@llamaindex/llama-cloud 2.0.0 → 2.2.0

package/src/resources/extract.ts

@@ -2,8 +2,7 @@
 
 import { APIResource } from '../core/resource';
 import * as ExtractAPI from './extract';
-import * as ParsingAPI from './parsing';
-import * as SplitAPI from './beta/split';
+import * as ConfigurationsAPI from './configurations';
 import { APIPromise } from '../core/api-promise';
 import { PagePromise, PaginatedCursor, type PaginatedCursorParams } from '../core/pagination';
 import { RequestOptions } from '../internal/request-options';
@@ -26,7 +25,7 @@ export class Extract extends APIResource {
    *
    * ## Document input
    *
-   * Set `document_input_value` to a file ID (`dfl-...`) or a completed parse job ID
+   * Set `file_input` to a file ID (`dfl-...`) or a completed parse job ID
    * (`pjb-...`).
    *
    * The job runs asynchronously. Poll `GET /extract/{job_id}` or register a webhook
@@ -35,8 +34,7 @@ export class Extract extends APIResource {
    * @example
    * ```ts
    * const extractV2Job = await client.extract.create({
-   *   document_input_value:
-   *     'dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee',
+   *   file_input: 'dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee',
    * });
    * ```
    */
@@ -48,10 +46,9 @@ export class Extract extends APIResource {
   /**
    * List extraction jobs with optional filtering and pagination.
    *
-   * Filter by `configuration_id`, `status`, `document_input_value`, or creation date
-   * range. Results are returned newest-first. Use `expand=configuration` to include
-   * the full configuration used, and `expand=extract_metadata` for per-field
-   * metadata.
+   * Filter by `configuration_id`, `status`, `file_input`, or creation date range.
+   * Results are returned newest-first. Use `expand=configuration` to include the
+   * full configuration used, and `expand=extract_metadata` for per-field metadata.
    *
    * @example
    * ```ts
@@ -93,13 +90,14 @@ export class Extract extends APIResource {
    *
    * @example
    * ```ts
-   * const response = await client.extract.generateSchema();
+   * const configurationCreate =
+   *   await client.extract.generateSchema();
    * ```
    */
   generateSchema(
     params: ExtractGenerateSchemaParams,
     options?: RequestOptions,
-  ): APIPromise<ExtractGenerateSchemaResponse> {
+  ): APIPromise<ConfigurationsAPI.ConfigurationCreate> {
     const { organization_id, project_id, ...body } = params;
     return this._client.post('/api/v2/extract/schema/generate', {
       query: { organization_id, project_id },
@@ -384,7 +382,7 @@ export interface ExtractV2Job {
   /**
    * File ID or parse job ID that was extracted
    */
-  document_input_value: string;
+  file_input: string;
 
   /**
    * Project this job belongs to
@@ -462,9 +460,9 @@ export namespace ExtractV2Job {
  */
 export interface ExtractV2JobCreate {
   /**
-   * File ID or Parse Job ID to extract from
+   * File ID or parse job ID to extract from
    */
-  document_input_value: string;
+  file_input: string;
 
   /**
    * Extract configuration combining parse and extract settings.
@@ -472,7 +470,7 @@ export interface ExtractV2JobCreate {
   configuration?: ExtractConfiguration | null;
 
   /**
-   * Saved extract configuration ID (mutually exclusive with configuration)
+   * Saved configuration ID
    */
   configuration_id?: string | null;
 
@@ -607,7 +605,11 @@ export interface ExtractV2SchemaValidateResponse {
  */
 export interface ExtractedFieldMetadata {
   /**
-   * Document-level metadata (citations, confidence) keyed by field name
+   * Per-field metadata keyed by field name from your schema. Scalar fields (e.g.
+   * `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields
+   * (e.g. `items`) map to a list where each element contains per-sub-field
+   * FieldMetadataEntry objects, indexed by array position. Nested objects contain
+   * sub-field entries recursively.
    */
   document_metadata?: {
     [key: string]: { [key: string]: unknown } | Array<unknown> | string | number | boolean | null;
@@ -630,1216 +632,11 @@ export interface ExtractedFieldMetadata {
 
 export type ExtractDeleteResponse = unknown;
 
-/**
- * Request body for creating a product configuration.
- */
-export interface ExtractGenerateSchemaResponse {
-  /**
-   * Human-readable name for this configuration.
-   */
-  name: string;
-
-  /**
-   * Product-specific configuration parameters.
-   */
-  parameters:
-    | ExtractGenerateSchemaResponse.SplitV1Parameters
-    | ExtractGenerateSchemaResponse.ExtractV2Parameters
-    | ExtractGenerateSchemaResponse.ClassifyV2Parameters
-    | ExtractGenerateSchemaResponse.ParseV2Parameters
-    | ExtractGenerateSchemaResponse.UntypedParameters;
-}
-
-export namespace ExtractGenerateSchemaResponse {
-  /**
-   * Typed parameters for a _split v1_ product configuration.
-   */
-  export interface SplitV1Parameters {
-    /**
-     * Categories to split documents into.
-     */
-    categories: Array<SplitAPI.SplitCategory>;
-
-    /**
-     * Product type.
-     */
-    product_type: 'split_v1';
-
-    /**
-     * Strategy for splitting documents.
-     */
-    splitting_strategy?: SplitV1Parameters.SplittingStrategy;
-  }
-
-  export namespace SplitV1Parameters {
-    /**
-     * Strategy for splitting documents.
-     */
-    export interface SplittingStrategy {
-      /**
-       * Controls handling of pages that don't match any category. 'include': pages can
-       * be grouped as 'uncategorized' and included in results. 'forbid': all pages must
-       * be assigned to a defined category. 'omit': pages can be classified as
-       * 'uncategorized' but are excluded from results.
-       */
-      allow_uncategorized?: 'include' | 'forbid' | 'omit';
-    }
-  }
-
-  /**
-   * Typed parameters for an _extract v2_ product configuration.
-   */
-  export interface ExtractV2Parameters {
-    /**
-     * JSON Schema defining the fields to extract. Validate with the /schema/validate
-     * endpoint first.
-     */
-    data_schema: {
-      [key: string]: { [key: string]: unknown } | Array<unknown> | string | number | boolean | null;
-    };
-
-    /**
-     * Product type.
-     */
-    product_type: 'extract_v2';
-
-    /**
-     * Include citations in results
-     */
-    cite_sources?: boolean;
-
-    /**
-     * Include confidence scores in results
-     */
-    confidence_scores?: boolean;
-
-    /**
-     * Extract algorithm version. Use 'latest' or a date string.
-     */
-    extract_version?: string;
-
-    /**
-     * Granularity of extraction: per_doc returns one object per document, per_page
-     * returns one object per page, per_table_row returns one object per table row
-     */
-    extraction_target?: 'per_doc' | 'per_page' | 'per_table_row';
-
-    /**
-     * ISO 639-1 language code for the document
-     */
-    lang?: string;
-
-    /**
-     * Maximum number of pages to process. Omit for no limit.
-     */
-    max_pages?: number | null;
-
-    /**
-     * Saved parse configuration ID to control how the document is parsed before
-     * extraction
-     */
-    parse_config_id?: string | null;
-
-    /**
-     * Parse tier to use before extraction (fast, cost_effective, or agentic)
-     */
-    parse_tier?: string | null;
-
-    /**
-     * Custom system prompt to guide extraction behavior
-     */
-    system_prompt?: string | null;
-
-    /**
-     * Comma-separated page numbers or ranges to process (1-based). Omit to process all
-     * pages.
-     */
-    target_pages?: string | null;
-
-    /**
-     * Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page)
-     */
-    tier?: 'cost_effective' | 'agentic';
-  }
-
-  /**
-   * Typed parameters for a _classify v2_ product configuration.
-   */
-  export interface ClassifyV2Parameters {
-    /**
-     * Product type.
-     */
-    product_type: 'classify_v2';
-
-    /**
-     * Classify rules to evaluate against the document (at least one required)
-     */
-    rules: Array<ClassifyV2Parameters.Rule>;
-
-    /**
-     * Classify execution mode
-     */
-    mode?: 'FAST';
-
-    /**
-     * Parsing configuration for classify jobs.
-     */
-    parsing_configuration?: ClassifyV2Parameters.ParsingConfiguration | null;
-  }
-
-  export namespace ClassifyV2Parameters {
-    /**
-     * A rule for classifying documents.
-     */
-    export interface Rule {
-      /**
-       * Natural language criteria for matching this rule
-       */
-      description: string;
-
-      /**
-       * Document type to assign when rule matches
-       */
-      type: string;
-    }
-
-    /**
-     * Parsing configuration for classify jobs.
-     */
-    export interface ParsingConfiguration {
-      /**
-       * ISO 639-1 language code for the document
-       */
-      lang?: string;
-
-      /**
-       * Maximum number of pages to process. Omit for no limit.
-       */
-      max_pages?: number | null;
-
-      /**
-       * Comma-separated page numbers or ranges to process (1-based). Omit to process all
-       * pages.
-       */
-      target_pages?: string | null;
-    }
-  }
-
-  /**
-   * Configuration for LlamaParse v2 document parsing.
-   *
-   * Includes tier selection, processing options, output formatting, page targeting,
-   * and webhook delivery. Refer to the LlamaParse documentation for details on each
-   * field.
-   */
-  export interface ParseV2Parameters {
-    /**
-     * Product type.
-     */
-    product_type: 'parse_v2';
-
-    /**
-     * Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced),
-     * 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with
-     * highest accuracy)
-     */
-    tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus';
-
-    /**
-     * Tier version. Use 'latest' for the current stable version, or specify a specific
-     * version (e.g., '1.0', '2.0') for reproducible results
-     */
-    version:
-      | '2025-12-11'
-      | '2025-12-18'
-      | '2025-12-31'
-      | '2026-01-08'
-      | '2026-01-09'
-      | '2026-01-16'
-      | '2026-01-21'
-      | '2026-01-22'
-      | '2026-01-24'
-      | '2026-01-29'
-      | '2026-01-30'
-      | '2026-02-03'
-      | '2026-02-18'
-      | '2026-02-20'
-      | '2026-02-24'
-      | '2026-02-26'
-      | '2026-03-02'
-      | '2026-03-03'
-      | '2026-03-04'
-      | '2026-03-05'
-      | '2026-03-09'
-      | '2026-03-10'
-      | '2026-03-11'
-      | '2026-03-12'
-      | '2026-03-17'
-      | '2026-03-19'
-      | '2026-03-20'
-      | '2026-03-22'
-      | '2026-03-23'
-      | '2026-03-24'
-      | '2026-03-25'
-      | '2026-03-26'
-      | '2026-03-27'
-      | 'latest'
-      | (string & {});
-
-    /**
-     * 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.
-     */
-    agentic_options?: ParseV2Parameters.AgenticOptions | null;
-
-    /**
-     * Identifier for the client/application making the request. Used for analytics and
-     * debugging. Example: 'my-app-v2'
-     */
-    client_name?: string | null;
-
-    /**
-     * Crop boundaries to process only a portion of each page. Values are ratios 0-1
-     * from page edges
-     */
-    crop_box?: ParseV2Parameters.CropBox;
-
-    /**
-     * Bypass result caching and force re-parsing. Use when document content may have
-     * changed or you need fresh results
-     */
-    disable_cache?: boolean | null;
-
-    /**
-     * 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.
-     */
-    fast_options?: unknown | null;
-
-    /**
-     * Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on
-     * detected input file type
-     */
-    input_options?: ParseV2Parameters.InputOptions;
-
-    /**
-     * Output formatting options for markdown, text, and extracted images
-     */
-    output_options?: ParseV2Parameters.OutputOptions;
-
-    /**
-     * Page selection: limit total pages or specify exact pages to process
-     */
-    page_ranges?: ParseV2Parameters.PageRanges;
-
-    /**
-     * Job execution controls including timeouts and failure thresholds
-     */
-    processing_control?: ParseV2Parameters.ProcessingControl;
-
-    /**
-     * Document processing options including OCR, table extraction, and chart parsing
-     */
-    processing_options?: ParseV2Parameters.ProcessingOptions;
-
-    /**
-     * Webhook endpoints for job status notifications. Multiple webhooks can be
-     * configured for different events or services
-     */
-    webhook_configurations?: Array<ParseV2Parameters.WebhookConfiguration>;
-  }
-
-  export namespace ParseV2Parameters {
-    /**
-     * 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.
-     */
-    export interface AgenticOptions {
-      /**
-       * 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.'
-       */
-      custom_prompt?: string | null;
-    }
-
-    /**
-     * Crop boundaries to process only a portion of each page. Values are ratios 0-1
-     * from page edges
-     */
-    export interface CropBox {
-      /**
-       * Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this
-       * line is excluded
-       */
-      bottom?: number | null;
-
-      /**
-       * Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this
-       * line is excluded
-       */
-      left?: number | null;
-
-      /**
-       * Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this
-       * line is excluded
-       */
-      right?: number | null;
-
-      /**
-       * Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line
-       * is excluded
-       */
-      top?: number | null;
-    }
-
-    /**
-     * Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on
-     * detected input file type
-     */
-    export interface InputOptions {
-      /**
-       * HTML/web page parsing options (applies to .html, .htm files)
-       */
-      html?: InputOptions.HTML;
-
-      /**
-       * PDF-specific parsing options (applies to .pdf files)
-       */
-      pdf?: unknown;
-
-      /**
-       * Presentation parsing options (applies to .pptx, .ppt, .odp, .key files)
-       */
-      presentation?: InputOptions.Presentation;
-
-      /**
-       * Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files)
-       */
-      spreadsheet?: InputOptions.Spreadsheet;
-    }
-
-    export namespace InputOptions {
-      /**
-       * HTML/web page parsing options (applies to .html, .htm files)
-       */
-      export interface HTML {
-        /**
-         * Force all HTML elements to be visible by overriding CSS display/visibility
-         * properties. Useful for parsing pages with hidden content or collapsed sections
-         */
-        make_all_elements_visible?: boolean | null;
-
-        /**
-         * Remove fixed-position elements (headers, footers, floating buttons) that appear
-         * on every page render
-         */
-        remove_fixed_elements?: boolean | null;
-
-        /**
-         * Remove navigation elements (nav bars, sidebars, menus) to focus on main content
-         */
-        remove_navigation_elements?: boolean | null;
-      }
-
-      /**
-       * Presentation parsing options (applies to .pptx, .ppt, .odp, .key files)
-       */
-      export interface Presentation {
-        /**
-         * Extract content positioned outside the visible slide area. Some presentations
-         * have hidden notes or content that extends beyond slide boundaries
-         */
-        out_of_bounds_content?: boolean | null;
-
-        /**
-         * Skip extraction of embedded chart data tables. When true, only the visual
-         * representation of charts is captured, not the underlying data
-         */
-        skip_embedded_data?: boolean | null;
-      }
-
-      /**
-       * Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files)
-       */
-      export interface Spreadsheet {
-        /**
-         * Detect and extract multiple tables within a single sheet. Useful when
-         * spreadsheets contain several data regions separated by blank rows/columns
-         */
-        detect_sub_tables_in_sheets?: boolean | null;
-
-        /**
-         * Compute formula results instead of extracting formula text. Use when you need
-         * calculated values rather than formula definitions
-         */
-        force_formula_computation_in_sheets?: boolean | null;
-
-        /**
-         * Parse hidden sheets in addition to visible ones. By default, hidden sheets are
-         * skipped
-         */
-        include_hidden_sheets?: boolean | null;
-      }
-    }
-
-    /**
-     * Output formatting options for markdown, text, and extracted images
-     */
-    export interface OutputOptions {
-      /**
-       * 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
-       */
-      extract_printed_page_number?: boolean | null;
-
-      /**
-       * 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
-       */
-      images_to_save?: Array<'screenshot' | 'embedded' | 'layout'>;
-
-      /**
-       * Markdown formatting options including table styles and link annotations
-       */
-      markdown?: OutputOptions.Markdown;
-
-      /**
-       * Spatial text output options for preserving document layout structure
-       */
-      spatial_text?: OutputOptions.SpatialText;
-
-      /**
-       * Options for exporting tables as XLSX spreadsheets
-       */
-      tables_as_spreadsheet?: OutputOptions.TablesAsSpreadsheet;
-    }
-
-    export namespace OutputOptions {
-      /**
-       * Markdown formatting options including table styles and link annotations
-       */
-      export interface Markdown {
-        /**
-         * Add link annotations to markdown output in the format [text](url). When false,
-         * only the link text is included
-         */
-        annotate_links?: boolean | null;
-
-        /**
-         * Embed images directly in markdown as base64 data URIs instead of extracting them
-         * as separate files. Useful for self-contained markdown output
-         */
-        inline_images?: boolean | null;
-
-        /**
-         * Table formatting options including markdown vs HTML format and merging behavior
-         */
-        tables?: Markdown.Tables;
-      }
-
-      export namespace Markdown {
-        /**
-         * Table formatting options including markdown vs HTML format and merging behavior
-         */
-        export interface Tables {
-          /**
-           * Remove extra whitespace padding in markdown table cells for more compact output
-           */
-          compact_markdown_tables?: boolean | null;
-
-          /**
-           * Separator string for multiline cell content in markdown tables. Example:
-           * '&lt;br&gt;' to preserve line breaks, ' ' to join with spaces
-           */
-          markdown_table_multiline_separator?: string | null;
-
-          /**
-           * Automatically merge tables that span multiple pages into a single table. The
-           * merged table appears on the first page with merged_from_pages metadata
-           */
-          merge_continued_tables?: boolean | null;
-
-          /**
-           * Output tables as markdown pipe tables instead of HTML &lt;table&gt; tags.
-           * Markdown tables are simpler but cannot represent complex structures like merged
-           * cells
-           */
-          output_tables_as_markdown?: boolean | null;
-        }
-      }
-
-      /**
-       * Spatial text output options for preserving document layout structure
-       */
-      export interface SpatialText {
-        /**
-         * Keep multi-column layouts intact instead of linearizing columns into sequential
-         * text. Automatically enabled for non-fast tiers
-         */
-        do_not_unroll_columns?: boolean | null;
-
-        /**
-         * Maintain consistent text column alignment across page boundaries. Automatically
-         * enabled for document-level parsing modes
-         */
-        preserve_layout_alignment_across_pages?: boolean | null;
-
-        /**
-         * Include text below the normal size threshold. Useful for footnotes, watermarks,
-         * or fine print that might otherwise be filtered out
-         */
-        preserve_very_small_text?: boolean | null;
-      }
-
-      /**
-       * Options for exporting tables as XLSX spreadsheets
-       */
-      export interface TablesAsSpreadsheet {
-        /**
-         * Whether this option is enabled
-         */
-        enable?: boolean | null;
-
-        /**
-         * Automatically generate descriptive sheet names from table context (headers,
-         * surrounding text) instead of using generic names like 'Table_1'
-         */
-        guess_sheet_name?: boolean;
-      }
-    }
-
-    /**
-     * Page selection: limit total pages or specify exact pages to process
-     */
-    export interface PageRanges {
-      /**
-       * 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
-       */
-      max_pages?: number | null;
-
-      /**
-       * 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
-       */
-      target_pages?: string | null;
-    }
-
-    /**
-     * Job execution controls including timeouts and failure thresholds
-     */
-    export interface ProcessingControl {
-      /**
-       * Quality thresholds that determine when a job should fail vs complete with
-       * partial results
-       */
-      job_failure_conditions?: ProcessingControl.JobFailureConditions;
-
-      /**
-       * Timeout settings for job execution. Increase for large or complex documents
-       */
-      timeouts?: ProcessingControl.Timeouts;
-    }
-
-    export namespace ProcessingControl {
-      /**
-       * Quality thresholds that determine when a job should fail vs complete with
-       * partial results
-       */
-      export interface JobFailureConditions {
-        /**
-         * 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%)
-         */
-        allowed_page_failure_ratio?: number | null;
-
-        /**
-         * Fail the job if a problematic font is detected that may cause incorrect text
-         * extraction. Buggy fonts can produce garbled or missing characters
-         */
-        fail_on_buggy_font?: boolean | null;
-
-        /**
-         * Fail the entire job if any embedded image cannot be extracted. By default, image
-         * extraction errors are logged but don't fail the job
-         */
-        fail_on_image_extraction_error?: boolean | null;
-
-        /**
-         * Fail the entire job if OCR fails on any image. By default, OCR errors result in
-         * empty text for that image
-         */
-        fail_on_image_ocr_error?: boolean | null;
-
-        /**
-         * Fail the entire job if markdown cannot be reconstructed for any page. By
-         * default, failed pages use fallback text extraction
-         */
-        fail_on_markdown_reconstruction_error?: boolean | null;
-      }
-
-      /**
-       * Timeout settings for job execution. Increase for large or complex documents
-       */
-      export interface Timeouts {
-        /**
-         * Base timeout for the job in seconds (max 1800 = 30 minutes). This is the minimum
-         * time allowed regardless of document size
-         */
-        base_in_seconds?: number | null;
-
-        /**
-         * Additional timeout per page in seconds (max 300 = 5 minutes). Total timeout =
-         * base + (this value × page count)
-         */
-        extra_time_per_page_in_seconds?: number | null;
-      }
-    }
-
-    /**
-     * Document processing options including OCR, table extraction, and chart parsing
-     */
-    export interface ProcessingOptions {
-      /**
-       * Use aggressive heuristics to detect table boundaries, even without visible
-       * borders. Useful for documents with borderless or complex tables
-       */
-      aggressive_table_extraction?: boolean | null;
-
-      /**
-       * 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
-       */
-      auto_mode_configuration?: Array<ProcessingOptions.AutoModeConfiguration> | null;
-
-      /**
-       * 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.
-       */
-      cost_optimizer?: ProcessingOptions.CostOptimizer | null;
-
-      /**
-       * Disable automatic heuristics including outlined table extraction and adaptive
-       * long table handling. Use when heuristics produce incorrect results
-       */
-      disable_heuristics?: boolean | null;
-
-      /**
-       * Options for ignoring specific text types (diagonal, hidden, text in images)
-       */
-      ignore?: ProcessingOptions.Ignore;
-
-      /**
-       * OCR configuration including language detection settings
-       */
-      ocr_parameters?: ProcessingOptions.OcrParameters;
-
-      /**
-       * 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
-       */
-      specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient' | null;
-    }
-
-    export namespace ProcessingOptions {
-      /**
-       * A single auto mode rule with trigger conditions and parsing configuration.
-       *
-       * Auto mode allows conditional parsing where different configurations are applied
-       * based on page content, structure, or filename. When triggers match, the
-       * parsing_conf overrides default settings for that page.
-       */
-      export interface AutoModeConfiguration {
-        /**
-         * Parsing configuration to apply when trigger conditions are met
-         */
-        parsing_conf: AutoModeConfiguration.ParsingConf;
-
-        /**
-         * Single glob pattern to match against filename
-         */
-        filename_match_glob?: string | null;
-
-        /**
-         * List of glob patterns to match against filename
-         */
-        filename_match_glob_list?: Array<string> | null;
-
-        /**
-         * Regex pattern to match against filename
-         */
-        filename_regexp?: string | null;
-
-        /**
-         * Regex mode flags (e.g., 'i' for case-insensitive)
-         */
-        filename_regexp_mode?: string | null;
-
-        /**
-         * Trigger if page contains a full-page image (scanned page detection)
-         */
-        full_page_image_in_page?: boolean | null;
-
-        /**
-         * Threshold for full page image detection (0.0-1.0, default 0.8)
-         */
-        full_page_image_in_page_threshold?: number | string | null;
-
-        /**
-         * Trigger if page contains non-screenshot images
-         */
-        image_in_page?: boolean | null;
-
-        /**
-         * Trigger if page contains this layout element type
-         */
-        layout_element_in_page?: string | null;
-
-        /**
-         * Confidence threshold for layout element detection
-         */
-        layout_element_in_page_confidence_threshold?: number | string | null;
-
-        /**
-         * Trigger if page has more than N charts
-         */
-        page_contains_at_least_n_charts?: number | string | null;
-
-        /**
-         * Trigger if page has more than N images
-         */
-        page_contains_at_least_n_images?: number | string | null;
-
-        /**
-         * Trigger if page has more than N layout elements
-         */
-        page_contains_at_least_n_layout_elements?: number | string | null;
-
-        /**
-         * Trigger if page has more than N lines
-         */
-        page_contains_at_least_n_lines?: number | string | null;
-
-        /**
-         * Trigger if page has more than N links
-         */
-        page_contains_at_least_n_links?: number | string | null;
-
-        /**
-         * Trigger if page has more than N numeric words
-         */
-        page_contains_at_least_n_numbers?: number | string | null;
-
-        /**
-         * Trigger if page has more than N% numeric words
-         */
-        page_contains_at_least_n_percent_numbers?: number | string | null;
-
-        /**
-         * Trigger if page has more than N tables
-         */
-        page_contains_at_least_n_tables?: number | string | null;
-
-        /**
-         * Trigger if page has more than N words
-         */
-        page_contains_at_least_n_words?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N charts
-         */
-        page_contains_at_most_n_charts?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N images
-         */
-        page_contains_at_most_n_images?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N layout elements
-         */
-        page_contains_at_most_n_layout_elements?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N lines
-         */
-        page_contains_at_most_n_lines?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N links
-         */
-        page_contains_at_most_n_links?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N numeric words
-         */
-        page_contains_at_most_n_numbers?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N% numeric words
-         */
-        page_contains_at_most_n_percent_numbers?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N tables
-         */
-        page_contains_at_most_n_tables?: number | string | null;
-
-        /**
-         * Trigger if page has fewer than N words
-         */
-        page_contains_at_most_n_words?: number | string | null;
-
-        /**
-         * Trigger if page has more than N characters
-         */
-        page_longer_than_n_chars?: number | string | null;
-
-        /**
-         * Trigger on pages with markdown extraction errors
-         */
-        page_md_error?: boolean | null;
-
-        /**
-         * Trigger if page has fewer than N characters
-         */
-        page_shorter_than_n_chars?: number | string | null;
-
-        /**
-         * Regex pattern to match in page content
-         */
-        regexp_in_page?: string | null;
-
-        /**
-         * Regex mode flags for regexp_in_page
-         */
-        regexp_in_page_mode?: string | null;
-
-        /**
-         * Trigger if page contains a table
-         */
-        table_in_page?: boolean | null;
-
-        /**
-         * Trigger if page text/markdown contains this string
-         */
-        text_in_page?: string | null;
-
-        /**
-         * How to combine multiple trigger conditions: 'and' (all conditions must match,
-         * this is the default) or 'or' (any single condition can trigger)
-         */
-        trigger_mode?: string | null;
-      }
-
-      export namespace AutoModeConfiguration {
-        /**
-         * Parsing configuration to apply when trigger conditions are met
-         */
-        export interface ParsingConf {
-          /**
-           * Whether to use adaptive long table handling
-           */
-          adaptive_long_table?: boolean | null;
-
-          /**
-           * Whether to use aggressive table extraction
-           */
-          aggressive_table_extraction?: boolean | null;
-
-          /**
-           * Crop box options for auto mode parsing configuration.
-           */
-          crop_box?: ParsingConf.CropBox | null;
-
-          /**
-           * Custom AI instructions for matched pages. Overrides the base custom_prompt
-           */
-          custom_prompt?: string | null;
-
-          /**
-           * Whether to extract layout information
-           */
-          extract_layout?: boolean | null;
-
-          /**
-           * Whether to use high resolution OCR
-           */
-          high_res_ocr?: boolean | null;
-
-          /**
-           * Ignore options for auto mode parsing configuration.
-           */
-          ignore?: ParsingConf.Ignore | null;
-
-          /**
-           * Primary language of the document
-           */
-          language?: string | null;
-
-          /**
-           * Whether to use outlined table extraction
-           */
-          outlined_table_extraction?: boolean | null;
-
-          /**
-           * Presentation-specific options for auto mode parsing configuration.
-           */
-          presentation?: ParsingConf.Presentation | null;
-
-          /**
-           * Spatial text options for auto mode parsing configuration.
-           */
-          spatial_text?: ParsingConf.SpatialText | null;
-
-          /**
-           * Enable specialized chart parsing with the specified mode
-           */
-          specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient' | null;
-
-          /**
-           * Override the parsing tier for matched pages. Must be paired with version
-           */
-          tier?: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus' | null;
-
-          /**
-           * Tier version when overriding tier. Required when tier is specified
-           */
-          version?:
-            | '2025-12-11'
-            | '2025-12-18'
-            | '2025-12-31'
-            | '2026-01-08'
-            | '2026-01-09'
-            | '2026-01-16'
-            | '2026-01-21'
-            | '2026-01-22'
-            | '2026-01-24'
-            | '2026-01-29'
-            | '2026-01-30'
-            | '2026-02-03'
-            | '2026-02-18'
-            | '2026-02-20'
-            | '2026-02-24'
-            | '2026-02-26'
-            | '2026-03-02'
-            | '2026-03-03'
-            | '2026-03-04'
-            | '2026-03-05'
-            | '2026-03-09'
-            | '2026-03-10'
-            | '2026-03-11'
-            | '2026-03-12'
-            | '2026-03-17'
-            | '2026-03-19'
-            | '2026-03-20'
-            | '2026-03-22'
-            | '2026-03-23'
-            | '2026-03-24'
-            | '2026-03-25'
-            | '2026-03-26'
-            | '2026-03-27'
-            | 'latest'
-            | (string & {})
-            | null;
-        }
-
-        export namespace ParsingConf {
-          /**
-           * Crop box options for auto mode parsing configuration.
-           */
-          export interface CropBox {
-            /**
-             * Bottom boundary of crop box as ratio (0-1)
-             */
-            bottom?: number | null;
-
-            /**
-             * Left boundary of crop box as ratio (0-1)
-             */
-            left?: number | null;
-
-            /**
-             * Right boundary of crop box as ratio (0-1)
-             */
-            right?: number | null;
-
-            /**
-             * Top boundary of crop box as ratio (0-1)
-             */
-            top?: number | null;
-          }
-
-          /**
-           * Ignore options for auto mode parsing configuration.
-           */
-          export interface Ignore {
-            /**
-             * Whether to ignore diagonal text in the document
-             */
-            ignore_diagonal_text?: boolean | null;
-
-            /**
-             * Whether to ignore hidden text in the document
-             */
-            ignore_hidden_text?: boolean | null;
-          }
-
-          /**
-           * Presentation-specific options for auto mode parsing configuration.
-           */
-          export interface Presentation {
-            /**
-             * Extract out of bounds content in presentation slides
-             */
-            out_of_bounds_content?: boolean | null;
-
-            /**
-             * Skip extraction of embedded data for charts in presentation slides
-             */
-            skip_embedded_data?: boolean | null;
-          }
-
-          /**
-           * Spatial text options for auto mode parsing configuration.
-           */
-          export interface SpatialText {
-            /**
-             * Keep column structure intact without unrolling
-             */
-            do_not_unroll_columns?: boolean | null;
-
-            /**
-             * Preserve text alignment across page boundaries
-             */
-            preserve_layout_alignment_across_pages?: boolean | null;
-
-            /**
-             * Include very small text in spatial output
-             */
-            preserve_very_small_text?: boolean | null;
-          }
-        }
-      }
-
-      /**
-       * 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.
-       */
-      export interface CostOptimizer {
-        /**
-         * 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
-         */
-        enable?: boolean | null;
-      }
-
-      /**
-       * Options for ignoring specific text types (diagonal, hidden, text in images)
-       */
-      export interface Ignore {
-        /**
-         * Skip text rotated at an angle (not horizontal/vertical). Useful for ignoring
-         * watermarks or decorative angled text
-         */
-        ignore_diagonal_text?: boolean | null;
-
-        /**
-         * Skip text marked as hidden in the document structure. Some PDFs contain
-         * invisible text layers used for accessibility or search indexing
-         */
-        ignore_hidden_text?: boolean | null;
-
-        /**
-         * Skip OCR text extraction from embedded images. Use when images contain
-         * irrelevant text (watermarks, logos) that shouldn't be in the output
-         */
-        ignore_text_in_image?: boolean | null;
-      }
-
-      /**
-       * OCR configuration including language detection settings
-       */
-      export interface OcrParameters {
-        /**
-         * 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
-         */
-        languages?: Array<ParsingAPI.ParsingLanguages> | null;
-      }
-    }
-
-    /**
-     * Webhook configuration for receiving parsing job notifications.
-     *
-     * Webhooks are called when specified events occur during job processing. Configure
-     * multiple webhook configurations to send to different endpoints.
-     */
-    export interface WebhookConfiguration {
-      /**
-       * Events that trigger this webhook. Options: 'parse.success' (job completed),
-       * 'parse.failure' (job failed), 'parse.partial' (some pages failed). If not
-       * specified, webhook fires for all events
-       */
-      webhook_events?: Array<string> | null;
-
-      /**
-       * Custom HTTP headers to include in webhook requests. Use for authentication
-       * tokens or custom routing. Example: {'Authorization': 'Bearer xyz'}
-       */
-      webhook_headers?: { [key: string]: unknown } | null;
-
-      /**
-       * HTTPS URL to receive webhook POST requests. Must be publicly accessible
-       */
-      webhook_url?: string | null;
-    }
-  }
-
-  /**
-   * Catch-all for configurations without a dedicated typed schema.
-   *
-   * Accepts arbitrary JSON fields alongside `product_type`.
-   */
-  export interface UntypedParameters {
-    /**
-     * Product type.
-     */
-    product_type: 'unknown';
-
-    [k: string]: unknown;
-  }
-}
-
 export interface ExtractCreateParams {
   /**
-   * Body param: File ID or Parse Job ID to extract from
+   * Body param: File ID or parse job ID to extract from
    */
-  document_input_value: string;
+  file_input: string;
 
   /**
    * Query param
@@ -1857,8 +654,7 @@ export interface ExtractCreateParams {
   configuration?: ExtractConfiguration | null;
 
   /**
-   * Body param: Saved extract configuration ID (mutually exclusive with
-   * configuration)
+   * Body param: Saved configuration ID
    */
   configuration_id?: string | null;
 
@@ -1921,12 +717,12 @@ export interface ExtractListParams extends PaginatedCursorParams {
   configuration_id?: string | null;
 
   /**
-   * Include jobs created at or after this timestamp (inclusive)
+   * Include items created at or after this timestamp (inclusive)
    */
   created_at_on_or_after?: string | null;
 
   /**
-   * Include jobs created at or before this timestamp (inclusive)
+   * Include items created at or before this timestamp (inclusive)
    */
   created_at_on_or_before?: string | null;
 
@@ -1936,7 +732,7 @@ export interface ExtractListParams extends PaginatedCursorParams {
   document_input_type?: string | null;
 
   /**
-   * Filter by document input value
+   * @deprecated Deprecated: use file_input instead
    */
   document_input_value?: string | null;
 
@@ -1945,6 +741,11 @@ export interface ExtractListParams extends PaginatedCursorParams {
    */
   expand?: Array<string>;
 
+  /**
+   * Filter by file input value
+   */
+  file_input?: string | null;
+
   /**
    * Filter by specific job IDs
    */
@@ -2033,7 +834,6 @@ export declare namespace Extract {
     type ExtractV2SchemaValidateResponse as ExtractV2SchemaValidateResponse,
     type ExtractedFieldMetadata as ExtractedFieldMetadata,
     type ExtractDeleteResponse as ExtractDeleteResponse,
-    type ExtractGenerateSchemaResponse as ExtractGenerateSchemaResponse,
     type ExtractV2JobsPaginatedCursor as ExtractV2JobsPaginatedCursor,
     type ExtractCreateParams as ExtractCreateParams,
     type ExtractListParams as ExtractListParams,