This article is about the legacy ADE endpoint (
v1/tools/agentic-document-analysis). Use the current endpoints for all new projects.Copy
Ask AI
{
"$defs": {
"DocumentAnalysisChunk": {
"description": "An extracted chunk from the document",
"properties": {
"text": {
"description": "A Markdown representation of the chunk (except for tables, which are represented in HTML).",
"title": "Text",
"type": "string"
},
"grounding": {
"description": "The specific spatial location(s) of this chunk within the original document. A chunk can have multiple groundings, for example if it is a single paragraph split across two columns.",
"items": {
"$ref": "#/$defs/Grounding"
},
"title": "Grounding",
"type": "array"
},
"chunk_type": {
"$ref": "#/$defs/ChunkType",
"description": "The detected type of the chunk, matching its role within the document."
},
"chunk_id": {
"description": "A UUID for the chunk. This matches UUIDs in the HTML comments in the Markdown output.",
"title": "Chunk Id",
"type": "string"
},
"rotation_angle": {
"description": "The rotation angle applied to the chunk (in degrees).",
"title": "Rotation Angle",
"type": "number",
"default": 0
}
},
"required": [
"text",
"grounding",
"chunk_type",
"chunk_id"
],
"title": "DocumentAnalysisChunk",
"type": "object"
},
"Grounding": {
"description": "Grounding for a chunk, specifying the location within the original document",
"properties": {
"box": {
"$ref": "#/$defs/GroundingBox",
"description": "A bounding box (in relative coordinates) establishing the chunk's spatial location within the page."
},
"page": {
"description": "The chunk's 0-indexed page within the original document.",
"title": "Page",
"type": "integer"
}
},
"required": [
"box",
"page"
],
"title": "Grounding",
"type": "object"
},
"GroundingBox": {
"description": "Bounding box, expressed in relative coordinates (float from 0 to 1)",
"properties": {
"l": {
"description": "Left coordinate",
"title": "L",
"type": "number"
},
"t": {
"description": "Top coordinate",
"title": "T",
"type": "number"
},
"r": {
"description": "Right coordinate",
"title": "R",
"type": "number"
},
"b": {
"description": "Bottom coordinate",
"title": "B",
"type": "number"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "GroundingBox",
"type": "object"
},
"ChunkType": {
"description": "Type of the chunk, signifying its role within the document",
"enum": [
"logo",
"card",
"attestation",
"scan_code",
"form",
"table",
"figure",
"text",
"marginalia",
"title",
"page_header",
"page_footer",
"page_number",
"key_value"
],
"title": "ChunkType",
"type": "string"
},
"AgenticDocumentAnalysisBase": {
"description": "The main data object containing parsed document content",
"properties": {
"markdown": {
"description": "A Markdown representation of the document, potentially with HTML comments at the end of each chunk. Can be a single string or an array of strings (one per page).",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
],
"title": "Markdown"
},
"extracted_schema": {
"description": "The extracted data based on the fields_schema provided in the request. Only present if fields_schema was provided.",
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"title": "Extracted Schema"
},
"extraction_metadata": {
"description": "Metadata about the extracted fields, including chunk references and confidence scores. Only present if fields_schema was provided.",
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"title": "Extraction Metadata"
},
"chunks": {
"description": "List of chunks extracted from the document in reading order.",
"items": {
"$ref": "#/$defs/DocumentAnalysisChunk"
},
"title": "Chunks",
"type": "array"
}
},
"required": [
"markdown",
"chunks"
],
"title": "AgenticDocumentAnalysisBase",
"type": "object"
},
"AgenticDocAnalysisPageError": {
"description": "Error information for a page that failed to process",
"properties": {
"page_num": {
"description": "The page number that failed (0-indexed)",
"title": "Page Num",
"type": "integer"
},
"error": {
"description": "Error message describing what went wrong",
"title": "Error",
"type": "string"
},
"error_code": {
"description": "HTTP error code",
"title": "Error Code",
"type": "integer"
}
},
"required": [
"page_num",
"error",
"error_code"
],
"title": "AgenticDocAnalysisPageError",
"type": "object"
}
},
"properties": {
"data": {
"$ref": "#/$defs/AgenticDocumentAnalysisBase",
"description": "The main data object containing the parsed document"
},
"errors": {
"description": "List of errors that occurred during page processing. Pages with errors are excluded from the data object.",
"items": {
"$ref": "#/$defs/AgenticDocAnalysisPageError"
},
"title": "Errors",
"type": "array"
},
"extraction_error": {
"description": "Error message if field extraction failed. Only present if fields_schema was provided and extraction encountered an error.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Extraction Error"
},
"metadata": {
"description": "Additional metadata about the processing job",
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"title": "Metadata"
}
},
"required": [
"data"
],
"title": "AgenticDocAnalysisResponse",
"type": "object"
}
Grounding Information
When the legacy API parses a document, it breaks the content into chunks, which are discrete elements extracted from a document, like blocks of text or tables. Each chunk includes a grounding, which represents the location of the chunk in the document. The grounding includes:- the page number that the chunk is on
- the relative coordinates of the bounding box of the chunk
text chunk from the legacy API. The grounding array indicates that the text is on the first page (page 0), and the box object indicates the bounding box coordinates.
Copy
Ask AI
{
"text": "## INSURANCE COMPANY",
"grounding": [
{
"box": {
"l": 0.35,
"t": 0.22619999999999998,
"r": 0.565,
"b": 0.24033749999999998
},
"page": 0
}
],
"chunk_type": "text",
"chunk_id": "9475461e-0686-4b16-b503-ccec7d7f115c"
}