# Parsing ## Parse File `ParsingCreateResponse Parsing.Create(ParsingCreateParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v2/parse` Parse a file by file ID or URL. Provide either `file_id` (a previously uploaded file) or `source_url` (a publicly accessible URL). Configure parsing with options like `tier`, `target_pages`, and `lang`. ## Tiers - `fast` — rule-based, cheapest, no AI - `cost_effective` — balanced speed and quality - `agentic` — full AI-powered parsing - `agentic_plus` — premium AI with specialized features The job runs asynchronously. Poll `GET /parse/{job_id}` with `expand=text` or `expand=markdown` to retrieve results. ### Parameters - `ParsingCreateParams parameters` - `required Tier tier` Body param: Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced), 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with highest accuracy) - `"fast"Fast` - `"cost_effective"CostEffective` - `"agentic"Agentic` - `"agentic_plus"AgenticPlus` - `required Version version` Body param: Version for the selected tier. Use `latest`, or pin one of that tier's dated versions. Current `latest` by tier: - `fast`: `2026-06-15` - `cost_effective`: `2026-06-26` - `agentic`: `2026-07-15` - `agentic_plus`: `2026-07-08` Full list: `GET /api/v2/parse/versions`. - `"latest"Latest` - `"2026-07-15"2026_07_15` - `"2026-07-08"2026_07_08` - `"2026-06-26"2026_06_26` - `"2026-06-15"2026_06_15` - `string? organizationID` Query param - `string? projectID` Query param - `AgenticOptions? agenticOptions` Body param: Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus). These options customize how the AI processes and interprets document content. Only applicable when using non-fast tiers. - `string? CustomPrompt` Custom instructions for the AI parser. Use to guide extraction behavior, specify output formatting, or provide domain-specific context. Example: 'Extract financial tables with currency symbols. Format dates as YYYY-MM-DD.' - `string? clientName` Body param: Identifier for the client/application making the request. Used for analytics and debugging. Example: 'my-app-v2' - `string? configurationID` Body param: ID of a saved parse configuration. When set, `tier` and `version` default to the saved configuration's values — omit them or pass `'configured'`. - `CropBox cropBox` Body param: Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges - `Double? Bottom` Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded - `Double? Left` Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded - `Double? Right` Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded - `Double? Top` Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded - `Boolean? disableCache` Body param: Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results - `JsonElement? fastOptions` Body param: Options for fast tier parsing (rule-based, no AI). Fast tier uses deterministic algorithms for text extraction without AI enhancement. It's the fastest and most cost-effective option, best suited for simple documents with standard layouts. Currently has no configurable options but reserved for future expansion. - `string? fileID` Body param: ID of an existing file in the project to parse. Mutually exclusive with source_url - `string? httpProxy` Body param: HTTP/HTTPS proxy for fetching source_url. Ignored if using file_id - `InputOptions inputOptions` Body param: Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type - `Html Html` HTML/web page parsing options (applies to .html, .htm files) - `Boolean? MakeAllElementsVisible` Force all HTML elements to be visible by overriding CSS display/visibility properties. Useful for parsing pages with hidden content or collapsed sections - `Boolean? RemoveFixedElements` Remove fixed-position elements (headers, footers, floating buttons) that appear on every page render - `Boolean? RemoveNavigationElements` Remove navigation elements (nav bars, sidebars, menus) to focus on main content - `Image Image` Image parsing options (applies to .jpg, .jpeg, .png, .webp files) - `Boolean? CameraPhotoCorrection` Detect documents photographed with a camera (e.g. phone scans of receipts or forms), then crop, perspective-correct, and flatten uneven lighting and shadows before parsing. Supports JPEG, PNG, WebP, and HEIC/HEIF inputs. Improves results when the document is tilted or surrounded by background. Images that already look like clean scans are left untouched - `JsonElement Pdf` PDF-specific parsing options (applies to .pdf files) - `Presentation Presentation` Presentation parsing options (applies to .pptx, .ppt, .odp, .key files) - `Boolean? OutOfBoundsContent` Extract content positioned outside the visible slide area. Some presentations have hidden notes or content that extends beyond slide boundaries - `Boolean? SkipEmbeddedData` Skip extraction of embedded chart data tables. When true, only the visual representation of charts is captured, not the underlying data - `Spreadsheet Spreadsheet` Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files) - `Boolean? DetectSubTablesInSheets` Detect and extract multiple tables within a single sheet. Useful when spreadsheets contain several data regions separated by blank rows/columns - `Boolean? ForceFormulaComputationInSheets` Compute formula results instead of extracting formula text. Use when you need calculated values rather than formula definitions - `Boolean? IncludeHiddenSheets` Parse hidden sheets in addition to visible ones. By default, hidden sheets are skipped - `OutputOptions outputOptions` Body param: Output formatting options for markdown, text, and extracted images - `IReadOnlyList AdditionalOutputs` Optional additional output artifacts to save alongside the primary parse output. Each value opts in to generating and persisting one extra file; the empty list (default) saves none. The three accepted values are: 'stripped_md' — per-page markdown stripped of formatting (links, bold/italic, images, HTML), saved as JSON for full-text-search indexing; fetch via `expand=stripped_markdown_content_metadata`. 'concatenated_stripped_txt' — all stripped pages concatenated into a single plain-text file with `\n\n---\n\n` between pages, useful for feeding the document into search or embedding pipelines as one blob; fetch via `expand=concatenated_stripped_markdown_content_metadata`. 'word_bbox' — raw word-level bounding boxes (one JSON object per word, with page number and x/y/w/h coordinates) saved as JSONL, useful for highlighting or grounding extracted answers back to the source document; fetch via `expand=raw_words_content_metadata`. - `Boolean? ExtractPrintedPageNumber` Extract the printed page number as it appears in the document (e.g., 'Page 5 of 10', 'v', 'A-3'). Useful for referencing original page numbers - `IReadOnlyList GranularBboxes` Bounding-box granularity levels to compute for the parse. 'word' computes one bounding box per detected word; 'line' computes one per text line; 'cell' computes one per table cell. Multiple levels can be requested. Empty list (default) disables granular bboxes — only item-level layout boxes are returned on the result. When set, the computed boxes are not inlined on the result items; they are written to a separate `grounded_items` sidecar (JSONL, one row per page) and exposed as `result_content_metadata.grounded_items` (a presigned download URL) on the parse result. Each row matches the `GroundedJsonItem` shape. - `"cell"Cell` - `"line"Line` - `"word"Word` - `IReadOnlyList ImagesToSave` Image categories to extract and save. Options: 'screenshot' (full page renders useful for visual QA), 'embedded' (images found within the document), 'layout' (cropped regions from layout detection like figures and diagrams). Empty list saves no images - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Markdown Markdown` Markdown formatting options including table styles and link annotations - `Boolean? AnnotateLinks` Add link annotations to markdown output in the format [text](url). When false, only the link text is included - `Boolean? InlineImages` Embed images directly in markdown as base64 data URIs instead of extracting them as separate files. Useful for self-contained markdown output - `Tables Tables` Table formatting options including markdown vs HTML format and merging behavior - `Boolean? CompactMarkdownTables` Remove extra whitespace padding in markdown table cells for more compact output - `string? MarkdownTableMultilineSeparator` Separator string for multiline cell content in markdown tables. Example: '
' to preserve line breaks, ' ' to join with spaces - `Boolean? MergeContinuedTables` Automatically merge tables that span multiple pages into a single table. The merged table appears on the first page with merged_from_pages metadata - `Boolean? OutputTablesAsMarkdown` Output tables as markdown pipe tables instead of HTML tags. Markdown tables are simpler but cannot represent complex structures like merged cells - `SpatialText SpatialText` Spatial text output options for preserving document layout structure - `Boolean? DoNotUnrollColumns` Keep multi-column layouts intact instead of linearizing columns into sequential text. Automatically enabled for non-fast tiers - `Boolean? PreserveLayoutAlignmentAcrossPages` Maintain consistent text column alignment across page boundaries. Automatically enabled for document-level parsing modes - `Boolean? PreserveVerySmallText` Include text below the normal size threshold. Useful for footnotes, watermarks, or fine print that might otherwise be filtered out - `TablesAsSpreadsheet TablesAsSpreadsheet` Options for exporting tables as XLSX spreadsheets - `Boolean? Enable` Whether this option is enabled - `Boolean GuessSheetName` Automatically generate descriptive sheet names from table context (headers, surrounding text) instead of using generic names like 'Table_1' - `PageRanges pageRanges` Body param: Page selection: limit total pages or specify exact pages to process - `Long? MaxPages` Maximum number of pages to process. Pages are processed in order starting from page 1. If both max_pages and target_pages are set, target_pages takes precedence - `string? TargetPages` Comma-separated list of specific pages to process using 1-based indexing. Supports individual pages and ranges. Examples: '1,3,5' (pages 1, 3, 5), '1-5' (pages 1 through 5 inclusive), '1,3,5-8,10' (pages 1, 3, 5-8, and 10). Pages are sorted and deduplicated automatically. Duplicate pages cause an error - `ProcessingControl processingControl` Body param: Job execution controls including timeouts and failure thresholds - `JobFailureConditions JobFailureConditions` Quality thresholds that determine when a job should fail vs complete with partial results - `Double? AllowedPageFailureRatio` Maximum ratio of pages allowed to fail before the job fails (0-1). Example: 0.1 means job fails if more than 10% of pages fail. Default is 0.05 (5%) - `Boolean? FailOnBuggyFont` Fail the job if a problematic font is detected that may cause incorrect text extraction. Buggy fonts can produce garbled or missing characters - `Boolean? FailOnImageExtractionError` Fail the entire job if any embedded image cannot be extracted. By default, image extraction errors are logged but don't fail the job - `Boolean? FailOnImageOcrError` Fail the entire job if OCR fails on any image. By default, OCR errors result in empty text for that image - `Boolean? FailOnMarkdownReconstructionError` Fail the entire job if markdown cannot be reconstructed for any page. By default, failed pages use fallback text extraction - `Timeouts Timeouts` Timeout settings for job execution. Increase for large or complex documents - `Long? BaseInSeconds` Base timeout for the job in seconds (max 7200 = 2 hours). This is the minimum time allowed regardless of document size - `Long? ExtraTimePerPageInSeconds` Additional timeout per page in seconds (max 300 = 5 minutes). Total timeout = base + (this value × page count) - `ProcessingOptions processingOptions` Body param: Document processing options including OCR, table extraction, and chart parsing - `Boolean? AggressiveTableExtraction` Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables - `IReadOnlyList? AutoModeConfiguration` Conditional processing rules that apply different parsing options based on page content, document structure, or filename patterns. Each entry defines trigger conditions and the parsing configuration to apply when triggered - `required ParsingConf ParsingConf` Parsing configuration to apply when trigger conditions are met - `Boolean? AdaptiveLongTable` Whether to use adaptive long table handling - `Boolean? AggressiveTableExtraction` Whether to use aggressive table extraction - `CropBox? CropBox` Crop box options for auto mode parsing configuration. - `Double? Bottom` Bottom boundary of crop box as ratio (0-1) - `Double? Left` Left boundary of crop box as ratio (0-1) - `Double? Right` Right boundary of crop box as ratio (0-1) - `Double? Top` Top boundary of crop box as ratio (0-1) - `string? CustomPrompt` Custom AI instructions for matched pages. Overrides the base custom_prompt - `Boolean? ExtractLayout` Whether to extract layout information - `Boolean? HighResOcr` Whether to use high resolution OCR - `Ignore? Ignore` Ignore options for auto mode parsing configuration. - `Boolean? IgnoreDiagonalText` Whether to ignore diagonal text in the document - `Boolean? IgnoreHiddenText` Whether to ignore hidden text in the document - `string? Language` Primary language of the document - `Boolean? OutlinedTableExtraction` Whether to use outlined table extraction - `Presentation? Presentation` Presentation-specific options for auto mode parsing configuration. - `Boolean? OutOfBoundsContent` Extract out of bounds content in presentation slides - `Boolean? SkipEmbeddedData` Skip extraction of embedded data for charts in presentation slides - `SpatialText? SpatialText` Spatial text options for auto mode parsing configuration. - `Boolean? DoNotUnrollColumns` Keep column structure intact without unrolling - `Boolean? PreserveLayoutAlignmentAcrossPages` Preserve text alignment across page boundaries - `Boolean? PreserveVerySmallText` Include very small text in spatial output - `SpecializedChartParsing? SpecializedChartParsing` Enable specialized chart parsing with the specified mode - `"agentic"Agentic` - `"agentic_plus"AgenticPlus` - `"efficient"Efficient` - `Tier? Tier` Override the parsing tier for matched pages. Must be paired with version - `"agentic"Agentic` - `"agentic_plus"AgenticPlus` - `"cost_effective"CostEffective` - `"fast"Fast` - `Version? Version` Version for the override tier. Required when `tier` is set. Use `latest`, or pin one of that tier's dated versions. Current `latest` by tier: - `fast`: `2026-06-15` - `cost_effective`: `2026-06-26` - `agentic`: `2026-07-15` - `agentic_plus`: `2026-07-08` Full list: `GET /api/v2/parse/versions`. - `"latest"Latest` - `"2026-07-15"2026_07_15` - `"2026-07-08"2026_07_08` - `"2026-06-26"2026_06_26` - `"2026-06-15"2026_06_15` - `string? FilenameMatchGlob` Single glob pattern to match against filename - `IReadOnlyList? FilenameMatchGlobList` List of glob patterns to match against filename - `string? FilenameRegexp` Regex pattern to match against filename - `string? FilenameRegexpMode` Regex mode flags (e.g., 'i' for case-insensitive) - `Boolean? FullPageImageInPage` Trigger if page contains a full-page image (scanned page detection) - `FullPageImageInPageThreshold? FullPageImageInPageThreshold` Threshold for full page image detection (0.0-1.0, default 0.8) - `Double` - `string` - `Boolean? ImageInPage` Trigger if page contains non-screenshot images - `string? LayoutElementInPage` Trigger if page contains this layout element type - `LayoutElementInPageConfidenceThreshold? LayoutElementInPageConfidenceThreshold` Confidence threshold for layout element detection - `Double` - `string` - `PageContainsAtLeastNCharts? PageContainsAtLeastNCharts` Trigger if page has more than N charts - `Long` - `string` - `PageContainsAtLeastNImages? PageContainsAtLeastNImages` Trigger if page has more than N images - `Long` - `string` - `PageContainsAtLeastNLayoutElements? PageContainsAtLeastNLayoutElements` Trigger if page has more than N layout elements - `Long` - `string` - `PageContainsAtLeastNLines? PageContainsAtLeastNLines` Trigger if page has more than N lines - `Long` - `string` - `PageContainsAtLeastNLinks? PageContainsAtLeastNLinks` Trigger if page has more than N links - `Long` - `string` - `PageContainsAtLeastNNumbers? PageContainsAtLeastNNumbers` Trigger if page has more than N numeric words - `Long` - `string` - `PageContainsAtLeastNPercentNumbers? PageContainsAtLeastNPercentNumbers` Trigger if page has more than N% numeric words - `Long` - `string` - `PageContainsAtLeastNTables? PageContainsAtLeastNTables` Trigger if page has more than N tables - `Long` - `string` - `PageContainsAtLeastNWords? PageContainsAtLeastNWords` Trigger if page has more than N words - `Long` - `string` - `PageContainsAtMostNCharts? PageContainsAtMostNCharts` Trigger if page has fewer than N charts - `Long` - `string` - `PageContainsAtMostNImages? PageContainsAtMostNImages` Trigger if page has fewer than N images - `Long` - `string` - `PageContainsAtMostNLayoutElements? PageContainsAtMostNLayoutElements` Trigger if page has fewer than N layout elements - `Long` - `string` - `PageContainsAtMostNLines? PageContainsAtMostNLines` Trigger if page has fewer than N lines - `Long` - `string` - `PageContainsAtMostNLinks? PageContainsAtMostNLinks` Trigger if page has fewer than N links - `Long` - `string` - `PageContainsAtMostNNumbers? PageContainsAtMostNNumbers` Trigger if page has fewer than N numeric words - `Long` - `string` - `PageContainsAtMostNPercentNumbers? PageContainsAtMostNPercentNumbers` Trigger if page has fewer than N% numeric words - `Long` - `string` - `PageContainsAtMostNTables? PageContainsAtMostNTables` Trigger if page has fewer than N tables - `Long` - `string` - `PageContainsAtMostNWords? PageContainsAtMostNWords` Trigger if page has fewer than N words - `Long` - `string` - `PageLongerThanNChars? PageLongerThanNChars` Trigger if page has more than N characters - `Long` - `string` - `Boolean? PageMdError` Trigger on pages with markdown extraction errors - `PageShorterThanNChars? PageShorterThanNChars` Trigger if page has fewer than N characters - `Long` - `string` - `string? RegexpInPage` Regex pattern to match in page content - `string? RegexpInPageMode` Regex mode flags for regexp_in_page - `Boolean? TableInPage` Trigger if page contains a table - `string? TextInPage` Trigger if page text/markdown contains this string - `string? TriggerMode` How to combine multiple trigger conditions: 'and' (all conditions must match, this is the default) or 'or' (any single condition can trigger) - `ConfidenceScoreEffort? ConfidenceScoreEffort` Confidence scoring effort. Omit for standard scoring. 'high': more accurate assessment of the parsing quality of every page, plus a document-level score in the result metadata; costs an additional 5 credits per page - `"high"High` - `CostOptimizer? CostOptimizer` Cost optimizer configuration for reducing parsing costs on simpler pages. When enabled, the parser analyzes each page and routes simpler pages to faster, cheaper processing while preserving quality for complex pages. Only works with 'agentic' or 'agentic_plus' tiers. - `Boolean? Enable` Enable cost-optimized parsing. Routes simpler pages to faster processing while complex pages use full AI analysis. May reduce speed on some documents. IMPORTANT: Only available with 'agentic' or 'agentic_plus' tiers - `Boolean? DisableHeuristics` Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results - `Forms? Forms` Beta: set to 'enrich' to run an additional AI form-analysis pass on pages detected as forms, producing a structured tree of the form's sections, fields, and fillable grids. Retrieve the result with expand=forms. 'default' (the default) applies standard parsing with no extra pass. Not available on the fast tier - `"default"Default` - `"enrich"Enrich` - `Ignore Ignore` Options for ignoring specific text types (diagonal, hidden, text in images) - `Boolean? IgnoreDiagonalText` Skip text rotated at an angle (not horizontal/vertical). Useful for ignoring watermarks or decorative angled text - `Boolean? IgnoreHiddenText` Skip text marked as hidden in the document structure. Some PDFs contain invisible text layers used for accessibility or search indexing - `Boolean? IgnoreTextInImage` Skip OCR text extraction from embedded images. Use when images contain irrelevant text (watermarks, logos) that shouldn't be in the output - `OcrParameters OcrParameters` OCR configuration including language detection settings - `IReadOnlyList? Languages` Languages to use for OCR text recognition. Specify multiple languages if document contains mixed-language content. Order matters - put primary language first. Example: ['en', 'es'] for English with Spanish - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `SpecializedChartParsing? SpecializedChartParsing` Enable AI-powered chart analysis. Modes: 'efficient' (fast, lower cost), 'agentic' (balanced), 'agentic_plus' (highest accuracy). Automatically enables extract_layout and precise_bounding_box when set - `"agentic"Agentic` - `"agentic_plus"AgenticPlus` - `"efficient"Efficient` - `string? sourceUrl` Body param: Public URL of the document to parse. Mutually exclusive with file_id - `IReadOnlyDictionary? userMetadata` Body param: Arbitrary key/value tags to attach to this job. Returned when retrieving the job. Not searchable. Limits apply to the number of entries and the length of keys and values; oversized metadata is rejected. - `IReadOnlyList? webhookConfigurationIds` Body param: IDs of saved webhook configurations to notify for this job. - `IReadOnlyList webhookConfigurations` Body param: Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services - `IReadOnlyList? WebhookEvents` Events that trigger this webhook. Options: 'parse.success' (job completed), 'parse.error' (job failed), 'parse.partial_success' (some pages failed), 'parse.pending', 'parse.running', 'parse.cancelled'. If not specified, webhook fires for all events - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers to include in webhook requests. Use for authentication tokens or custom routing. Example: {'Authorization': 'Bearer xyz'} - `WebhookOutputFormat? WebhookOutputFormat` Format of the webhook payload body. 'string' (default) sends the payload as a JSON-encoded string; 'json' sends it as a JSON object. - `"json"Json` - `"string"String` - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` HTTPS URL to receive webhook POST requests. Must be publicly accessible ### Returns - `class ParsingCreateResponse:` A parse job. - `required string ID` Unique parse job identifier - `required string ProjectID` Project this job belongs to - `required Status Status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` - `DateTimeOffset? CreatedAt` Creation datetime - `string? ErrorMessage` Error details when status is FAILED - `string? Name` Optional display name for this parse job - `string? Tier` Parsing tier used for this job - `DateTimeOffset? UpdatedAt` Update datetime - `IReadOnlyDictionary? UserMetadata` Key/value tags associated with this job. ### Example ```csharp ParsingCreateParams parameters = new() { Tier = Tier.Fast, Version = Version.Latest, }; var parsing = await client.Parsing.Create(parameters); Console.WriteLine(parsing); ``` #### Response ```json { "id": "pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "CANCELLED", "created_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "name": "Q4 Financial Report", "tier": "fast", "updated_at": "2019-12-27T18:11:19.117Z", "user_metadata": { "owner": "jerry", "team": "research" } } ``` ## Get Parse Job `ParsingGetResponse Parsing.Get(ParsingGetParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v2/parse/{job_id}` Retrieve a parse job with optional expanded content. By default returns job metadata only. Use `expand` to include parsed content: - `text` — plain text output - `markdown` — markdown output - `items` — structured page-by-page output - `job_metadata` — usage and processing details Content metadata fields (e.g. `text_content_metadata`) return presigned URLs for downloading large results. ### Parameters - `ParsingGetParams parameters` - `required string jobID` - `IReadOnlyList expand` Fields to include: text, markdown, items, metadata, forms, job_metadata, text_content_metadata, markdown_content_metadata, items_content_metadata, metadata_content_metadata, forms_content_metadata, raw_words_content_metadata, xlsx_content_metadata, output_pdf_content_metadata, images_content_metadata. Metadata fields include presigned URLs. - `string? imageFilenames` Filter to specific image filenames (optional). Example: image_0.png,image_1.jpg - `string? organizationID` - `string? projectID` ### Returns - `class ParsingGetResponse:` Parse result response with job status and optional content or metadata. The job field is always included. Other fields are included based on expand parameters. - `required Job Job` Parse job status and metadata - `required string ID` Unique parse job identifier - `required string ProjectID` Project this job belongs to - `required Status Status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` - `DateTimeOffset? CreatedAt` Creation datetime - `string? ErrorMessage` Error details when status is FAILED - `string? Name` Optional display name for this parse job - `string? Tier` Parsing tier used for this job - `DateTimeOffset? UpdatedAt` Update datetime - `IReadOnlyDictionary? UserMetadata` Key/value tags associated with this job. - `Forms? Forms` Per-page form analysis results (one entry per page). - `required IReadOnlyList Pages` List of form pages or failed page entries - `class FormsResultPage:` Forms found on one page. Pages without form content have an empty forms list. - `required IReadOnlyList
Forms` Forms detected on the page - `required IReadOnlyList Json` Structured representation: an ordered tree of sections, fields, and tables - `class FormField:` One labeled form entry: a text input, checkbox, select group, or signature line. - `required Field Field` Kind of entry: text (any free-text input), checkbox, single_select, multi_select, or signature - `"checkbox"Checkbox` - `"multi_select"MultiSelect` - `"signature"Signature` - `"single_select"SingleSelect` - `"text"Text` - `string? ID` Field number/letter printed on the form (e.g. '1a'), if any - `Boolean? IsEmpty` True for a printed-but-blank text field (mutually exclusive with value) - `string? Label` Printed field caption, if any - `Type Type` Form field node - `"field"Field` - `Value? Value` Entered content: verbatim text for text fields, or a boolean for checkbox (checked) and signature (signed). Absent on blank text fields and on select groups - `string` - `Boolean` - `IReadOnlyList? ValueItems` Options of a single_select/multi_select group (only on select fields) - `class FormField:` One labeled form entry: a text input, checkbox, select group, or signature line. - `class FormSection:` A grouping of form content, in the form's reading order. - `` - `string? ID` Identifier printed on the form (e.g. 'Part III'), if any - `string? Label` Printed section heading, if any - `Type Type` Form section node - `"section"Section` - `class FormTable:` A fillable grid printed on the form: repeating records or a row-by-column matrix. - `` - `string? ID` Identifier printed on the form, if any - `IReadOnlyList? Columns` Printed column headers in order, if any - `string? Label` Printed table caption, if any - `Type Type` Form table node - `"table"Table` - `class FormSection:` A grouping of form content, in the form's reading order. - `class FormTable:` A fillable grid printed on the form: repeating records or a row-by-column matrix. - `required FormListItem List` Flattened list representation of the same content - `required IReadOnlyList Items` Nested lines and sub-lists, in the form's reading order - `class FormListTextItem:` One line of a form's list representation. - `required string Md` Markdown representation of the line - `required string Value` Line content (e.g. '[1a] Wages: 29,513') - `Type Type` Text line - `"text"Text` - `class FormListItem:` The list representation of form content: nested lists of rendered field lines. - `required string Md` Markdown representation of this list - `required Boolean Ordered` Whether the list is ordered - `Type Type` List node - `"list"List` - `required Long PageNumber` Page number of the document - `JsonElement Success trueconstant` Success indicator - `class FailedFormsPage:` A page whose processing failed. - `required string Error` Error message describing the failure - `required Long PageNumber` Page number of the document - `JsonElement Success falseconstant` Failure indicator - `ImagesContentMetadata? ImagesContentMetadata` Metadata for all extracted images. - `required IReadOnlyList Images` List of image metadata with presigned URLs - `required string Filename` Image filename (e.g., 'image_0.png') - `required Long Index` Index of the image in the extraction order - `Bbox? Bbox` Bounding box for an image on its page. - `required Long H` Height of the bounding box - `required Long W` Width of the bounding box - `required Long X` X coordinate of the bounding box - `required Long Y` Y coordinate of the bounding box - `Category? Category` Image category: 'screenshot' (full page), 'embedded' (images in document), or 'layout' (cropped from layout detection) - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `string? ContentType` MIME type of the image - `string? PresignedUrl` Presigned URL to download the image - `Long? SizeBytes` Deprecated: always returns None. Will be removed in a future release. - `required Long TotalCount` Total number of extracted images - `Items? Items` Structured JSON result (if requested) - `required IReadOnlyList Pages` List of structured pages or failed page entries - `class StructuredResultPage:` - `required IReadOnlyList Items` List of structured items on the page - `class CodeItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Code content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `string? Language` Programming language identifier - `Type Type` Code block item type - `"code"Code` - `class FooterItem:` - `required IReadOnlyList Items` List of items within the footer - `class CodeItem:` - `class HeadingItem:` - `required Long Level` Heading level (1-6) - `required string Md` Markdown representation preserving formatting - `required string Value` Heading text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Heading item type - `"heading"Heading` - `class ImageItem:` - `required string Caption` Image caption - `required string Md` Markdown representation preserving formatting - `required string Url` URL to the image - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Image item type - `"image"Image` - `class LinkItem:` - `required string Md` Markdown representation preserving formatting - `required string Text` Display text of the link - `required string Url` URL of the link - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Link item type - `"link"Link` - `class ListItem:` - `required IReadOnlyList Items` List of nested text or list items - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Text item type - `"text"Text` - `class ListItem:` - `required string Md` Markdown representation preserving formatting - `required Boolean Ordered` Whether the list is ordered or unordered - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` List item type - `"list"List` - `class TableItem:` - `required string Csv` CSV representation of the table - `required string Html` HTML representation of the table - `required string Md` Markdown representation preserving formatting - `required IReadOnlyList> Rows` Table data as array of arrays (string, number, or null) - `string` - `Double` - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `IReadOnlyList? MergedFromPages` List of page numbers with tables that were merged into this table (e.g., [1, 2, 3, 4]) - `Long? MergedIntoPage` Populated when merged into another table. Page number where the full merged table begins (used on empty tables). - `IReadOnlyList? ParseConcerns` Quality concerns detected during table extraction, indicating the table may have issues - `required string Details` Human-readable details about the concern - `required string Type` Type of parse concern (e.g. header_value_type_mismatch, inconsistent_row_cell_count) - `Type Type` Table item type - `"table"Table` - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Page footer container - `"footer"Footer` - `class HeaderItem:` - `required IReadOnlyList Items` List of items within the header - `class CodeItem:` - `class HeadingItem:` - `class ImageItem:` - `class LinkItem:` - `class ListItem:` - `class TableItem:` - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Page header container - `"header"Header` - `class HeadingItem:` - `class ImageItem:` - `class LinkItem:` - `class ListItem:` - `class TableItem:` - `class TextItem:` - `required Double PageHeight` Height of the page in points - `required Long PageNumber` Page number of the document - `required Double PageWidth` Width of the page in points - `JsonElement Success trueconstant` Success indicator - `class FailedStructuredPage:` - `required string Error` Error message describing the failure - `required Long PageNumber` Page number of the document - `JsonElement Success falseconstant` Failure indicator - `IReadOnlyDictionary? JobMetadata` Job execution metadata (if requested) - `Markdown? Markdown` Markdown result (if requested) - `required IReadOnlyList Pages` List of markdown pages or failed page entries - `class MarkdownResultPage:` - `required string Markdown` Markdown content of the page - `required Long PageNumber` Page number of the document - `JsonElement Success trueconstant` Success indicator - `string? Footer` Footer of the page in markdown - `string? Header` Header of the page in markdown - `class FailedMarkdownPage:` - `required string Error` Error message describing the failure - `required Long PageNumber` Page number of the document - `JsonElement Success falseconstant` Failure indicator - `string? MarkdownFull` Full raw markdown content (if requested) - `Metadata? Metadata` Result containing metadata (page level and general) for the parsed document. - `required IReadOnlyList Pages` List of page metadata entries - `required Long PageNumber` Page number of the document - `Double? Confidence` Confidence score for the page parsing (0-1) - `Boolean? CostOptimized` Whether cost-optimized parsing was used for the page - `Long? OriginalOrientationAngle` Original orientation angle of the page in degrees - `string? PrintedPageNumber` Printed page number as it appears in the document - `string? SlideSectionName` Section name from presentation slides - `string? SpeakerNotes` Speaker notes from presentation slides - `Boolean? TriggeredAutoMode` Whether auto mode was triggered for the page - `IReadOnlyDictionary? RawParameters` - `IReadOnlyDictionary? ResultContentMetadata` Metadata including size, existence, and presigned URLs for result files - `required Long SizeBytes` Size of the result file in bytes - `Boolean Exists` Whether the result file exists in S3 - `string? PresignedUrl` Presigned URL to download the result file - `Text? Text` Plain text result (if requested) - `required IReadOnlyList Pages` List of text pages - `required Long PageNumber` Page number of the document - `required string Text` Plain text content of the page - `string? TextFull` Full raw text content (if requested) ### Example ```csharp ParsingGetParams parameters = new() { JobID = "job_id" }; var parsing = await client.Parsing.Get(parameters); Console.WriteLine(parsing); ``` #### Response ```json { "job": { "id": "pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "CANCELLED", "created_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "name": "Q4 Financial Report", "tier": "fast", "updated_at": "2019-12-27T18:11:19.117Z", "user_metadata": { "owner": "jerry", "team": "research" } }, "forms": { "pages": [ { "forms": [ { "json": [ { "field": "checkbox", "id": "id", "isEmpty": true, "label": "label", "type": "field", "value": "string", "valueItems": [ { "items": [ { "rows": [ [ "string" ] ], "id": "id", "columns": [ "string" ], "label": "label", "type": "table" } ], "id": "id", "label": "label", "type": "section" } ] } ], "list": { "items": [ { "md": "md", "value": "value", "type": "text" } ], "md": "md", "ordered": true, "type": "list" } } ], "page_number": 0, "success": true } ] }, "images_content_metadata": { "images": [ { "filename": "filename", "index": 0, "bbox": { "h": 0, "w": 0, "x": 0, "y": 0 }, "category": "embedded", "content_type": "content_type", "presigned_url": "presigned_url", "size_bytes": 0 } ], "total_count": 0 }, "items": { "pages": [ { "items": [ { "md": "md", "value": "value", "bbox": [ { "h": 0, "w": 0, "x": 0, "y": 0, "confidence": 0, "end_index": 0, "label": "label", "r": 0, "start_index": 0 } ], "language": "language", "type": "code" } ], "page_height": 0, "page_number": 0, "page_width": 0, "success": true } ] }, "job_metadata": { "foo": "bar" }, "markdown": { "pages": [ { "markdown": "markdown", "page_number": 0, "success": true, "footer": "footer", "header": "header" } ] }, "markdown_full": "markdown_full", "metadata": { "pages": [ { "page_number": 0, "confidence": 0, "cost_optimized": true, "original_orientation_angle": 0, "printed_page_number": "printed_page_number", "slide_section_name": "slide_section_name", "speaker_notes": "speaker_notes", "triggered_auto_mode": true } ] }, "raw_parameters": { "foo": "bar" }, "result_content_metadata": { "foo": { "size_bytes": 0, "exists": true, "presigned_url": "presigned_url" } }, "text": { "pages": [ { "page_number": 0, "text": "text" } ] }, "text_full": "text_full" } ``` ## List Parse Jobs `ParsingListPageResponse Parsing.List(ParsingListParams?parameters, CancellationTokencancellationToken = default)` **get** `/api/v2/parse` List parse jobs for the current project. Filter by `status` or creation date range. Results are paginated — use `page_token` from the response to fetch subsequent pages. ### Parameters - `ParsingListParams parameters` - `DateTimeOffset? createdAtOnOrAfter` Include items created at or after this timestamp (inclusive) - `DateTimeOffset? createdAtOnOrBefore` Include items created at or before this timestamp (inclusive) - `IReadOnlyList? jobIds` Filter by specific job IDs - `string? organizationID` - `Long? pageSize` Number of items per page - `string? pageToken` Token for pagination - `string? projectID` - `Status? status` Filter by job status (PENDING, RUNNING, COMPLETED, FAILED, CANCELLED) - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` ### Returns - `class ParsingListPageResponse:` Response schema for paginated parse job queries. - `required IReadOnlyList Items` The list of items. - `required string ID` Unique parse job identifier - `required string ProjectID` Project this job belongs to - `required Status Status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` - `DateTimeOffset? CreatedAt` Creation datetime - `string? ErrorMessage` Error details when status is FAILED - `string? Name` Optional display name for this parse job - `string? Tier` Parsing tier used for this job - `DateTimeOffset? UpdatedAt` Update datetime - `IReadOnlyDictionary? UserMetadata` Key/value tags associated with this job. - `string? NextPageToken` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `Long? TotalSize` The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. ### Example ```csharp ParsingListParams parameters = new(); var page = await client.Parsing.List(parameters); await foreach (var item in page.Paginate()) { Console.WriteLine(item); } ``` #### Response ```json { "items": [ { "id": "pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "CANCELLED", "created_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "name": "Q4 Financial Report", "tier": "fast", "updated_at": "2019-12-27T18:11:19.117Z", "user_metadata": { "owner": "jerry", "team": "research" } } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Domain Types ### B Box - `class BBox:` Bounding box with coordinates and optional metadata. - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text ### Code Item - `class CodeItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Code content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `string? Language` Programming language identifier - `Type Type` Code block item type - `"code"Code` ### Fail Page Mode - `enum FailPageMode:` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` ### Footer Item - `class FooterItem:` - `required IReadOnlyList Items` List of items within the footer - `class CodeItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Code content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `string? Language` Programming language identifier - `Type Type` Code block item type - `"code"Code` - `class HeadingItem:` - `required Long Level` Heading level (1-6) - `required string Md` Markdown representation preserving formatting - `required string Value` Heading text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Heading item type - `"heading"Heading` - `class ImageItem:` - `required string Caption` Image caption - `required string Md` Markdown representation preserving formatting - `required string Url` URL to the image - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Image item type - `"image"Image` - `class LinkItem:` - `required string Md` Markdown representation preserving formatting - `required string Text` Display text of the link - `required string Url` URL of the link - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Link item type - `"link"Link` - `class ListItem:` - `required IReadOnlyList Items` List of nested text or list items - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Text item type - `"text"Text` - `class ListItem:` - `required string Md` Markdown representation preserving formatting - `required Boolean Ordered` Whether the list is ordered or unordered - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` List item type - `"list"List` - `class TableItem:` - `required string Csv` CSV representation of the table - `required string Html` HTML representation of the table - `required string Md` Markdown representation preserving formatting - `required IReadOnlyList> Rows` Table data as array of arrays (string, number, or null) - `string` - `Double` - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `IReadOnlyList? MergedFromPages` List of page numbers with tables that were merged into this table (e.g., [1, 2, 3, 4]) - `Long? MergedIntoPage` Populated when merged into another table. Page number where the full merged table begins (used on empty tables). - `IReadOnlyList? ParseConcerns` Quality concerns detected during table extraction, indicating the table may have issues - `required string Details` Human-readable details about the concern - `required string Type` Type of parse concern (e.g. header_value_type_mismatch, inconsistent_row_cell_count) - `Type Type` Table item type - `"table"Table` - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Page footer container - `"footer"Footer` ### Form - `class Form:` One form detected on a page, in two representations of the same content. - `required IReadOnlyList Json` Structured representation: an ordered tree of sections, fields, and tables - `class FormField:` One labeled form entry: a text input, checkbox, select group, or signature line. - `required Field Field` Kind of entry: text (any free-text input), checkbox, single_select, multi_select, or signature - `"checkbox"Checkbox` - `"multi_select"MultiSelect` - `"signature"Signature` - `"single_select"SingleSelect` - `"text"Text` - `string? ID` Field number/letter printed on the form (e.g. '1a'), if any - `Boolean? IsEmpty` True for a printed-but-blank text field (mutually exclusive with value) - `string? Label` Printed field caption, if any - `Type Type` Form field node - `"field"Field` - `Value? Value` Entered content: verbatim text for text fields, or a boolean for checkbox (checked) and signature (signed). Absent on blank text fields and on select groups - `string` - `Boolean` - `IReadOnlyList? ValueItems` Options of a single_select/multi_select group (only on select fields) - `class FormField:` One labeled form entry: a text input, checkbox, select group, or signature line. - `class FormSection:` A grouping of form content, in the form's reading order. - `` - `string? ID` Identifier printed on the form (e.g. 'Part III'), if any - `string? Label` Printed section heading, if any - `Type Type` Form section node - `"section"Section` - `class FormTable:` A fillable grid printed on the form: repeating records or a row-by-column matrix. - `` - `string? ID` Identifier printed on the form, if any - `IReadOnlyList? Columns` Printed column headers in order, if any - `string? Label` Printed table caption, if any - `Type Type` Form table node - `"table"Table` - `class FormSection:` A grouping of form content, in the form's reading order. - `class FormTable:` A fillable grid printed on the form: repeating records or a row-by-column matrix. - `required FormListItem List` Flattened list representation of the same content - `required IReadOnlyList Items` Nested lines and sub-lists, in the form's reading order - `class FormListTextItem:` One line of a form's list representation. - `required string Md` Markdown representation of the line - `required string Value` Line content (e.g. '[1a] Wages: 29,513') - `Type Type` Text line - `"text"Text` - `class FormListItem:` The list representation of form content: nested lists of rendered field lines. - `required string Md` Markdown representation of this list - `required Boolean Ordered` Whether the list is ordered - `Type Type` List node - `"list"List` ### Form Field - `class FormField:` One labeled form entry: a text input, checkbox, select group, or signature line. - `required Field Field` Kind of entry: text (any free-text input), checkbox, single_select, multi_select, or signature - `"checkbox"Checkbox` - `"multi_select"MultiSelect` - `"signature"Signature` - `"single_select"SingleSelect` - `"text"Text` - `string? ID` Field number/letter printed on the form (e.g. '1a'), if any - `Boolean? IsEmpty` True for a printed-but-blank text field (mutually exclusive with value) - `string? Label` Printed field caption, if any - `Type Type` Form field node - `"field"Field` - `Value? Value` Entered content: verbatim text for text fields, or a boolean for checkbox (checked) and signature (signed). Absent on blank text fields and on select groups - `string` - `Boolean` - `IReadOnlyList? ValueItems` Options of a single_select/multi_select group (only on select fields) - `class FormField:` One labeled form entry: a text input, checkbox, select group, or signature line. - `class FormSection:` A grouping of form content, in the form's reading order. - `` - `string? ID` Identifier printed on the form (e.g. 'Part III'), if any - `string? Label` Printed section heading, if any - `Type Type` Form section node - `"section"Section` - `class FormTable:` A fillable grid printed on the form: repeating records or a row-by-column matrix. - `` - `string? ID` Identifier printed on the form, if any - `IReadOnlyList? Columns` Printed column headers in order, if any - `string? Label` Printed table caption, if any - `Type Type` Form table node - `"table"Table` ### Form List Item - `class FormListItem:` The list representation of form content: nested lists of rendered field lines. - `required IReadOnlyList Items` Nested lines and sub-lists, in the form's reading order - `class FormListTextItem:` One line of a form's list representation. - `required string Md` Markdown representation of the line - `required string Value` Line content (e.g. '[1a] Wages: 29,513') - `Type Type` Text line - `"text"Text` - `class FormListItem:` The list representation of form content: nested lists of rendered field lines. - `required string Md` Markdown representation of this list - `required Boolean Ordered` Whether the list is ordered - `Type Type` List node - `"list"List` ### Form List Text Item - `class FormListTextItem:` One line of a form's list representation. - `required string Md` Markdown representation of the line - `required string Value` Line content (e.g. '[1a] Wages: 29,513') - `Type Type` Text line - `"text"Text` ### Form Section - `class FormSection:` A grouping of form content, in the form's reading order. - `` - `string? ID` Identifier printed on the form (e.g. 'Part III'), if any - `string? Label` Printed section heading, if any - `Type Type` Form section node - `"section"Section` ### Form Table - `class FormTable:` A fillable grid printed on the form: repeating records or a row-by-column matrix. - `` - `string? ID` Identifier printed on the form, if any - `IReadOnlyList? Columns` Printed column headers in order, if any - `string? Label` Printed table caption, if any - `Type Type` Form table node - `"table"Table` ### Form Table Cell Items - `` ### Header Item - `class HeaderItem:` - `required IReadOnlyList Items` List of items within the header - `class CodeItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Code content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `string? Language` Programming language identifier - `Type Type` Code block item type - `"code"Code` - `class HeadingItem:` - `required Long Level` Heading level (1-6) - `required string Md` Markdown representation preserving formatting - `required string Value` Heading text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Heading item type - `"heading"Heading` - `class ImageItem:` - `required string Caption` Image caption - `required string Md` Markdown representation preserving formatting - `required string Url` URL to the image - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Image item type - `"image"Image` - `class LinkItem:` - `required string Md` Markdown representation preserving formatting - `required string Text` Display text of the link - `required string Url` URL of the link - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Link item type - `"link"Link` - `class ListItem:` - `required IReadOnlyList Items` List of nested text or list items - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Text item type - `"text"Text` - `class ListItem:` - `required string Md` Markdown representation preserving formatting - `required Boolean Ordered` Whether the list is ordered or unordered - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` List item type - `"list"List` - `class TableItem:` - `required string Csv` CSV representation of the table - `required string Html` HTML representation of the table - `required string Md` Markdown representation preserving formatting - `required IReadOnlyList> Rows` Table data as array of arrays (string, number, or null) - `string` - `Double` - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `IReadOnlyList? MergedFromPages` List of page numbers with tables that were merged into this table (e.g., [1, 2, 3, 4]) - `Long? MergedIntoPage` Populated when merged into another table. Page number where the full merged table begins (used on empty tables). - `IReadOnlyList? ParseConcerns` Quality concerns detected during table extraction, indicating the table may have issues - `required string Details` Human-readable details about the concern - `required string Type` Type of parse concern (e.g. header_value_type_mismatch, inconsistent_row_cell_count) - `Type Type` Table item type - `"table"Table` - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Page header container - `"header"Header` ### Heading Item - `class HeadingItem:` - `required Long Level` Heading level (1-6) - `required string Md` Markdown representation preserving formatting - `required string Value` Heading text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Heading item type - `"heading"Heading` ### Image Item - `class ImageItem:` - `required string Caption` Image caption - `required string Md` Markdown representation preserving formatting - `required string Url` URL to the image - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Image item type - `"image"Image` ### Link Item - `class LinkItem:` - `required string Md` Markdown representation preserving formatting - `required string Text` Display text of the link - `required string Url` URL of the link - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Link item type - `"link"Link` ### List Item - `class ListItem:` - `required IReadOnlyList Items` List of nested text or list items - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Text item type - `"text"Text` - `class ListItem:` - `required string Md` Markdown representation preserving formatting - `required Boolean Ordered` Whether the list is ordered or unordered - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` List item type - `"list"List` ### Llama Parse Supported File Extensions - `enum LlamaParseSupportedFileExtensions:` Enum for supported file extensions. - `".abw"Abw` - `".awt"Awt` - `".azw"Azw` - `".azw3"Azw3` - `".azw4"Azw4` - `".bmp"Bmp` - `".cb7"Cb7` - `".cbc"Cbc` - `".cbr"Cbr` - `".cbz"Cbz` - `".cgm"Cgm` - `".chm"Chm` - `".csv"Csv` - `".cwk"Cwk` - `".dbf"Dbf` - `".dif"Dif` - `".djvu"Djvu` - `".doc"Doc` - `".docm"Docm` - `".docx"Docx` - `".dot"Dot` - `".dotm"Dotm` - `".dotx"Dotx` - `".epub"Epub` - `".et"Et` - `".eth"Eth` - `".fb2"Fb2` - `".fbz"Fbz` - `".fodg"Fodg` - `".fodp"Fodp` - `".fods"Fods` - `".fodt"Fodt` - `".fopd"Fopd` - `".gif"Gif` - `".heic"Heic` - `".heif"Heif` - `".htm"Htm` - `".html"Html` - `".htmlz"Htmlz` - `".hwp"Hwp` - `".jpeg"Jpeg` - `".jpg"Jpg` - `".key"Key` - `".lit"Lit` - `".lrf"Lrf` - `".lwp"Lwp` - `".m4a"M4a` - `".mcw"Mcw` - `".md"Md` - `".mobi"Mobi` - `".mp3"Mp3` - `".mp4"Mp4` - `".mpeg"Mpeg` - `".mpga"Mpga` - `".mw"Mw` - `".mwd"Mwd` - `".numbers"Numbers` - `".odf"Odf` - `".odg"Odg` - `".odp"Odp` - `".ods"Ods` - `".odt"Odt` - `".otg"Otg` - `".otp"Otp` - `".ots"Ots` - `".ott"Ott` - `".pages"Pages` - `".pbd"Pbd` - `".pdb"Pdb` - `".pdf"Pdf` - `".pml"Pml` - `".png"Png` - `".pot"Pot` - `".potm"Potm` - `".potx"Potx` - `".ppt"Ppt` - `".pptm"Pptm` - `".pptx"Pptx` - `".prc"Prc` - `".prn"Prn` - `".psw"Psw` - `".qpw"Qpw` - `".rb"Rb` - `".rtf"Rtf` - `".sda"Sda` - `".sdd"Sdd` - `".sdp"Sdp` - `".sdw"Sdw` - `".sgl"Sgl` - `".slk"Slk` - `".snb"Snb` - `".stc"Stc` - `".std"Std` - `".sti"Sti` - `".stw"Stw` - `".svg"Svg` - `".sxc"Sxc` - `".sxd"Sxd` - `".sxg"Sxg` - `".sxi"Sxi` - `".sxm"Sxm` - `".sxw"Sxw` - `".sylk"Sylk` - `".tcr"Tcr` - `".tif"Tif` - `".tiff"Tiff` - `".tsv"Tsv` - `".txtz"Txtz` - `".uof"Uof` - `".uop"Uop` - `".uos"Uos` - `".uos1"Uos1` - `".uos2"Uos2` - `".uot"Uot` - `".vdx"Vdx` - `".vor"Vor` - `".vsd"Vsd` - `".vsdm"Vsdm` - `".vsdx"Vsdx` - `".wav"Wav` - `".wb1"Wb1` - `".wb2"Wb2` - `".wb3"Wb3` - `".webm"Webm` - `".webp"Webp` - `".wk1"Wk1` - `".wk2"Wk2` - `".wk3"Wk3` - `".wk4"Wk4` - `".wks"Wks` - `".wn"Wn` - `".wpd"Wpd` - `".wps"Wps` - `".wpt"Wpt` - `".wq1"Wq1` - `".wq2"Wq2` - `".wri"Wri` - `".xhtm"Xhtm` - `".xlr"Xlr` - `".xls"Xls` - `".xlsb"Xlsb` - `".xlsm"Xlsm` - `".xlsx"Xlsx` - `".xlw"Xlw` - `".xml"Xml` - `".yxmd"Yxmd` - `".zabw"Zabw` ### Parsing Job - `class ParsingJob:` A parse job (v1). - `required string ID` Unique parse job identifier - `required StatusEnum Status` Current job status - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"PARTIAL_SUCCESS"PartialSuccess` - `"PENDING"Pending` - `"SUCCESS"Success` - `string? ErrorCode` Machine-readable error code when failed - `string? ErrorMessage` Human-readable error details when failed ### Parsing Languages - `enum ParsingLanguages:` Enum for representing the languages supported by the parser. - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` ### Parsing Mode - `enum ParsingMode:` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` ### Status Enum - `enum StatusEnum:` Enum for representing the status of a job - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"PARTIAL_SUCCESS"PartialSuccess` - `"PENDING"Pending` - `"SUCCESS"Success` ### Table Item - `class TableItem:` - `required string Csv` CSV representation of the table - `required string Html` HTML representation of the table - `required string Md` Markdown representation preserving formatting - `required IReadOnlyList> Rows` Table data as array of arrays (string, number, or null) - `string` - `Double` - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `IReadOnlyList? MergedFromPages` List of page numbers with tables that were merged into this table (e.g., [1, 2, 3, 4]) - `Long? MergedIntoPage` Populated when merged into another table. Page number where the full merged table begins (used on empty tables). - `IReadOnlyList? ParseConcerns` Quality concerns detected during table extraction, indicating the table may have issues - `required string Details` Human-readable details about the concern - `required string Type` Type of parse concern (e.g. header_value_type_mismatch, inconsistent_row_cell_count) - `Type Type` Table item type - `"table"Table` ### Text Item - `class TextItem:` - `required string Md` Markdown representation preserving formatting - `required string Value` Text content - `IReadOnlyList? Bbox` List of bounding boxes - `required Double H` Height of the bounding box - `required Double W` Width of the bounding box - `required Double X` X coordinate of the bounding box - `required Double Y` Y coordinate of the bounding box - `Double? Confidence` Confidence score - `Long? EndIndex` End index in the text - `string? Label` Label for the bounding box - `Double? R` Optional visual text rotation angle in degrees. Omitted when unrotated. - `Long? StartIndex` Start index in the text - `Type Type` Text item type - `"text"Text`