pdf_evidenceFocused PDF evidence operations. Pure-Rust supports inspect, bounded page rendering/crops, opt-in bounded command-provider OCR, and region analysis via command, HTTP URL, or ollama/openai-compatible/lmstudio/llamacpp presets.Input schema{
"$defs": {
"PageNumber": {
"format": "uint32",
"minimum": 1,
"type": "integer"
},
"PageSpecifier": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/PageNumber"
},
"type": "array"
},
{
"minLength": 1,
"type": "string"
}
]
},
"PdfEvidenceOperation": {
"enum": [
"inspect",
"render_page",
"extract_regions",
"ocr_pages",
"analyze_regions"
],
"type": "string"
},
"PdfEvidenceRegion": {
"properties": {
"bounding_box": {
"$ref": "#/$defs/RegionBoundingBox"
},
"id": {
"type": [
"string",
"null"
]
},
"padding": {
"format": "double",
"maximum": 200,
"minimum": 0,
"type": [
"number",
"null"
]
},
"page": {
"format": "uint32",
"minimum": 1,
"type": "integer"
}
},
"required": [
"page",
"bounding_box"
],
"type": "object"
},
"PdfEvidenceSource": {
"properties": {
"pages": {
"anyOf": [
{
"$ref": "#/$defs/PageSpecifier"
},
{
"type": "null"
}
]
},
"path": {
"description": "Path to the local PDF file. Provide exactly one of path or url (not both).",
"minLength": 1,
"type": [
"string",
"null"
]
},
"regions": {
"items": {
"$ref": "#/$defs/PdfEvidenceRegion"
},
"type": [
"array",
"null"
]
},
"url": {
"description": "URL of the PDF file. Provide exactly one of path or url (not both).",
"minLength": 1,
"type": [
"string",
"null"
]
}
},
"type": "object"
},
"RegionBoundingBox": {
"properties": {
"bottom": {
"format": "double",
"minimum": 0,
"type": "number"
},
"left": {
"format": "double",
"minimum": 0,
"type": "number"
},
"right": {
"format": "double",
"minimum": 0,
"type": "number"
},
"top": {
"format": "double",
"minimum": 0,
"type": "number"
}
},
"required": [
"left",
"bottom",
"right",
"top"
],
"type": "object"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"include_image": {
"type": [
"boolean",
"null"
]
},
"include_metadata": {
"type": [
"boolean",
"null"
]
},
"languages": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"max_output_chars": {
"format": "uint32",
"maximum": 1000000,
"minimum": 1000,
"type": [
"integer",
"null"
]
},
"max_pages": {
"format": "uint32",
"maximum": 20,
"minimum": 1,
"type": [
"integer",
"null"
]
},
"max_pixels_per_page": {
"format": "uint64",
"maximum": 64000000,
"minimum": 10000,
"type": [
"integer",
"null"
]
},
"max_regions": {
"format": "uint32",
"maximum": 100,
"minimum": 1,
"type": [
"integer",
"null"
]
},
"operation": {
"$ref": "#/$defs/PdfEvidenceOperation"
},
"sample_pages": {
"format": "uint32",
"maximum": 20,
"minimum": 1,
"type": [
"integer",
"null"
]
},
"scale": {
"format": "double",
"maximum": 4,
"minimum": 0.25,
"type": [
"number",
"null"
]
},
"sources": {
"items": {
"$ref": "#/$defs/PdfEvidenceSource"
},
"type": "array"
},
"timeout_ms": {
"format": "uint32",
"maximum": 300000,
"minimum": 1000,
"type": [
"integer",
"null"
]
}
},
"required": [
"operation",
"sources"
],
"type": "object"
} | — | | — |
read_pdfPrimary PDF reader. Pure-Rust default: selectable text, markdown, chunks, tables, search, and evidence-oriented twin fields under capability-first semantic compatibility (ADR-0005).Input schema{
"$defs": {
"PageNumber": {
"format": "uint32",
"minimum": 1,
"type": "integer"
},
"PageSpecifier": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/PageNumber"
},
"type": "array"
},
{
"minLength": 1,
"type": "string"
}
]
},
"PdfSource": {
"properties": {
"pages": {
"anyOf": [
{
"$ref": "#/$defs/PageSpecifier"
},
{
"type": "null"
}
]
},
"path": {
"description": "Path to the local PDF file (absolute or relative to cwd). Provide exactly one of path or url (not both).",
"minLength": 1,
"type": [
"string",
"null"
]
},
"url": {
"description": "URL of the PDF file. Provide exactly one of path or url (not both).",
"minLength": 1,
"type": [
"string",
"null"
]
}
},
"type": "object"
},
"ReadPdfAutoDetail": {
"enum": [
"fast",
"balanced",
"full"
],
"type": "string"
},
"TrustReportRedaction": {
"enum": [
"standard",
"strict",
"off"
],
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"auto": {
"description": "Automatically choose high-value extraction options. Defaults to true only when no explicit include_* options are supplied.",
"type": [
"boolean",
"null"
]
},
"auto_detail": {
"anyOf": [
{
"$ref": "#/$defs/ReadPdfAutoDetail"
},
{
"type": "null"
}
],
"description": "Automatic extraction depth: fast | balanced | full."
},
"include_accessibility_report": {
"type": [
"boolean",
"null"
]
},
"include_annotations": {
"type": [
"boolean",
"null"
]
},
"include_attachments": {
"type": [
"boolean",
"null"
]
},
"include_chunks": {
"type": [
"boolean",
"null"
]
},
"include_document_ast": {
"type": [
"boolean",
"null"
]
},
"include_document_map": {
"type": [
"boolean",
"null"
]
},
"include_elements": {
"type": [
"boolean",
"null"
]
},
"include_form_fields": {
"type": [
"boolean",
"null"
]
},
"include_full_text": {
"type": [
"boolean",
"null"
]
},
"include_html": {
"type": [
"boolean",
"null"
]
},
"include_images": {
"type": [
"boolean",
"null"
]
},
"include_layout_diagnostics": {
"type": [
"boolean",
"null"
]
},
"include_markdown": {
"type": [
"boolean",
"null"
]
},
"include_metadata": {
"type": [
"boolean",
"null"
]
},
"include_ocr_text_layer": {
"type": [
"boolean",
"null"
]
},
"include_outline": {
"type": [
"boolean",
"null"
]
},
"include_page_count": {
"type": [
"boolean",
"null"
]
},
"include_page_geometry": {
"type": [
"boolean",
"null"
]
},
"include_page_labels": {
"type": [
"boolean",
"null"
]
},
"include_permissions": {
"type": [
"boolean",
"null"
]
},
"include_safety_findings": {
"type": [
"boolean",
"null"
]
},
"include_semantic_hints": {
"type": [
"boolean",
"null"
]
},
"include_structure_tree": {
"type": [
"boolean",
"null"
]
},
"include_tables": {
"type": [
"boolean",
"null"
]
},
"include_text_layer": {
"type": [
"boolean",
"null"
]
},
"include_trust_report": {
"type": [
"boolean",
"null"
]
},
"include_visual_enrichments": {
"type": [
"boolean",
"null"
]
},
"max_visual_enrichments": {
"format": "uint32",
"minimum": 1,
"type": [
"integer",
"null"
]
},
"sample_pages": {
"format": "uint32",
"maximum": 20,
"minimum": 1,
"type": [
"integer",
"null"
]
},
"sources": {
"items": {
"$ref": "#/$defs/PdfSource"
},
"type": "array"
},
"trust_report_redaction": {
"anyOf": [
{
"$ref": "#/$defs/TrustReportRedaction"
},
{
"type": "null"
}
]
}
},
"required": [
"sources"
],
"type": "object"
} | — | | — |
search_pdfSearches extracted PDF text with page, snippet, geometry, and provenance. Optional OCR uses the bounded command provider.Input schema{
"$defs": {
"PageNumber": {
"format": "uint32",
"minimum": 1,
"type": "integer"
},
"PageSpecifier": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/PageNumber"
},
"type": "array"
},
{
"minLength": 1,
"type": "string"
}
]
},
"PdfSource": {
"properties": {
"pages": {
"anyOf": [
{
"$ref": "#/$defs/PageSpecifier"
},
{
"type": "null"
}
]
},
"path": {
"description": "Path to the local PDF file (absolute or relative to cwd). Provide exactly one of path or url (not both).",
"minLength": 1,
"type": [
"string",
"null"
]
},
"url": {
"description": "URL of the PDF file. Provide exactly one of path or url (not both).",
"minLength": 1,
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"case_sensitive": {
"type": [
"boolean",
"null"
]
},
"context_chars": {
"format": "uint32",
"maximum": 1000,
"minimum": 0,
"type": [
"integer",
"null"
]
},
"include_ocr_text_layer": {
"type": [
"boolean",
"null"
]
},
"max_matches_per_source": {
"format": "uint32",
"maximum": 500,
"minimum": 1,
"type": [
"integer",
"null"
]
},
"max_pages": {
"format": "uint32",
"maximum": 1000,
"minimum": 1,
"type": [
"integer",
"null"
]
},
"prefer_speed": {
"description": "Prefer faster text-index search (omit match geometry; ignored when OCR is enabled).",
"type": [
"boolean",
"null"
]
},
"query": {
"description": "Literal text query to search for in extracted PDF text.",
"minLength": 1,
"type": "string"
},
"sources": {
"items": {
"$ref": "#/$defs/PdfSource"
},
"type": "array"
},
"whole_word": {
"type": [
"boolean",
"null"
]
}
},
"required": [
"sources",
"query",
"prefer_speed"
],
"type": "object"
} | — | | — |