pulse-ts-sdk 1.0.7 → 1.0.9

package/dist/esm/api/types/ExtractOptions.d.mts

@@ -10,6 +10,8 @@ export interface ExtractOptions {
     figureProcessing?: ExtractOptions.FigureProcessing;
     /** Settings that enable additional processing passes or alternate output formats. Each enabled extension produces a corresponding output field under `response.extensions.*`. */
     extensions?: ExtractOptions.Extensions;
+    /** Settings for Excel/spreadsheet extraction. Controls handling of hidden rows, columns, and sheets. Only applies to `.xlsx` and `.xls` files. Accepts both camelCase and snake_case field names. */
+    spreadsheet?: ExtractOptions.Spreadsheet;
     /** Options for persisting extraction artifacts. When enabled (default), artifacts are saved to storage and a database record is created. */
     storage?: ExtractOptions.Storage;
     /** If true, returns immediately with a job_id for polling via GET /job/{jobId}. Otherwise processes synchronously. */
@@ -56,8 +58,6 @@ export declare namespace ExtractOptions {
      * Settings that enable additional processing passes or alternate output formats. Each enabled extension produces a corresponding output field under `response.extensions.*`.
      */
     interface Extensions {
-        /** Merge tables that span multiple pages into a single table. */
-        mergeTables?: boolean;
         /** Link footnote markers to their corresponding footnote text. */
         footnoteReferences?: boolean;
         /** Chunking configuration. When provided, the document is split into chunks using the specified strategies. Results appear in `response.extensions.chunking`. */
@@ -99,6 +99,17 @@ export declare namespace ExtractOptions {
             returnXml?: boolean;
         }
     }
+    /**
+     * Settings for Excel/spreadsheet extraction. Controls handling of hidden rows, columns, and sheets. Only applies to `.xlsx` and `.xls` files. Accepts both camelCase and snake_case field names.
+     */
+    interface Spreadsheet {
+        /** Include rows that are hidden in the Excel workbook. */
+        includeHiddenRows?: boolean;
+        /** Include columns that are hidden in the Excel workbook. */
+        includeHiddenCols?: boolean;
+        /** Include sheets that are hidden in the Excel workbook. */
+        includeHiddenSheets?: boolean;
+    }
     /**
      * Options for persisting extraction artifacts. When enabled (default), artifacts are saved to storage and a database record is created.
      */

package/dist/esm/api/types/ExtractResponse.d.mts

@@ -1,6 +1,6 @@
 import type * as Pulse from "../index.mjs";
 /**
- * Full extraction result returned by the synchronous `/extract` endpoint. Contains the extracted markdown, optional extensions output, bounding boxes, and storage metadata.
+ * Full extraction result returned by the synchronous `/extract` endpoint. Inherits all core fields and adds deprecated backward-compatibility fields.
  */
 export interface ExtractResponse {
     /** Primary markdown content extracted from the document. Always present in the new format. */
@@ -19,6 +19,8 @@ export interface ExtractResponse {
     plan_info?: ExtractResponse.PlanInfo;
     /** Non-fatal warnings generated during extraction. Includes deprecation notices when legacy input parameters are used, as well as processing warnings (e.g. word-level bounding box limitations). */
     warnings?: string[];
+    /** Number of credits consumed by this request. Only present when the organization has the credit billing system enabled. */
+    credits_used?: number | null;
     /** **Deprecated** — Use `extensions.altOutputs.html` instead. HTML representation of the extracted content. Present when the legacy `returnHtml` input was used. */
     html?: string;
     /** **Deprecated** — Use `extensions.chunking` instead. Document content split into chunks. Present when the legacy `chunking` input was used. */
@@ -45,8 +47,6 @@ export declare namespace ExtractResponse {
     interface Extensions {
         /** Chunk results by strategy. Present when `extensions.chunking` was provided in the request. */
         chunking?: Extensions.Chunking;
-        /** Merge tables result/metadata. Present when `extensions.mergeTables` was enabled. */
-        mergeTables?: Record<string, unknown>;
         /** List of detected footnotes with their in-text references. Present when `extensions.footnoteReferences` was enabled. Each item links a footnote paragraph to the body-text paragraphs that reference it, using bounding-box text IDs. */
         footnoteReferences?: Extensions.FootnoteReferences.Item[];
         /** Alternate output formats. Each key corresponds to an enabled alt output. */

package/dist/esm/api/types/ExtractResultCore.d.mts

@@ -0,0 +1,112 @@
+/**
+ * Core extraction result fields shared by the synchronous `/extract` endpoint and the pipeline extract step.
+ */
+export interface ExtractResultCore {
+    /** Primary markdown content extracted from the document. Always present in the new format. */
+    markdown?: string;
+    /** Output from enabled extensions. Each key corresponds to an extension that was enabled in the request under `extensions.*`. Only keys for enabled extensions are present. */
+    extensions?: ExtractResultCore.Extensions;
+    /** Positional bounding-box data for text, titles, headers, footers, images, and tables. Used by the frontend for annotation overlays. */
+    bounding_boxes?: Record<string, unknown>;
+    /** Persisted extraction ID. Present when storage is enabled (default). Use this ID with `/split` and `/schema` endpoints. */
+    extraction_id?: string;
+    /** URL to view the extraction on the Pulse platform. Present when storage is enabled. */
+    extraction_url?: string;
+    /** Number of pages processed. */
+    page_count?: number;
+    /** Billing tier and usage information. */
+    plan_info?: ExtractResultCore.PlanInfo;
+    /** Non-fatal warnings generated during extraction. Includes deprecation notices when legacy input parameters are used, as well as processing warnings (e.g. word-level bounding box limitations). */
+    warnings?: string[];
+    /** Number of credits consumed by this request. Only present when the organization has the credit billing system enabled. */
+    credits_used?: number | null;
+}
+export declare namespace ExtractResultCore {
+    /**
+     * Output from enabled extensions. Each key corresponds to an extension that was enabled in the request under `extensions.*`. Only keys for enabled extensions are present.
+     */
+    interface Extensions {
+        /** Chunk results by strategy. Present when `extensions.chunking` was provided in the request. */
+        chunking?: Extensions.Chunking;
+        /** List of detected footnotes with their in-text references. Present when `extensions.footnoteReferences` was enabled. Each item links a footnote paragraph to the body-text paragraphs that reference it, using bounding-box text IDs. */
+        footnoteReferences?: Extensions.FootnoteReferences.Item[];
+        /** Alternate output formats. Each key corresponds to an enabled alt output. */
+        altOutputs?: Extensions.AltOutputs;
+    }
+    namespace Extensions {
+        /**
+         * Chunk results by strategy. Present when `extensions.chunking` was provided in the request.
+         */
+        interface Chunking {
+            /** Semantically-segmented chunks. */
+            semantic?: string[];
+            /** Chunks split by document headers/headings. */
+            header?: string[];
+            /** One chunk per page. */
+            page?: string[];
+            /** Recursively-split chunks respecting size limits. */
+            recursive?: string[];
+        }
+        type FootnoteReferences = FootnoteReferences.Item[];
+        namespace FootnoteReferences {
+            interface Item {
+                /** The footnote marker symbol (e.g. "*", "†", "1", "#"). */
+                symbol?: string;
+                /** The bounding-box text ID (e.g. "txt-15") of the footnote explanation paragraph. */
+                footnoteTextId?: string;
+                /** Bounding-box text IDs of body-text paragraphs that contain a reference to this footnote marker. */
+                referenceTextIds?: string[];
+            }
+        }
+        /**
+         * Alternate output formats. Each key corresponds to an enabled alt output.
+         */
+        interface AltOutputs {
+            /** Word-level bounding box data. Present when `extensions.altOutputs.wlbb` was enabled and input is a PDF. */
+            wlbb?: AltOutputs.Wlbb;
+            /** HTML representation of the document. Present when `extensions.altOutputs.returnHtml` was enabled. */
+            html?: string;
+            /** XML representation of the document. Present when `extensions.altOutputs.returnXml` was enabled. (WIP) */
+            xml?: string;
+        }
+        namespace AltOutputs {
+            /**
+             * Word-level bounding box data. Present when `extensions.altOutputs.wlbb` was enabled and input is a PDF.
+             */
+            interface Wlbb {
+                /** List of detected words with their positions. */
+                words?: Wlbb.Words.Item[];
+                /** Error message if word-level extraction failed. */
+                error?: string;
+            }
+            namespace Wlbb {
+                type Words = Words.Item[];
+                namespace Words {
+                    interface Item {
+                        /** Unique identifier for the word (e.g. "w-1", "w-2", …). */
+                        id?: string;
+                        /** The recognised word text. */
+                        text?: string;
+                        /** 1-indexed page number in the original document. */
+                        page_number?: number;
+                        /** Flat 4-corner polygon: [x1,y1, x2,y2, x3,y3, x4,y4]. All coordinates normalised to 0–1 range. */
+                        bounding_box?: number[];
+                        /** Recognition confidence score (0–1). */
+                        average_word_confidence?: number;
+                    }
+                }
+            }
+        }
+    }
+    /**
+     * Billing tier and usage information.
+     */
+    interface PlanInfo {
+        /** Current plan tier name. */
+        tier?: string;
+        /** Cumulative pages used after this extraction. */
+        pages_used?: number;
+        /** Human-readable plan note. */
+        note?: string;
+    }
+}

package/dist/esm/api/types/ExtractResultCore.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/GoneErrorBody.d.mts

@@ -0,0 +1,9 @@
+export interface GoneErrorBody {
+    error?: GoneErrorBody.Error_;
+}
+export declare namespace GoneErrorBody {
+    interface Error_ {
+        code?: string;
+        message?: string;
+    }
+}

package/dist/esm/api/types/GoneErrorBody.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/JobStatusResponse.d.mts

@@ -10,7 +10,7 @@ export interface JobStatusResponse {
     created_at: string;
     /** Timestamp of the last status update, if available. */
     updated_at?: string;
-    /** Structured payload that contains output when the job is completed. */
+    /** Structured payload returned when the job completes.  For large extractions (70+ pages) this object contains `is_url: true` and a single-use `url` to download the full result via `GET /large_results/{jobId}`. */
     result?: Record<string, unknown>;
     /** Error message describing why the job failed, if applicable. */
     error?: string;

package/dist/esm/api/types/PipelineBatchExtractResult.d.mts

@@ -0,0 +1,13 @@
+/**
+ * Result from the batch_extract step in a pipeline.
+ */
+export interface PipelineBatchExtractResult {
+    /** List of extraction IDs for each processed file. */
+    extraction_ids?: string[];
+    /** Number of files processed. */
+    total_files?: number;
+    /** Step execution time in seconds. */
+    latency?: number;
+    /** Accepts any additional properties */
+    [key: string]: any;
+}

package/dist/esm/api/types/PipelineBatchExtractResult.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/PipelineExecuteMultipartInput.d.mts

@@ -0,0 +1,13 @@
+/**
+ * Multipart form-data request body for ad-hoc pipeline execution. Upload file(s) directly and provide step configs as a JSON string.
+ */
+export interface PipelineExecuteMultipartInput {
+    /** Document file to upload. For batch_extract, multiple `file` fields can be provided. */
+    file?: string;
+    /** JSON string containing the step configurations (same structure as `PipelineSteps`). */
+    steps: string;
+    /** Set to `"true"` for async execution. */
+    async?: string;
+    /** Set to `"true"` for zero-retention mode. */
+    auto_delete?: string;
+}

package/dist/esm/api/types/PipelineExecuteMultipartInput.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/PipelineExecuteResponse.d.mts

@@ -0,0 +1,21 @@
+import type * as Pulse from "../index.mjs";
+/**
+ * Synchronous pipeline execution result. Contains the status, total latency, and results from each step.
+ */
+export interface PipelineExecuteResponse {
+    /** Pipeline execution status. */
+    status: PipelineExecuteResponse.Status;
+    /** Total pipeline execution time in seconds. */
+    total_latency?: number;
+    /** Per-step results. */
+    results: Pulse.PipelineResults;
+    /** Present and true when auto-delete mode was used. Confirms that artifacts have been purged. */
+    auto_delete?: boolean;
+}
+export declare namespace PipelineExecuteResponse {
+    /** Pipeline execution status. */
+    const Status: {
+        readonly Completed: "completed";
+    };
+    type Status = (typeof Status)[keyof typeof Status];
+}

package/dist/esm/api/types/PipelineExecuteResponse.mjs

@@ -0,0 +1,8 @@
+// This file was auto-generated by Fern from our API Definition.
+export var PipelineExecuteResponse;
+(function (PipelineExecuteResponse) {
+    /** Pipeline execution status. */
+    PipelineExecuteResponse.Status = {
+        Completed: "completed",
+    };
+})(PipelineExecuteResponse || (PipelineExecuteResponse = {}));

package/dist/esm/api/types/PipelineExtractResult.d.mts

@@ -0,0 +1,118 @@
+/**
+ * Result from the extract step in a pipeline. Inherits all core extraction fields and adds pipeline-specific timing.
+ */
+export interface PipelineExtractResult {
+    /** Primary markdown content extracted from the document. Always present in the new format. */
+    markdown?: string;
+    /** Output from enabled extensions. Each key corresponds to an extension that was enabled in the request under `extensions.*`. Only keys for enabled extensions are present. */
+    extensions?: PipelineExtractResult.Extensions;
+    /** Positional bounding-box data for text, titles, headers, footers, images, and tables. Used by the frontend for annotation overlays. */
+    bounding_boxes?: Record<string, unknown>;
+    /** Persisted extraction ID. Present when storage is enabled (default). Use this ID with `/split` and `/schema` endpoints. */
+    extraction_id?: string;
+    /** URL to view the extraction on the Pulse platform. Present when storage is enabled. */
+    extraction_url?: string;
+    /** Number of pages processed. */
+    page_count?: number;
+    /** Billing tier and usage information. */
+    plan_info?: PipelineExtractResult.PlanInfo;
+    /** Non-fatal warnings generated during extraction. Includes deprecation notices when legacy input parameters are used, as well as processing warnings (e.g. word-level bounding box limitations). */
+    warnings?: string[];
+    /** Number of credits consumed by this request. Only present when the organization has the credit billing system enabled. */
+    credits_used?: number | null;
+    /** Number of pages processed. Convenience alias for `page_count`. */
+    pages?: number;
+    /** Step execution time in seconds. */
+    latency?: number;
+    /** Accepts any additional properties */
+    [key: string]: any;
+}
+export declare namespace PipelineExtractResult {
+    /**
+     * Output from enabled extensions. Each key corresponds to an extension that was enabled in the request under `extensions.*`. Only keys for enabled extensions are present.
+     */
+    interface Extensions {
+        /** Chunk results by strategy. Present when `extensions.chunking` was provided in the request. */
+        chunking?: Extensions.Chunking;
+        /** List of detected footnotes with their in-text references. Present when `extensions.footnoteReferences` was enabled. Each item links a footnote paragraph to the body-text paragraphs that reference it, using bounding-box text IDs. */
+        footnoteReferences?: Extensions.FootnoteReferences.Item[];
+        /** Alternate output formats. Each key corresponds to an enabled alt output. */
+        altOutputs?: Extensions.AltOutputs;
+    }
+    namespace Extensions {
+        /**
+         * Chunk results by strategy. Present when `extensions.chunking` was provided in the request.
+         */
+        interface Chunking {
+            /** Semantically-segmented chunks. */
+            semantic?: string[];
+            /** Chunks split by document headers/headings. */
+            header?: string[];
+            /** One chunk per page. */
+            page?: string[];
+            /** Recursively-split chunks respecting size limits. */
+            recursive?: string[];
+        }
+        type FootnoteReferences = FootnoteReferences.Item[];
+        namespace FootnoteReferences {
+            interface Item {
+                /** The footnote marker symbol (e.g. "*", "†", "1", "#"). */
+                symbol?: string;
+                /** The bounding-box text ID (e.g. "txt-15") of the footnote explanation paragraph. */
+                footnoteTextId?: string;
+                /** Bounding-box text IDs of body-text paragraphs that contain a reference to this footnote marker. */
+                referenceTextIds?: string[];
+            }
+        }
+        /**
+         * Alternate output formats. Each key corresponds to an enabled alt output.
+         */
+        interface AltOutputs {
+            /** Word-level bounding box data. Present when `extensions.altOutputs.wlbb` was enabled and input is a PDF. */
+            wlbb?: AltOutputs.Wlbb;
+            /** HTML representation of the document. Present when `extensions.altOutputs.returnHtml` was enabled. */
+            html?: string;
+            /** XML representation of the document. Present when `extensions.altOutputs.returnXml` was enabled. (WIP) */
+            xml?: string;
+        }
+        namespace AltOutputs {
+            /**
+             * Word-level bounding box data. Present when `extensions.altOutputs.wlbb` was enabled and input is a PDF.
+             */
+            interface Wlbb {
+                /** List of detected words with their positions. */
+                words?: Wlbb.Words.Item[];
+                /** Error message if word-level extraction failed. */
+                error?: string;
+            }
+            namespace Wlbb {
+                type Words = Words.Item[];
+                namespace Words {
+                    interface Item {
+                        /** Unique identifier for the word (e.g. "w-1", "w-2", …). */
+                        id?: string;
+                        /** The recognised word text. */
+                        text?: string;
+                        /** 1-indexed page number in the original document. */
+                        page_number?: number;
+                        /** Flat 4-corner polygon: [x1,y1, x2,y2, x3,y3, x4,y4]. All coordinates normalised to 0–1 range. */
+                        bounding_box?: number[];
+                        /** Recognition confidence score (0–1). */
+                        average_word_confidence?: number;
+                    }
+                }
+            }
+        }
+    }
+    /**
+     * Billing tier and usage information.
+     */
+    interface PlanInfo {
+        /** Current plan tier name. */
+        tier?: string;
+        /** Cumulative pages used after this extraction. */
+        pages_used?: number;
+        /** Human-readable plan note. */
+        note?: string;
+    }
+}

package/dist/esm/api/types/PipelineExtractResult.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/PipelineResults.d.mts

@@ -0,0 +1,14 @@
+import type * as Pulse from "../index.mjs";
+/**
+ * Results from each pipeline step, keyed by step name. Only steps that were executed are present.
+ */
+export interface PipelineResults {
+    /** Extract step result. */
+    extract?: Pulse.PipelineExtractResult;
+    /** Batch extract step result. */
+    batch_extract?: Pulse.PipelineBatchExtractResult;
+    /** Schema step result. */
+    schema?: Pulse.PipelineSchemaResult;
+    /** Split step result. */
+    split?: Pulse.PipelineSplitResult;
+}

package/dist/esm/api/types/PipelineResults.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/PipelineSchemaResult.d.mts

@@ -0,0 +1,14 @@
+import type * as Pulse from "../index.mjs";
+/**
+ * Result from the schema step in a pipeline.
+ */
+export interface PipelineSchemaResult {
+    /** Persisted schema version ID. */
+    schema_id?: string;
+    /** Extracted values and citations. */
+    schema_output?: Pulse.StructuredOutputResult;
+    /** Step execution time in seconds. */
+    latency?: number;
+    /** Accepts any additional properties */
+    [key: string]: any;
+}

package/dist/esm/api/types/PipelineSchemaResult.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/PipelineSplitResult.d.mts

@@ -0,0 +1,18 @@
+import type * as Pulse from "../index.mjs";
+/**
+ * Result from the split step in a pipeline. Inherits all core split fields and adds pipeline-specific timing and input echo.
+ */
+export interface PipelineSplitResult {
+    /** Unique identifier for this split result. Use this ID with the `/schema` endpoint (split mode) to apply schemas to specific page groups. */
+    split_id?: string;
+    /** Page assignments per topic. */
+    split_output?: Pulse.SplitOutput;
+    /** Number of credits consumed by this request. Only present when the organization has the credit billing system enabled. */
+    credits_used?: number | null;
+    /** Echo of the topic definitions used. */
+    split_input?: Pulse.TopicDefinition[];
+    /** Step execution time in seconds. */
+    latency?: number;
+    /** Accepts any additional properties */
+    [key: string]: any;
+}

package/dist/esm/api/types/PipelineSplitResult.mjs

@@ -0,0 +1,2 @@
+// This file was auto-generated by Fern from our API Definition.
+export {};

package/dist/esm/api/types/PipelineStepBatchExtractConfig.d.mts

@@ -0,0 +1,146 @@
+import type * as Pulse from "../index.mjs";
+/**
+ * Configuration for the batch_extract step. Same extract options as `POST /extract` (applied to every file) plus file inputs and a `workers` field for parallelism. Provide files via `file_urls` (URL list) or `files` (base64 inline uploads).
+ */
+export interface PipelineStepBatchExtractConfig {
+    /** Extraction model to use. When set to `enterprise-preview`, routes the request through Pulse's self-hosted VPC extraction model instead of the default cloud-based service. If omitted or set to any other value, the default model is used. */
+    model?: PipelineStepBatchExtractConfig.Model;
+    /** Page range filter supporting segments such as `1-2` or mixed ranges like `1-2,5`. */
+    pages?: string;
+    /** Settings that control how figures in the document are processed. These affect the markdown output directly (e.g. figure descriptions, chart-to-table conversion, image embedding) and do not produce additional output fields in the response. */
+    figureProcessing?: PipelineStepBatchExtractConfig.FigureProcessing;
+    /** Settings that enable additional processing passes or alternate output formats. Each enabled extension produces a corresponding output field under `response.extensions.*`. */
+    extensions?: PipelineStepBatchExtractConfig.Extensions;
+    /** Settings for Excel/spreadsheet extraction. Controls handling of hidden rows, columns, and sheets. Only applies to `.xlsx` and `.xls` files. Accepts both camelCase and snake_case field names. */
+    spreadsheet?: PipelineStepBatchExtractConfig.Spreadsheet;
+    /** Options for persisting extraction artifacts. When enabled (default), artifacts are saved to storage and a database record is created. */
+    storage?: PipelineStepBatchExtractConfig.Storage;
+    /** If true, returns immediately with a job_id for polling via GET /job/{jobId}. Otherwise processes synchronously. */
+    async?: boolean;
+    /** **⚠️ DEPRECATED** — Use the `/schema` endpoint after extraction instead. Pass the `extraction_id` from the extract response to `/schema` with your `schema_config`. This parameter still works for backward compatibility but will be removed in a future version. */
+    structuredOutput?: PipelineStepBatchExtractConfig.StructuredOutput;
+    /** (Deprecated) JSON schema describing structured data to extract. Use structuredOutput instead. Accepts either a JSON object or a stringified JSON representation. */
+    schema?: PipelineStepBatchExtractConfig.Schema;
+    /** (Deprecated) Natural language prompt for schema-guided extraction. Use structuredOutput.schemaPrompt instead. */
+    schemaPrompt?: string;
+    /** (Deprecated) Custom instructions that augment the default extraction behaviour. Use `figureProcessing` or `extensions` instead. */
+    customPrompt?: string;
+    /** **⚠️ DEPRECATED** — Use `extensions.chunking.chunkTypes` instead. Comma-separated list of chunking strategies to apply (for example `semantic,header,page,recursive`). Still accepted for backward compatibility. */
+    chunking?: string;
+    /** **⚠️ DEPRECATED** — Use `extensions.chunking.chunkSize` instead. Override for maximum characters per chunk when chunking is enabled. */
+    chunkSize?: number;
+    /** **⚠️ DEPRECATED** — Toggle to enable figure extraction in results. */
+    extractFigure?: boolean;
+    /** **⚠️ DEPRECATED** — Use `figureProcessing.description` instead. Toggle to generate descriptive captions for extracted figures. */
+    figureDescription?: boolean;
+    /** **⚠️ DEPRECATED** — Use `figureProcessing.showImages` instead. Embed base64-encoded images inline in figure tags in the output. Increases response size. */
+    showImages?: boolean;
+    /** **⚠️ DEPRECATED** — Use `extensions.altOutputs.returnHtml` instead. Whether to include HTML representation alongside markdown in the response. */
+    returnHtml?: boolean;
+    /** (Deprecated) Enables expanded rationale output for debugging. */
+    thinking?: boolean;
+    /** List of document URLs to process in parallel. */
+    file_urls?: string[];
+    /** Inline file uploads. Each entry contains a filename and base64-encoded file content. Use instead of `file_urls` when you have local files. */
+    files?: Pulse.BatchFileUpload[];
+    /** Number of parallel workers. */
+    workers?: number;
+}
+export declare namespace PipelineStepBatchExtractConfig {
+    /** Extraction model to use. When set to `enterprise-preview`, routes the request through Pulse's self-hosted VPC extraction model instead of the default cloud-based service. If omitted or set to any other value, the default model is used. */
+    const Model: {
+        readonly EnterprisePreview: "enterprise-preview";
+    };
+    type Model = (typeof Model)[keyof typeof Model];
+    /**
+     * Settings that control how figures in the document are processed. These affect the markdown output directly (e.g. figure descriptions, chart-to-table conversion, image embedding) and do not produce additional output fields in the response.
+     */
+    interface FigureProcessing {
+        /** Generate descriptive captions for extracted figures. */
+        description?: boolean;
+        /** Embed base64-encoded images inline in figure tags in the output. Increases response size. */
+        showImages?: boolean;
+    }
+    /**
+     * Settings that enable additional processing passes or alternate output formats. Each enabled extension produces a corresponding output field under `response.extensions.*`.
+     */
+    interface Extensions {
+        /** Link footnote markers to their corresponding footnote text. */
+        footnoteReferences?: boolean;
+        /** Chunking configuration. When provided, the document is split into chunks using the specified strategies. Results appear in `response.extensions.chunking`. */
+        chunking?: Extensions.Chunking;
+        /** Alternate output format options. Each enabled format produces a corresponding field under `response.extensions.altOutputs`. */
+        altOutputs?: Extensions.AltOutputs;
+    }
+    namespace Extensions {
+        /**
+         * Chunking configuration. When provided, the document is split into chunks using the specified strategies. Results appear in `response.extensions.chunking`.
+         */
+        interface Chunking {
+            /** List of chunking strategies to apply (e.g. `["semantic", "header", "page", "recursive"]`). */
+            chunkTypes?: Chunking.ChunkTypes.Item[];
+            /** Maximum characters per chunk. */
+            chunkSize?: number;
+        }
+        namespace Chunking {
+            type ChunkTypes = ChunkTypes.Item[];
+            namespace ChunkTypes {
+                const Item: {
+                    readonly Semantic: "semantic";
+                    readonly Header: "header";
+                    readonly Page: "page";
+                    readonly Recursive: "recursive";
+                };
+                type Item = (typeof Item)[keyof typeof Item];
+            }
+        }
+        /**
+         * Alternate output format options. Each enabled format produces a corresponding field under `response.extensions.altOutputs`.
+         */
+        interface AltOutputs {
+            /** Enable word-level bounding boxes. Runs an additional OCR model to derive bounding boxes for each word. Only applies to PDFs. Results in `response.extensions.altOutputs.wlbb`. */
+            wlbb?: boolean;
+            /** Include an HTML representation of the document. When enabled, `response.markdown` is still present and the HTML is available at `response.extensions.altOutputs.html`. */
+            returnHtml?: boolean;
+            /** Include an XML representation of the document. Results in `response.extensions.altOutputs.xml`. (Work in progress.) */
+            returnXml?: boolean;
+        }
+    }
+    /**
+     * Settings for Excel/spreadsheet extraction. Controls handling of hidden rows, columns, and sheets. Only applies to `.xlsx` and `.xls` files. Accepts both camelCase and snake_case field names.
+     */
+    interface Spreadsheet {
+        /** Include rows that are hidden in the Excel workbook. */
+        includeHiddenRows?: boolean;
+        /** Include columns that are hidden in the Excel workbook. */
+        includeHiddenCols?: boolean;
+        /** Include sheets that are hidden in the Excel workbook. */
+        includeHiddenSheets?: boolean;
+    }
+    /**
+     * Options for persisting extraction artifacts. When enabled (default), artifacts are saved to storage and a database record is created.
+     */
+    interface Storage {
+        /** Whether to persist extraction artifacts. Set to false for temporary extractions with no storage or database record. */
+        enabled?: boolean;
+        /** Target folder name to save the extraction to. Creates the folder if it doesn't exist. */
+        folderName?: string;
+        /** Target folder ID to save the extraction to. Takes precedence over folderName if both are provided. */
+        folderId?: string;
+    }
+    /**
+     * **⚠️ DEPRECATED** — Use the `/schema` endpoint after extraction instead. Pass the `extraction_id` from the extract response to `/schema` with your `schema_config`. This parameter still works for backward compatibility but will be removed in a future version.
+     */
+    interface StructuredOutput {
+        /** JSON schema describing the structured data to extract. */
+        schema?: Record<string, unknown>;
+        /** Natural language prompt with additional extraction instructions. */
+        schemaPrompt?: string;
+        /** Use higher quality model for better results. When true, uses a more capable model at the cost of higher latency. */
+        effort?: boolean;
+    }
+    /**
+     * (Deprecated) JSON schema describing structured data to extract. Use structuredOutput instead. Accepts either a JSON object or a stringified JSON representation.
+     */
+    type Schema = Record<string, unknown> | string;
+}

package/dist/esm/api/types/PipelineStepBatchExtractConfig.mjs

@@ -0,0 +1,23 @@
+// This file was auto-generated by Fern from our API Definition.
+export var PipelineStepBatchExtractConfig;
+(function (PipelineStepBatchExtractConfig) {
+    /** Extraction model to use. When set to `enterprise-preview`, routes the request through Pulse's self-hosted VPC extraction model instead of the default cloud-based service. If omitted or set to any other value, the default model is used. */
+    PipelineStepBatchExtractConfig.Model = {
+        EnterprisePreview: "enterprise-preview",
+    };
+    let Extensions;
+    (function (Extensions) {
+        let Chunking;
+        (function (Chunking) {
+            let ChunkTypes;
+            (function (ChunkTypes) {
+                ChunkTypes.Item = {
+                    Semantic: "semantic",
+                    Header: "header",
+                    Page: "page",
+                    Recursive: "recursive",
+                };
+            })(ChunkTypes = Chunking.ChunkTypes || (Chunking.ChunkTypes = {}));
+        })(Chunking = Extensions.Chunking || (Extensions.Chunking = {}));
+    })(Extensions = PipelineStepBatchExtractConfig.Extensions || (PipelineStepBatchExtractConfig.Extensions = {}));
+})(PipelineStepBatchExtractConfig || (PipelineStepBatchExtractConfig = {}));