on how to standardize the documents. If omitted, use the schema's guidelines."
},
"useMetadata": {
"type": "boolean",
"title": "Use Metadata",
"description": "Whether to use metadata during standardization.",
"default": false
},
"citations": {
"type": "boolean",
"title": "Citations",
"description": "V3 only. If true, every extracted value is cited to its place on the page (bounding box + confidence in fieldMetadata) and a Review object is created per standardization. Runs at standard effort (effortLevel is ignored) and costs 1 extra credits per page.",
"default": false
},
"displayMode": {
"$ref": "#/$defs/DisplayMode",
"title": "Displaymode",
"description": "The display mode of the standardization. For V1, this is called `standardizationMode`. The options are: `auto`, `spatial`, `sections`.",
"default": "auto"
},
"splitMode": {
"$ref": "#/$defs/SplitMode",
"title": "Splitmode",
"description": "The split mode of the standardization. The options are: `auto`, `never`, `all`.",
"default": "auto"
},
"effortLevel": {
"$ref": "#/$defs/EffortLevel",
"title": "Effortlevel",
"description": "The effort level of the standardization. The options are: `standard`, `high`.",
"default": "standard"
},
"schemaToEffort": {
"additionalProperties": {
"$ref": "#/$defs/EffortLevel"
},
"type": "object",
"title": "Schematoeffort",
"description": "Optional per-schema effort override, keyed by schema ID. Keys must appear in `classToSchema`. Any schema not listed here runs at `effortLevel`. Use this when one route needs a heavier read than the rest - e.g. a dense price-matrix schema at `high` while a simple flat-list schema stays at `standard`."
},
"classifyUseMetadata": {
"type": "boolean",
"title": "Classifyusemetadata",
"description": "Whether to show the document's metadata to the AI during the CLASSIFY step. Separate from `useMetadata`, which governs the standardize step only, so turning one on does not change the other.",
"default": false
},
"standardizeTimeout": {
"type": "integer",
"title": "Standardizetimeout",
"description": "The timeout in seconds for the standardization operation for webhook error reporting"
},
"pages": {
"additionalProperties": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "object",
"title": "Pages",
"description": "Optional per-class page restriction, keyed by classId. Keys must be a subset of `classToSchema` keys. Values are non-empty lists of zero indexed page numbers with no duplicates. Any classId not present in this dict standardizes the full document. Out-of-range pages are silently filtered out at execution time. For XLS/XLSX files, each number selects a worksheet by its zero indexed position. Page targeting is ignored for CSV, TXT, XML, and JSON files, which are always standardized in full."
},
"schemaToTransformations": {
"additionalProperties": {
"items": {
"type": "string"
},
"type": "array"
},
"type": "object",
"title": "Schematotransformations",
"description": "A mapping of schema ID to an ordered list of transformation IDs applied after that schema's standardization is saved. Each transformation's output feeds the next. Keys must be schemas that appear in `classToSchema`; a schema with no entry is standardized and left untransformed."
}
},
"type": "object",
"required": [
"classToSchema",
"schemaToTransformations"
],
"title": "ClassifyStandardizeTransformStep"
},
"ClassifyVersion": {
"type": "number",
"enum": [
1,
1.1
],
"title": "ClassifyVersion"
},
"DisplayMode": {
"type": "string",
"enum": [
"auto",
"spatial",
"sections",
"image"
],
"title": "DisplayMode"
},
"EffortLevel": {
"type": "string",
"enum": [
"standard",
"high",
"extended"
],
"title": "EffortLevel"
},
"SplitClassifyStandardizeStep": {
"properties": {
"classIds": {
"items": {
"type": "string"
},
"type": "array",
"title": "Classids",
"description": "The ids of the classes to classify the data to. If omitted or empty list, use all classes."
},
"multiClass": {
"type": "boolean",
"title": "Multi-Class",
"description": "Whether the classification is multi-class or not.",
"default": false
},
"includeUnknown": {
"type": "boolean",
"title": "Include Unknown",
"description": "Whether to include the 'unknown' class in the classification. Only relevant for if multiClass is false and classIds is not provided.",
"default": true
},
"instructions": {
"type": "string",
"title": "Instructions",
"description": "Instructions for the AI on how to classify the document."
},
"classifyVersion": {
"$ref": "#/$defs/ClassifyVersion",
"title": "Classify Version",
"description": "Version of the classify behavior. Supported values: 1.0, 1.1.",
"default": 1.1
},
"classToSchema": {
"additionalProperties": {
"type": "string"
},
"type": "object",
"title": "Classtoschema",
"description": "A mapping of class ID to a schema that we should standardize into. Note that not every class must be mapped to a schema, if you do not wish to standardize certain classes. Any schemas mentioned will trigger a standardize action based on the schemaId provided."
},
"stdVersion": {
"$ref": "#/$defs/StdVersion",
"title": "Stdversion",
"description": "The version of the standardization engine. Supported values: [2.0, 2.1, 2.2, 2.3, 3.0, 3.1, 3.2]. This is the only version field you need to set.",
"default": 3.2
},
"stdReleaseVersion": {
"$ref": "#/$defs/StdReleaseVersion",
"description": "Deprecated - set `stdVersion` instead and this will be inferred automatically (e.g. `stdVersion=3.0` infers release 3). Kept for backwards compatibility. Supported values: [1, 2, 3].",
"default": 2,
"deprecated": true
},
"guidelines": {
"type": "string",
"title": "Guidelines",
"description": "Guidelines for the AI on how to standardize the documents. If omitted, use the schema's guidelines."
},
"useMetadata": {
"type": "boolean",
"title": "Use Metadata",
"description": "Whether to use metadata during standardization.",
"default": false
},
"citations": {
"type": "boolean",
"title": "Citations",
"description": "V3 only. If true, every extracted value is cited to its place on the page (bounding box + confidence in fieldMetadata) and a Review object is created per standardization. Runs at standard effort (effortLevel is ignored) and costs 1 extra credits per page.",
"default": false
},
"displayMode": {
"$ref": "#/$defs/DisplayMode",
"title": "Displaymode",
"description": "The display mode of the standardization. For V1, this is called `standardizationMode`. The options are: `auto`, `spatial`, `sections`.",
"default": "auto"
},
"splitMode": {
"$ref": "#/$defs/SplitMode",
"title": "Splitmode",
"description": "The split mode of the standardization. The options are: `auto`, `never`, `all`.",
"default": "auto"
},
"effortLevel": {
"$ref": "#/$defs/EffortLevel",
"title": "Effortlevel",
"description": "The effort level of the standardization. The options are: `standard`, `high`.",
"default": "standard"
},
"schemaToEffort": {
"additionalProperties": {
"$ref": "#/$defs/EffortLevel"
},
"type": "object",
"title": "Schematoeffort",
"description": "Optional per-schema effort override, keyed by schema ID. Keys must appear in `classToSchema`. Any schema not listed here runs at `effortLevel`. Use this when one route needs a heavier read than the rest - e.g. a dense price-matrix schema at `high` while a simple flat-list schema stays at `standard`."
},
"classifyUseMetadata": {
"type": "boolean",
"title": "Classifyusemetadata",
"description": "Whether to show the document's metadata to the AI during the CLASSIFY step. Separate from `useMetadata`, which governs the standardize step only, so turning one on does not change the other.",
"default": false
},
"standardizeTimeout": {
"type": "integer",
"title": "Standardizetimeout",
"description": "The timeout in seconds for the standardization operation for webhook error reporting"
},
"pages": {
"additionalProperties": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "object",
"title": "Pages",
"description": "Optional per-class page restriction, keyed by classId. Keys must be a subset of `classToSchema` keys. Values are non-empty lists of zero indexed page numbers with no duplicates. When splitting creates sub-documents, each list is applied separately to every matching sub-document, not to the original uploaded document. For example, `{\"classId1\": [0]}` selects the first page of every sub-document classified as `classId1`. If splitting creates no sub-documents, each list is applied to the original document. For XLS/XLSX files, each number then selects a worksheet by its zero indexed position. Page targeting is ignored for CSV, TXT, XML, and JSON files, which are standardized in full. Any classId not present in this dict standardizes the full matching document, so omitting this field applies no page restriction. Out-of-range pages are silently filtered out at execution time."
},
"schemaToTransformations": {
"additionalProperties": {
"items": {
"type": "string"
},
"type": "array"
},
"type": "object",
"title": "Schematotransformations",
"description": "Optional mapping of schema ID to an ordered list of transformation IDs applied after that schema's standardization is saved, exactly as in `classifyStandardizeTransformStep`. Each transformation's output feeds the next. Keys must be schemas that appear in `classToSchema`; a schema with no entry is standardized and left untransformed. Omit the field entirely to run no transformations."
},
"splitInstructions": {
"type": "string",
"title": "Splitinstructions",
"description": "Optional instructions that control how the document is split before classification and standardization."
},
"splitDatasetSuffix": {
"type": "string",
"title": "Splitdatasetsuffix",
"description": "Suffix appended to the dataset provided during upload when assigning sub-documents. If the original document has no dataset, this suffix is used as the entire dataset name."
},
"splitFilenamePrefix": {
"type": "string",
"title": "Splitfilenameprefix",
"description": "Filename prefix to apply to each generated sub-document during the split operation."
},
"splitDisplayMode": {
"$ref": "#/$defs/DisplayMode",
"title": "Splitdisplaymode",
"description": "Display mode to use when running the split operation. The options mirror the split endpoint: `auto`, `spatial`, `sections`, `image`.",
"default": "auto"
},
"splitVersion": {
"$ref": "#/$defs/SplitVersion",
"description": "Version of the split behavior. Supported values: 1.0, 1.1, 1.2.",
"default": 1.2
}
},
"type": "object",
"required": [
"classToSchema"
],
"title": "SplitClassifyStandardizeStep"
},
"SplitMode": {
"type": "string",
"enum": [
"auto",
"all",
"never"
],
"title": "SplitMode"
},
"SplitStandardizeStep": {
"properties": {
"schemaIds": {
"items": {
"type": "string"
},
"type": "array",
"title": "Schemaids",
"description": "Optional list of schema IDs to standardize each resulting sub-document. If omitted or empty, only the split operation is performed."
},
"stdVersion": {
"$ref": "#/$defs/StdVersion",
"title": "Stdversion",
"description": "The version of the standardization engine. Supported values: [2.0, 2.1, 2.2, 2.3, 3.0, 3.1, 3.2]. This is the only version field you need to set.",
"default": 3.2
},
"stdReleaseVersion": {
"$ref": "#/$defs/StdReleaseVersion",
"description": "Deprecated - set `stdVersion` instead and this will be inferred automatically (e.g. `stdVersion=3.0` infers release 3). Kept for backwards compatibility. Supported values: [1, 2, 3].",
"default": 2,
"deprecated": true
},
"guidelines": {
"type": "string",
"title": "Guidelines",
"description": "Guidelines for the AI on how to standardize the documents. If omitted, use the schema's guidelines."
},
"useMetadata": {
"type": "boolean",
"title": "Use Metadata",
"description": "Whether to use metadata during standardization.",
"default": false
},
"citations": {
"type": "boolean",
"title": "Citations",
"description": "V3 only. If true, every extracted value is cited to its place on the page (bounding box + confidence in fieldMetadata) and a Review object is created per standardization. Runs at standard effort (effortLevel is ignored) and costs 1 extra credits per page.",
"default": false
},
"displayMode": {
"$ref": "#/$defs/DisplayMode",
"title": "Displaymode",
"description": "The display mode of the standardization. For V1, this is called `standardizationMode`. The options are: `auto`, `spatial`, `sections`.",
"default": "auto"
},
"splitMode": {
"$ref": "#/$defs/SplitMode",
"title": "Splitmode",
"description": "The split mode of the standardization. The options are: `auto`, `never`, `all`.",
"default": "auto"
},
"effortLevel": {
"$ref": "#/$defs/EffortLevel",
"title": "Effortlevel",
"description": "The effort level of the standardization. The options are: `standard`, `high`.",
"default": "standard"
},
"schemaToEffort": {
"additionalProperties": {
"$ref": "#/$defs/EffortLevel"
},
"type": "object",
"title": "Schematoeffort",
"description": "Optional per-schema effort override, keyed by schema ID. Keys must appear in `schemaIds`. Any schema not listed here runs at `effortLevel`. Use this when one schema needs a heavier read than the rest - e.g. a dense price-matrix schema at `high` while simpler schemas stay at `standard`."
},
"standardizeTimeout": {
"type": "integer",
"title": "Standardizetimeout",
"description": "The timeout in seconds for the standardization operation for webhook error reporting"
},
"pages": {
"items": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "array",
"title": "Pages",
"description": "Optional per-schema page restriction, aligned with `schemaIds` by index. Each entry is either `null` (standardize the full document against that schema) or a non-empty list of zero indexed page numbers with no duplicates. When splitting creates sub-documents, each list is applied separately to every sub-document, not to the original uploaded document. For example, `[[0]]` selects the first page of every sub-document. If splitting creates no sub-documents, each list is applied to the original document. For XLS/XLSX files, each number then selects a worksheet by its zero indexed position. Page targeting is ignored for CSV, TXT, XML, and JSON files, which are standardized in full. If provided, length must equal `len(schemaIds)`. If omitted, every schema standardizes the full document passed from the split step. Out-of-range pages are silently filtered out at execution time."
},
"splitInstructions": {
"type": "string",
"title": "Splitinstructions",
"description": "Optional instructions that control how the document is split before standardization."
},
"splitDatasetSuffix": {
"type": "string",
"title": "Splitdatasetsuffix",
"description": "Suffix appended to the dataset provided during upload when assigning sub-documents. If the original document has no dataset, this suffix is used as the entire dataset name."
},
"splitFilenamePrefix": {
"type": "string",
"title": "Splitfilenameprefix",
"description": "Filename prefix to apply to each generated sub-document during the split operation."
},
"splitDisplayMode": {
"$ref": "#/$defs/DisplayMode",
"title": "Splitdisplaymode",
"description": "Display mode to use when running the split operation. The options mirror the split endpoint: `auto`, `spatial`, `sections`, `image`.",
"default": "auto"
},
"splitVersion": {
"$ref": "#/$defs/SplitVersion",
"description": "Version of the split behavior. Supported values: 1.0, 1.1, 1.2.",
"default": 1.2
}
},
"type": "object",
"title": "SplitStandardizeStep"
},
"SplitVersion": {
"type": "number",
"enum": [
1,
1.1,
1.2
],
"title": "SplitVersion"
},
"StandardizeReviewStep": {
"properties": {
"schemaIds": {
"items": {
"type": "string"
},
"type": "array",
"title": "Schemaids",
"description": "The IDs of all the schemas to standardize the document into."
},
"stdVersion": {
"$ref": "#/$defs/StdVersion",
"title": "Stdversion",
"description": "The version of the standardization engine. Supported values: [2.0, 2.1, 2.2, 2.3, 3.0, 3.1, 3.2]. This is the only version field you need to set.",
"default": 3.2
},
"stdReleaseVersion": {
"$ref": "#/$defs/StdReleaseVersion",
"description": "Deprecated - set `stdVersion` instead and this will be inferred automatically (e.g. `stdVersion=3.0` infers release 3). Kept for backwards compatibility. Supported values: [1, 2, 3].",
"default": 2,
"deprecated": true
},
"guidelines": {
"type": "string",
"title": "Guidelines",
"description": "Guidelines for the AI on how to standardize the documents. If omitted, use the schema's guidelines."
},
"useMetadata": {
"type": "boolean",
"title": "Use Metadata",
"description": "Whether to use metadata during standardization.",
"default": false
},
"citations": {
"type": "boolean",
"title": "Citations",
"description": "V3 only. If true, every extracted value is cited to its place on the page (bounding box + confidence in fieldMetadata) and a Review object is created per standardization. Runs at standard effort (effortLevel is ignored) and costs 1 extra credits per page.",
"default": false
},
"displayMode": {
"$ref": "#/$defs/DisplayMode",
"title": "Displaymode",
"description": "The display mode of the standardization. For V1, this is called `standardizationMode`. The options are: `auto`, `spatial`, `sections`.",
"default": "auto"
},
"splitMode": {
"$ref": "#/$defs/SplitMode",
"title": "Splitmode",
"description": "The split mode of the standardization. The options are: `auto`, `never`, `all`.",
"default": "auto"
},
"effortLevel": {
"$ref": "#/$defs/EffortLevel",
"title": "Effortlevel",
"description": "The effort level of the standardization. The options are: `standard`, `high`.",
"default": "standard"
},
"schemaToEffort": {
# --- truncated at 32 KB (38 KB total) ---
# Full source: https://artifacts.apis.io/docupanda/json-schema/docupanda-workflow-on-submit-document-request-schema.json
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/docupanda-workflow-on-submit-document-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.