> ## Documentation Index > Fetch the complete documentation index at: https://docs.reducto.ai/llms.txt > Use this file to discover all available pages before exploring further. # Extract ## OpenAPI ````yaml openapi-legacy.json post /extract openapi: 3.1.0 info: title: Reducto API (Legacy) version: v1.11.81-297-g4204a908d servers: - url: https://platform.reducto.ai security: [] paths: /extract: post: summary: Extract operationId: extract_extract_post requestBody: content: application/json: schema: $ref: '#/components/schemas/ExtractConfigNew' required: true responses: '200': description: Successful Response content: application/json: schema: anyOf: - $ref: '#/components/schemas/ExtractResponse' - $ref: '#/components/schemas/V3ExtractResponse' title: Response Extract Extract Post '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - SkippableHTTPBearer: [] components: schemas: ExtractConfigNew: properties: options: $ref: '#/components/schemas/BaseProcessingOptions' advanced_options: $ref: '#/components/schemas/AdvancedProcessingOptions' experimental_options: $ref: '#/components/schemas/ExperimentalProcessingOptions' schema: title: Schema description: The JSON schema to use for extraction. system_prompt: type: string title: System Prompt description: >- A system prompt to use for the extraction. This is a general prompt that is applied to the entire document before any other prompts. default: Be precise and thorough. deep_extract: type: boolean title: Deep Extract description: >- If True, use Deep Extract, an agentic extraction mode that iteratively refines its output to achieve near-perfect accuracy. Best for complex documents where accuracy is critical. default: false generate_citations: type: boolean title: Generate Citations description: If citations should be generated for the extracted content. default: false array_extract: $ref: '#/components/schemas/ArrayExtractConfig' description: The configuration options for array extract default: enabled: false mode: legacy pages_per_segment: 10 use_chunking: type: boolean title: Use Chunking description: If chunking should be used for the extraction. Defaults to False. default: false include_images: type: boolean title: Include Images description: >- If images should be passed directly for extractions. Can only be enabled for documents with less than 10 pages. Defaults to False. default: false spreadsheet_agent: type: boolean title: Spreadsheet Agent description: If spreadsheet agent should be used for extraction. default: false experimental_table_citations: type: boolean title: Experimental Table Citations description: If table citations should be generated for the extracted content. default: true priority: type: boolean title: Priority description: >- If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs. default: true citations_options: $ref: '#/components/schemas/AdvancedCitationsConfig' description: The configuration options for citations. default: numerical_confidence: false parent_block: full agent_extract: $ref: '#/components/schemas/AgentExtractConfig' description: The configuration options for agent extract default: enabled: false document_url: anyOf: - type: string - items: type: string type: array - $ref: '#/components/schemas/UploadResponse' title: Document Url description: > The URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A job_id (jobid://) or a list of job_ids (jobid://) obtained from a previous /parse endpoint additionalProperties: false type: object required: - schema - document_url title: ExtractConfigNew ExtractResponse: additionalProperties: true type: object V3ExtractResponse: additionalProperties: true type: object HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError BaseProcessingOptions: properties: ocr_mode: type: string enum: - standard - agentic title: Ocr Mode description: >- The mode to use for OCR. Agentic mode adds an extra pass, correcting any table/text mistakes at a small cost. default: standard extraction_mode: type: string enum: - ocr - metadata - hybrid title: Extraction Mode description: >- The mode to use for extraction. Metadata/hybrid are only recommended with high quality metadata embeddings. default: ocr chunking: $ref: '#/components/schemas/ChunkingConfig' description: >- The configuration options for chunking. Chunking is commonly used for RAG usecases. default: chunk_mode: variable chunk_overlap: 0 table_summary: $ref: '#/components/schemas/TableSummaryConfig' description: The configuration options for table summarization. default: enabled: false figure_summary: $ref: '#/components/schemas/FigureSummaryConfig' description: The configuration options for figure summarization. filter_blocks: items: type: string enum: - Header - Footer - Title - Section Header - Page Number - List Item - Figure - Table - Key Value - Text - Comment - Signature type: array title: Filter Blocks description: >- A list of block types to filter from chunk content. Pass blocks to filter them from content. By default, no blocks are filtered. default: [] force_url_result: type: boolean title: Force Url Result description: >- Force the result to be returned in URL form (by default only used for very large responses). default: false type: object title: BaseProcessingOptions AdvancedProcessingOptions: properties: ocr_system: type: string enum: - highres - multilingual - combined - reducto - legacy title: Ocr System description: >- The OCR system to use. Highres is recommended for documents with English characters. Legacy uses an alternative OCR backend. default: highres table_output_format: type: string enum: - html - json - md - jsonbbox - dynamic - ai_json - csv title: Table Output Format description: >- The mode to use for table output. Dynamic returns md for simpler tables and html for more complex tables. default: html merge_tables: type: boolean title: Merge Tables description: >- A flag to indicate if consecutive tables with the same number of columns should be merged across breaks and spaces. default: false include_formula_information: type: boolean title: Include Formula Information description: >- If True, preserve formula information in spreadsheet cells by wrapping text with LaTeX formula commands during parsing. default: false include_color_information: type: boolean title: Include Color Information description: >- If True, preserve Excel cell colours in the extracted spreadsheet text using LaTeX colour commands. default: false include_dropdown_information: type: boolean title: Include Dropdown Information description: >- If True, include dropdown options and the selected value when rendering spreadsheet cells. default: false continue_hierarchy: type: boolean title: Continue Hierarchy description: >- A flag to indicate if the hierarchy of the document should be continued from chunk to chunk. default: true keep_line_breaks: type: boolean title: Keep Line Breaks description: If line breaks should be preserved in the text. default: false page_range: anyOf: - $ref: '#/components/schemas/PageRange' - items: $ref: '#/components/schemas/PageRange' type: array - items: type: integer type: array - items: type: string type: array title: Page Range description: >- The page range to process (1-indexed). By default, the entire document is processed. For spreadsheets, you can also provide a list of sheet names. default: {} force_file_extension: type: string title: Force File Extension description: >- Force the URL to be downloaded as a specific file extension (e.g. .png). large_table_chunking: $ref: '#/components/schemas/LargeTableChunkingConfig' description: >- The configuration options for large table chunking (currently only supported on spreadsheet and CSV files). default: enabled: true size: 50 spreadsheet_table_clustering: type: string enum: - default - disabled - intelligent title: Spreadsheet Table Clustering description: >- In a spreadsheet with different tables inside, we enable splitting up the tables by default. Intelligent mode applies more powerful models for superior accuracy, at 5× the default per-cell rate. Disabling will register as one large table. default: default max_cell_count: anyOf: - type: integer minimum: 1 - type: 'null' title: Max Cell Count description: >- Maximum total non-empty cells allowed across all sheets. If exceeded, the request is rejected with a 422 error. Set to null to disable the limit. Defaults to null. add_page_markers: type: boolean title: Add Page Markers description: >- If True, add page markers to the output (e.g. [[PAGE 1 BEGINS HERE]] and [[PAGE 1 ENDS HERE]] added as blocks to the content). Defaults to False. default: false remove_text_formatting: type: boolean title: Remove Text Formatting description: >- If True, remove text formatting from the output (e.g. hyphens for list items). Defaults to False. default: false return_ocr_data: type: boolean title: Return Ocr Data description: If True, return OCR data in the result. Defaults to False. default: false document_password: type: string title: Document Password description: Password to decrypt password-protected documents. filter_line_numbers: type: boolean title: Filter Line Numbers description: If True, filter out line numbers from the output. Defaults to False. default: false read_comments: type: boolean title: Read Comments description: If True, pull in PDF comments from the document. Defaults to False. default: false persist_results: type: boolean title: Persist Results description: If True, persist the results indefinitely. Defaults to False. default: false exclude_hidden_sheets: type: boolean title: Exclude Hidden Sheets description: Skip hidden sheets in Excel files. Defaults to False. default: false exclude_hidden_rows_cols: type: boolean title: Exclude Hidden Rows Cols description: Skip hidden rows and cols in Excel files. Defaults to False. default: false enable_change_tracking: type: boolean title: Enable Change Tracking description: >- Enables model-based detection of underlines and strikethroughs, adding / tags to OCR text. Works with any extraction mode. Defaults to False. default: false enable_highlight_detection: type: boolean title: Enable Highlight Detection description: >- If True, enable highlight detection. Highlighted text will be surrounded by tags in the output. Defaults to False. default: false ignore_watermarks: type: boolean title: Ignore Watermarks description: >- If True, ignore and remove watermarks from OCR output. Defaults to False. default: false type: object title: AdvancedProcessingOptions ExperimentalProcessingOptions: properties: enrich: $ref: '#/components/schemas/EnrichConfig' description: The configuration options for enrichment. default: enabled: false mode: standard layout_enrichment: type: boolean title: Layout Enrichment description: >- Layout enrichment is a beta feature that improves our layout and reading order performance at the cost of increased latency. Defaults to False. default: false enable_checkboxes: type: boolean title: Enable Checkboxes description: >- Use an experimental checkbox detection model to add checkboxes to the output, defaults to False default: false enable_equations: type: boolean title: Enable Equations description: >- Use an experimental equation detection model to add equations to the output, defaults to False default: false rotate_pages: type: boolean title: Rotate Pages description: >- Use an orientation model to detect and rotate pages as needed, defaults to True default: true rotate_figures: type: boolean title: Rotate Figures description: >- Use an orientation model to detect and rotate figures as needed, defaults to False default: false enable_scripts: type: boolean title: Enable Scripts description: >- Add tag around subscripts and tag around superscripts, defaults to False default: false return_figure_images: type: boolean title: Return Figure Images description: >- If figure images should be returned in the result. Defaults to False. default: false return_table_images: type: boolean title: Return Table Images description: If table images should be returned in the result. Defaults to False. default: false return_page_images: type: boolean title: Return Page Images description: >- If full page images should be returned in the result. Defaults to False. default: false layout_model: type: string enum: - default - beta title: Layout Model description: >- The layout model to use for the document. This will be deprecated in the future. default: default embed_text_metadata_pdf: type: boolean title: Embed Text Metadata Pdf description: >- If extracted OCR text metadata should be embedded back into the returned PDF, overwriting any existing text. Defaults to False. default: false embed_pdf_metadata_dpi: type: integer maximum: 250 minimum: 50 title: Embed Pdf Metadata Dpi description: >- Render DPI used when rasterizing the source PDF before embedding the OCR text layer. Lower values produce dramatically smaller output PDFs; higher values preserve more detail when zoomed past 200%. Defaults to 100 (good for on-screen viewing); raise toward the source scan DPI for crisper output. Min 50, max 250. default: 100 detect_signatures: type: boolean title: Detect Signatures description: If True, detect signatures in the document. Defaults to False. default: false danger_filter_wide_boxes: type: boolean title: Danger Filter Wide Boxes description: >- You probably shouldn't use this. If True, filter out boxes with width greater than 50% of the document width. Defaults to False. You probably don't want to use this. default: false user_specified_timeout_seconds: anyOf: - type: number - type: 'null' title: User Specified Timeout Seconds description: A user specified timeout, defaults to None additionalProperties: true type: object title: ExperimentalProcessingOptions ArrayExtractConfig: properties: enabled: type: boolean title: Enabled description: >- Array extraction allows you to extract long lists of information from lengthy documents. It makes parallel calls on overlapping sections of the document. default: false mode: type: string enum: - auto - legacy - no_overlap title: Mode description: The array extraction version to use. default: legacy pages_per_segment: type: integer title: Pages Per Segment description: >- Length of each segment, in pages, for parallel calls with array extraction. default: 10 type: object title: ArrayExtractConfig AdvancedCitationsConfig: properties: numerical_confidence: type: boolean title: Numerical Confidence description: >- If True, enable numeric citation confidence scores. Defaults to False. default: false parent_block: $ref: '#/components/schemas/CitationParentBlockMode' description: >- How much of the source parse block to embed on each citation's parentBlock. 'full' (default) embeds the verbatim source-block HTML in parentBlock.content. 'bbox_only' suppresses parentBlock.content (returned as an empty string) while keeping parentBlock.bbox and all citation-level fields — this can drastically shrink responses on table-heavy schemas where the same source block is cited many times. default: full type: object title: AdvancedCitationsConfig AgentExtractConfig: properties: enabled: type: boolean title: Enabled description: If agent extraction should be used for extraction. default: false type: object title: AgentExtractConfig UploadResponse: properties: file_id: type: string title: File Id presigned_url: anyOf: - type: string - type: 'null' title: Presigned Url type: object required: - file_id title: UploadResponse ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError ChunkingConfig: properties: chunk_mode: type: string enum: - variable - section - page - block - disabled - page_sections title: Chunk Mode description: >- Choose how to partition chunks. Variable mode chunks by character length and visual context. Section mode chunks by section headers. Page mode chunks according to pages. Page sections mode chunks first by page, then by sections within each page. Disabled returns one single chunk. default: variable chunk_size: type: integer title: Chunk Size description: >- The approximate size of chunks (in characters) that the document will be split into. Defaults to None, in which case the chunk size is variable between 250 - 1500 characters. chunk_overlap: type: integer title: Chunk Overlap description: >- Number of characters of overlap to include from adjacent chunks. Defaults to 0. default: 0 type: object title: ChunkingConfig TableSummaryConfig: properties: enabled: type: boolean title: Enabled description: If table summarization should be performed. default: false prompt: type: string title: Prompt description: Add information to the prompt for table summarization. type: object title: TableSummaryConfig FigureSummaryConfig: properties: enabled: type: boolean title: Enabled description: If figure summarization should be performed. default: false prompt: type: string title: Prompt description: >- Add information to the prompt for figure summarization. Note any visual cues that should be incorporated. Example: 'When provided a diagram, extract all of the figure content verbatim.' override: type: boolean title: Override description: If the figure summary prompt should override our default prompt. default: false advanced_chart_agent: type: boolean title: Advanced Chart Agent description: If True, use the advanced chart agent. Defaults to False. default: false type: object title: FigureSummaryConfig PageRange: properties: start: anyOf: - type: integer - type: 'null' title: Start description: The page number to start processing from (1-indexed). end: anyOf: - type: integer - type: 'null' title: End description: The page number to stop processing at (1-indexed). type: object title: PageRange LargeTableChunkingConfig: properties: enabled: type: boolean title: Enabled description: >- If large tables should be chunked into smaller tables, currently only supported on spreadsheet and CSV files. default: true size: type: integer title: Size description: >- The max row/column size for a table to be chunked. Defaults to 50. Header rows/columns are persisted based on heuristics. default: 50 type: object title: LargeTableChunkingConfig EnrichConfig: properties: enabled: type: boolean title: Enabled description: >- If enabled, a large language/vision model will be used to postprocess the extracted content. Note: enabling enrich requires tables be outputted in markdown format. Defaults to False. default: false mode: type: string enum: - standard - page - table - table_auto title: Mode description: The mode to use for enrichment. Defaults to standard default: standard prompt: type: string title: Prompt description: Add information to the prompt for enrichment. type: object title: EnrichConfig CitationParentBlockMode: type: string enum: - full - bbox_only title: CitationParentBlockMode description: >- How much of the source parse block to embed on each citation's ``parentBlock``. ``FULL`` embeds the verbatim source-block HTML in ``parentBlock.content``. ``BBOX_ONLY`` returns ``parentBlock.content`` as an empty string while keeping ``parentBlock.bbox`` and all citation-level fields — on table-heavy schemas the same source block is re-embedded into every citation that points into it, so the content can dominate the response (90%+ of bytes) while being redundant with the parse output. securitySchemes: SkippableHTTPBearer: type: http scheme: bearer ````