@kreuzberg/node 4.7.3 → 4.8.0

package/README.md

@@ -22,7 +22,7 @@
     <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java&color=007ec6" alt="Java">
   </a>
   <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
-    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.7.3" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.8.0" alt="Go">
   </a>
   <a href="https://www.nuget.org/packages/Kreuzberg/">
     <img src="https://img.shields.io/nuget/v/Kreuzberg?label=C%23&color=007ec6" alt="C#">
@@ -42,7 +42,7 @@
 
   <!-- Project Info -->
   <a href="https://github.com/kreuzberg-dev/kreuzberg/blob/main/LICENSE">
-    <img src="https://img.shields.io/badge/License-MIT-007ec6" alt="License">
+    <img src="https://img.shields.io/badge/License-Elastic--2.0-blue.svg" alt="License">
   </a>
   <a href="https://docs.kreuzberg.dev">
     <img src="https://img.shields.io/badge/docs-kreuzberg.dev-007ec6" alt="Documentation">
@@ -525,7 +525,7 @@ Contributions are welcome! See [Contributing Guide](https://github.com/kreuzberg
 
 ## License
 
-MIT License - see LICENSE file for details.
+Elastic License 2.0 (ELv2) - see [LICENSE](../../LICENSE) for details.
 
 ## Support
 

package/dist/errors.d.mts

@@ -70,7 +70,11 @@ declare enum ErrorCode {
     /**
      * Required system dependency is missing
      */
-    MissingDependency = 7
+    MissingDependency = 7,
+    /**
+     * Error during embedding generation
+     */
+    Embedding = 8
 }
 /**
  * Context information for panics in native code.
@@ -353,5 +357,30 @@ declare class PluginError extends KreuzbergError {
 declare class MissingDependencyError extends KreuzbergError {
     constructor(message: string, panicContext?: PanicContext | null);
 }
+/**
+ * Error thrown when text embedding generation fails.
+ *
+ * Embedding errors occur during vector generation, such as:
+ * - Model loading failures
+ * - Inference engine errors
+ * - Invalid input text for the selected model
+ * - Resource exhaustion during batch processing
+ *
+ * @example
+ * ```typescript
+ * import { embed, EmbeddingError } from '@kreuzberg/node';
+ *
+ * try {
+ *   const result = await embed(['hello world']);
+ * } catch (error) {
+ *   if (error instanceof EmbeddingError) {
+ *     console.error('Embedding generation failed:', error.message);
+ *   }
+ * }
+ * ```
+ */
+declare class EmbeddingError extends KreuzbergError {
+    constructor(message: string, panicContext?: PanicContext | null);
+}
 
-export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, type PanicContext, ParsingError, PluginError, ValidationError };
+export { CacheError, EmbeddingError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, type PanicContext, ParsingError, PluginError, ValidationError };

package/dist/errors.d.ts

@@ -70,7 +70,11 @@ declare enum ErrorCode {
     /**
      * Required system dependency is missing
      */
-    MissingDependency = 7
+    MissingDependency = 7,
+    /**
+     * Error during embedding generation
+     */
+    Embedding = 8
 }
 /**
  * Context information for panics in native code.
@@ -353,5 +357,30 @@ declare class PluginError extends KreuzbergError {
 declare class MissingDependencyError extends KreuzbergError {
     constructor(message: string, panicContext?: PanicContext | null);
 }
+/**
+ * Error thrown when text embedding generation fails.
+ *
+ * Embedding errors occur during vector generation, such as:
+ * - Model loading failures
+ * - Inference engine errors
+ * - Invalid input text for the selected model
+ * - Resource exhaustion during batch processing
+ *
+ * @example
+ * ```typescript
+ * import { embed, EmbeddingError } from '@kreuzberg/node';
+ *
+ * try {
+ *   const result = await embed(['hello world']);
+ * } catch (error) {
+ *   if (error instanceof EmbeddingError) {
+ *     console.error('Embedding generation failed:', error.message);
+ *   }
+ * }
+ * ```
+ */
+declare class EmbeddingError extends KreuzbergError {
+    constructor(message: string, panicContext?: PanicContext | null);
+}
 
-export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, type PanicContext, ParsingError, PluginError, ValidationError };
+export { CacheError, EmbeddingError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, type PanicContext, ParsingError, PluginError, ValidationError };

package/dist/errors.js

@@ -21,6 +21,7 @@ var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: tru
 var errors_exports = {};
 __export(errors_exports, {
   CacheError: () => CacheError,
+  EmbeddingError: () => EmbeddingError,
   ErrorCode: () => ErrorCode,
   ImageProcessingError: () => ImageProcessingError,
   KreuzbergError: () => KreuzbergError,
@@ -40,6 +41,7 @@ var ErrorCode = /* @__PURE__ */ ((ErrorCode2) => {
   ErrorCode2[ErrorCode2["ParsingError"] = 5] = "ParsingError";
   ErrorCode2[ErrorCode2["OcrError"] = 6] = "OcrError";
   ErrorCode2[ErrorCode2["MissingDependency"] = 7] = "MissingDependency";
+  ErrorCode2[ErrorCode2["Embedding"] = 8] = "Embedding";
   return ErrorCode2;
 })(ErrorCode || {});
 var KreuzbergError = class _KreuzbergError extends Error {
@@ -126,9 +128,17 @@ var MissingDependencyError = class _MissingDependencyError extends KreuzbergErro
     Object.setPrototypeOf(this, _MissingDependencyError.prototype);
   }
 };
+var EmbeddingError = class _EmbeddingError extends KreuzbergError {
+  constructor(message, panicContext) {
+    super(message, panicContext);
+    this.name = "EmbeddingError";
+    Object.setPrototypeOf(this, _EmbeddingError.prototype);
+  }
+};
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
   CacheError,
+  EmbeddingError,
   ErrorCode,
   ImageProcessingError,
   KreuzbergError,

package/dist/errors.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install Tesseract OCR for image processing');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAhCW,SAAAA;AAAA,GAAA;AAyGL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAwBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;","names":["ErrorCode"]}
+{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n\t/**\n\t * Error during embedding generation\n\t */\n\tEmbedding = 8,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install Tesseract OCR for image processing');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n\n/**\n * Error thrown when text embedding generation fails.\n *\n * Embedding errors occur during vector generation, such as:\n * - Model loading failures\n * - Inference engine errors\n * - Invalid input text for the selected model\n * - Resource exhaustion during batch processing\n *\n * @example\n * ```typescript\n * import { embed, EmbeddingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await embed(['hello world']);\n * } catch (error) {\n *   if (error instanceof EmbeddingError) {\n *     console.error('Embedding generation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class EmbeddingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"EmbeddingError\";\n\t\tObject.setPrototypeOf(this, EmbeddingError.prototype);\n\t}\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAIA,EAAAA,sBAAA,eAAY,KAAZ;AApCW,SAAAA;AAAA,GAAA;AA6GL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAwBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;AAwBO,IAAM,iBAAN,MAAM,wBAAuB,eAAe;AAAA,EAClD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AACD;","names":["ErrorCode"]}

package/dist/errors.mjs

@@ -8,6 +8,7 @@ var ErrorCode = /* @__PURE__ */ ((ErrorCode2) => {
   ErrorCode2[ErrorCode2["ParsingError"] = 5] = "ParsingError";
   ErrorCode2[ErrorCode2["OcrError"] = 6] = "OcrError";
   ErrorCode2[ErrorCode2["MissingDependency"] = 7] = "MissingDependency";
+  ErrorCode2[ErrorCode2["Embedding"] = 8] = "Embedding";
   return ErrorCode2;
 })(ErrorCode || {});
 var KreuzbergError = class _KreuzbergError extends Error {
@@ -94,8 +95,16 @@ var MissingDependencyError = class _MissingDependencyError extends KreuzbergErro
     Object.setPrototypeOf(this, _MissingDependencyError.prototype);
   }
 };
+var EmbeddingError = class _EmbeddingError extends KreuzbergError {
+  constructor(message, panicContext) {
+    super(message, panicContext);
+    this.name = "EmbeddingError";
+    Object.setPrototypeOf(this, _EmbeddingError.prototype);
+  }
+};
 export {
   CacheError,
+  EmbeddingError,
   ErrorCode,
   ImageProcessingError,
   KreuzbergError,

package/dist/errors.mjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install Tesseract OCR for image processing');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n"],"mappings":";AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAhCW,SAAAA;AAAA,GAAA;AAyGL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAwBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;","names":["ErrorCode"]}
+{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n\t/**\n\t * Error during embedding generation\n\t */\n\tEmbedding = 8,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install Tesseract OCR for image processing');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n\n/**\n * Error thrown when text embedding generation fails.\n *\n * Embedding errors occur during vector generation, such as:\n * - Model loading failures\n * - Inference engine errors\n * - Invalid input text for the selected model\n * - Resource exhaustion during batch processing\n *\n * @example\n * ```typescript\n * import { embed, EmbeddingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await embed(['hello world']);\n * } catch (error) {\n *   if (error instanceof EmbeddingError) {\n *     console.error('Embedding generation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class EmbeddingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"EmbeddingError\";\n\t\tObject.setPrototypeOf(this, EmbeddingError.prototype);\n\t}\n}\n"],"mappings":";AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAIA,EAAAA,sBAAA,eAAY,KAAZ;AApCW,SAAAA;AAAA,GAAA;AA6GL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAwBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;AAwBO,IAAM,iBAAN,MAAM,wBAAuB,eAAe;AAAA,EAClD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AACD;","names":["ErrorCode"]}

package/dist/index.d.mts

@@ -1,7 +1,7 @@
-import { ErrorClassification, ExtractionConfig, ExtractionResult, WorkerPool, WorkerPoolStats, PostProcessorProtocol, ValidatorProtocol, OcrBackendProtocol } from './types.mjs';
-export { Chunk, ChunkingConfig, ExtractedImage, HtmlConversionOptions, HtmlPreprocessingOptions, ImageExtractionConfig, KeywordConfig, LanguageDetectionConfig, OcrConfig, PageContent, PageExtractionConfig, PdfConfig, PostProcessorConfig, Table, TesseractConfig, TokenReductionConfig } from './types.mjs';
+import { ErrorClassification, ExtractionConfig, ExtractionResult, WorkerPool, WorkerPoolStats, PostProcessorProtocol, ValidatorProtocol, OcrBackendProtocol, EmbeddingConfig } from './types.mjs';
+export { Chunk, ChunkingConfig, EmbeddingModelType, ExtractedImage, HtmlConversionOptions, HtmlPreprocessingOptions, ImageExtractionConfig, KeywordConfig, LanguageDetectionConfig, OcrConfig, PageContent, PageExtractionConfig, PdfConfig, PostProcessorConfig, Table, TesseractConfig, TokenReductionConfig } from './types.mjs';
 import { PanicContext } from './errors.mjs';
-export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, ParsingError, PluginError, ValidationError } from './errors.mjs';
+export { CacheError, EmbeddingError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, ParsingError, PluginError, ValidationError } from './errors.mjs';
 
 /**
  * Get the error code for the last FFI error.
@@ -18,6 +18,7 @@ export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDep
  * - 5: ParsingError
  * - 6: OcrError
  * - 7: MissingDependency
+ * - 8: Embedding
  *
  * @returns The integer error code
  *
@@ -67,8 +68,8 @@ declare function getLastPanicContext(): PanicContext | null;
  * Maps numeric error codes to their string names, providing a consistent way
  * to get error code names across all platforms.
  *
- * @param code - The numeric error code (0-7)
- * @returns The error code name as a string (e.g., "validation", "ocr", "unknown")
+ * @param code - The numeric error code (0-8)
+ * @returns The error code name as a string (e.g., "validation", "ocr", "embedding")
  *
  * @example
  * ```typescript
@@ -85,7 +86,7 @@ declare function getErrorCodeName(code: number): string;
  *
  * Retrieves user-friendly descriptions of error types from the FFI layer.
  *
- * @param code - The numeric error code (0-7)
+ * @param code - The numeric error code (0-8)
  * @returns A brief description of the error type
  *
  * @example
@@ -112,8 +113,9 @@ declare function getErrorCodeDescription(code: number): string;
  * - **MissingDependency (3)**: Keywords like "not found", "missing", "dependency"
  * - **Io (4)**: Keywords like "file", "disk", "read", "write", "permission"
  * - **Plugin (5)**: Keywords like "plugin", "register", "extension"
- * - **UnsupportedFormat (6)**: Keywords like "unsupported", "format", "mime"
- * - **Internal (7)**: Keywords like "internal", "bug", "panic"
+ * - **UnsupportedFormat (6)**: Keywords: unsupported, format, mime
+ * - **Internal (7)**: Keywords: internal, bug, panic
+ * - **Embedding (8)**: Keywords: embed, embedding, vector, inference
  *
  * @param errorMessage - The error message string to classify
  * @returns An object with the classification details
@@ -1210,6 +1212,50 @@ declare function listEmbeddingPresets(): string[];
  * ```
  */
 declare function getEmbeddingPreset(name: string): EmbeddingPreset | null;
+/**
+ * Generate vector embeddings for a list of texts (synchronous).
+ *
+ * Requires the `embeddings` feature to be enabled (ONNX Runtime must be available).
+ * Returns one float32 array per input text. An empty input returns an empty array.
+ *
+ * @param texts - Array of strings to embed
+ * @param config - Optional embedding configuration (model preset, batch size, normalization)
+ * @returns Array of float32 arrays (one embedding vector per input text)
+ *
+ * @throws {Error} If ONNX Runtime is not available or the model cannot be loaded
+ *
+ * @example
+ * ```typescript
+ * import { embedSync } from '@kreuzberg/node';
+ *
+ * const embeddings = embedSync(['Hello, world!'], { model: { type: 'preset', name: 'balanced' } });
+ * console.log(embeddings.length); // 1
+ * console.log(embeddings[0].length); // 768
+ * ```
+ */
+declare function embedSync(texts: string[], config?: EmbeddingConfig): number[][];
+/**
+ * Generate vector embeddings for a list of texts (asynchronous).
+ *
+ * Requires the `embeddings` feature to be enabled (ONNX Runtime must be available).
+ * Returns one float32 array per input text. An empty input returns an empty array.
+ *
+ * @param texts - Array of strings to embed
+ * @param config - Optional embedding configuration (model preset, batch size, normalization)
+ * @returns Promise resolving to an array of float32 arrays (one embedding vector per input text)
+ *
+ * @throws {Error} If ONNX Runtime is not available or the model cannot be loaded
+ *
+ * @example
+ * ```typescript
+ * import { embed } from '@kreuzberg/node';
+ *
+ * const embeddings = await embed(['Hello, world!'], { model: { type: 'preset', name: 'balanced' } });
+ * console.log(embeddings.length); // 1
+ * console.log(embeddings[0].length); // 768
+ * ```
+ */
+declare function embed(texts: string[], config?: EmbeddingConfig): Promise<number[][]>;
 
 /**
  * @internal Allows tests to provide a mocked native binding.
@@ -1282,6 +1328,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.7.3";
+declare const __version__ = "4.8.0";
 
-export { type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, PdfPageIterator, type PdfPageResult, PostProcessorProtocol, ValidatorProtocol, WorkerPool, WorkerPoolStats, __resetBindingForTests, __setBindingForTests, __version__, batchExtractBytes, batchExtractBytesSync, batchExtractFiles, batchExtractFilesInWorker, batchExtractFilesSync, classifyError, clearDocumentExtractors, clearOcrBackends, clearPostProcessors, clearValidators, closeWorkerPool, createWorkerPool, detectMimeType, detectMimeTypeFromPath, extractBytes, extractBytesSync, extractFile, extractFileInWorker, extractFileSync, getEmbeddingPreset, getErrorCodeDescription, getErrorCodeName, getExtensionsForMime, getLastErrorCode, getLastPanicContext, getWorkerPoolStats, iteratePdfPages, iteratePdfPagesSync, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, pdfPageCount, registerOcrBackend, registerPostProcessor, registerValidator, renderPdfPage, renderPdfPageSync, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };
+export { EmbeddingConfig, type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, PdfPageIterator, type PdfPageResult, PostProcessorProtocol, ValidatorProtocol, WorkerPool, WorkerPoolStats, __resetBindingForTests, __setBindingForTests, __version__, batchExtractBytes, batchExtractBytesSync, batchExtractFiles, batchExtractFilesInWorker, batchExtractFilesSync, classifyError, clearDocumentExtractors, clearOcrBackends, clearPostProcessors, clearValidators, closeWorkerPool, createWorkerPool, detectMimeType, detectMimeTypeFromPath, embed, embedSync, extractBytes, extractBytesSync, extractFile, extractFileInWorker, extractFileSync, getEmbeddingPreset, getErrorCodeDescription, getErrorCodeName, getExtensionsForMime, getLastErrorCode, getLastPanicContext, getWorkerPoolStats, iteratePdfPages, iteratePdfPagesSync, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, pdfPageCount, registerOcrBackend, registerPostProcessor, registerValidator, renderPdfPage, renderPdfPageSync, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };

package/dist/index.d.ts

@@ -1,7 +1,7 @@
-import { ErrorClassification, ExtractionConfig, ExtractionResult, WorkerPool, WorkerPoolStats, PostProcessorProtocol, ValidatorProtocol, OcrBackendProtocol } from './types.js';
-export { Chunk, ChunkingConfig, ExtractedImage, HtmlConversionOptions, HtmlPreprocessingOptions, ImageExtractionConfig, KeywordConfig, LanguageDetectionConfig, OcrConfig, PageContent, PageExtractionConfig, PdfConfig, PostProcessorConfig, Table, TesseractConfig, TokenReductionConfig } from './types.js';
+import { ErrorClassification, ExtractionConfig, ExtractionResult, WorkerPool, WorkerPoolStats, PostProcessorProtocol, ValidatorProtocol, OcrBackendProtocol, EmbeddingConfig } from './types.js';
+export { Chunk, ChunkingConfig, EmbeddingModelType, ExtractedImage, HtmlConversionOptions, HtmlPreprocessingOptions, ImageExtractionConfig, KeywordConfig, LanguageDetectionConfig, OcrConfig, PageContent, PageExtractionConfig, PdfConfig, PostProcessorConfig, Table, TesseractConfig, TokenReductionConfig } from './types.js';
 import { PanicContext } from './errors.js';
-export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, ParsingError, PluginError, ValidationError } from './errors.js';
+export { CacheError, EmbeddingError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, ParsingError, PluginError, ValidationError } from './errors.js';
 
 /**
  * Get the error code for the last FFI error.
@@ -18,6 +18,7 @@ export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDep
  * - 5: ParsingError
  * - 6: OcrError
  * - 7: MissingDependency
+ * - 8: Embedding
  *
  * @returns The integer error code
  *
@@ -67,8 +68,8 @@ declare function getLastPanicContext(): PanicContext | null;
  * Maps numeric error codes to their string names, providing a consistent way
  * to get error code names across all platforms.
  *
- * @param code - The numeric error code (0-7)
- * @returns The error code name as a string (e.g., "validation", "ocr", "unknown")
+ * @param code - The numeric error code (0-8)
+ * @returns The error code name as a string (e.g., "validation", "ocr", "embedding")
  *
  * @example
  * ```typescript
@@ -85,7 +86,7 @@ declare function getErrorCodeName(code: number): string;
  *
  * Retrieves user-friendly descriptions of error types from the FFI layer.
  *
- * @param code - The numeric error code (0-7)
+ * @param code - The numeric error code (0-8)
  * @returns A brief description of the error type
  *
  * @example
@@ -112,8 +113,9 @@ declare function getErrorCodeDescription(code: number): string;
  * - **MissingDependency (3)**: Keywords like "not found", "missing", "dependency"
  * - **Io (4)**: Keywords like "file", "disk", "read", "write", "permission"
  * - **Plugin (5)**: Keywords like "plugin", "register", "extension"
- * - **UnsupportedFormat (6)**: Keywords like "unsupported", "format", "mime"
- * - **Internal (7)**: Keywords like "internal", "bug", "panic"
+ * - **UnsupportedFormat (6)**: Keywords: unsupported, format, mime
+ * - **Internal (7)**: Keywords: internal, bug, panic
+ * - **Embedding (8)**: Keywords: embed, embedding, vector, inference
  *
  * @param errorMessage - The error message string to classify
  * @returns An object with the classification details
@@ -1210,6 +1212,50 @@ declare function listEmbeddingPresets(): string[];
  * ```
  */
 declare function getEmbeddingPreset(name: string): EmbeddingPreset | null;
+/**
+ * Generate vector embeddings for a list of texts (synchronous).
+ *
+ * Requires the `embeddings` feature to be enabled (ONNX Runtime must be available).
+ * Returns one float32 array per input text. An empty input returns an empty array.
+ *
+ * @param texts - Array of strings to embed
+ * @param config - Optional embedding configuration (model preset, batch size, normalization)
+ * @returns Array of float32 arrays (one embedding vector per input text)
+ *
+ * @throws {Error} If ONNX Runtime is not available or the model cannot be loaded
+ *
+ * @example
+ * ```typescript
+ * import { embedSync } from '@kreuzberg/node';
+ *
+ * const embeddings = embedSync(['Hello, world!'], { model: { type: 'preset', name: 'balanced' } });
+ * console.log(embeddings.length); // 1
+ * console.log(embeddings[0].length); // 768
+ * ```
+ */
+declare function embedSync(texts: string[], config?: EmbeddingConfig): number[][];
+/**
+ * Generate vector embeddings for a list of texts (asynchronous).
+ *
+ * Requires the `embeddings` feature to be enabled (ONNX Runtime must be available).
+ * Returns one float32 array per input text. An empty input returns an empty array.
+ *
+ * @param texts - Array of strings to embed
+ * @param config - Optional embedding configuration (model preset, batch size, normalization)
+ * @returns Promise resolving to an array of float32 arrays (one embedding vector per input text)
+ *
+ * @throws {Error} If ONNX Runtime is not available or the model cannot be loaded
+ *
+ * @example
+ * ```typescript
+ * import { embed } from '@kreuzberg/node';
+ *
+ * const embeddings = await embed(['Hello, world!'], { model: { type: 'preset', name: 'balanced' } });
+ * console.log(embeddings.length); // 1
+ * console.log(embeddings[0].length); // 768
+ * ```
+ */
+declare function embed(texts: string[], config?: EmbeddingConfig): Promise<number[][]>;
 
 /**
  * @internal Allows tests to provide a mocked native binding.
@@ -1282,6 +1328,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.7.3";
+declare const __version__ = "4.8.0";
 
-export { type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, PdfPageIterator, type PdfPageResult, PostProcessorProtocol, ValidatorProtocol, WorkerPool, WorkerPoolStats, __resetBindingForTests, __setBindingForTests, __version__, batchExtractBytes, batchExtractBytesSync, batchExtractFiles, batchExtractFilesInWorker, batchExtractFilesSync, classifyError, clearDocumentExtractors, clearOcrBackends, clearPostProcessors, clearValidators, closeWorkerPool, createWorkerPool, detectMimeType, detectMimeTypeFromPath, extractBytes, extractBytesSync, extractFile, extractFileInWorker, extractFileSync, getEmbeddingPreset, getErrorCodeDescription, getErrorCodeName, getExtensionsForMime, getLastErrorCode, getLastPanicContext, getWorkerPoolStats, iteratePdfPages, iteratePdfPagesSync, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, pdfPageCount, registerOcrBackend, registerPostProcessor, registerValidator, renderPdfPage, renderPdfPageSync, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };
+export { EmbeddingConfig, type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, PdfPageIterator, type PdfPageResult, PostProcessorProtocol, ValidatorProtocol, WorkerPool, WorkerPoolStats, __resetBindingForTests, __setBindingForTests, __version__, batchExtractBytes, batchExtractBytesSync, batchExtractFiles, batchExtractFilesInWorker, batchExtractFilesSync, classifyError, clearDocumentExtractors, clearOcrBackends, clearPostProcessors, clearValidators, closeWorkerPool, createWorkerPool, detectMimeType, detectMimeTypeFromPath, embed, embedSync, extractBytes, extractBytesSync, extractFile, extractFileInWorker, extractFileSync, getEmbeddingPreset, getErrorCodeDescription, getErrorCodeName, getExtensionsForMime, getLastErrorCode, getLastPanicContext, getWorkerPoolStats, iteratePdfPages, iteratePdfPagesSync, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, pdfPageCount, registerOcrBackend, registerPostProcessor, registerValidator, renderPdfPage, renderPdfPageSync, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };

package/dist/index.js

@@ -21,6 +21,7 @@ var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: tru
 var index_exports = {};
 __export(index_exports, {
   CacheError: () => CacheError,
+  EmbeddingError: () => EmbeddingError,
   ErrorCode: () => ErrorCode,
   ExtractionConfig: () => ExtractionConfig,
   ImageProcessingError: () => ImageProcessingError,
@@ -48,6 +49,8 @@ __export(index_exports, {
   createWorkerPool: () => createWorkerPool,
   detectMimeType: () => detectMimeType,
   detectMimeTypeFromPath: () => detectMimeTypeFromPath,
+  embed: () => embed,
+  embedSync: () => embedSync,
   extractBytes: () => extractBytes,
   extractBytesSync: () => extractBytesSync,
   extractFile: () => extractFile,
@@ -224,6 +227,7 @@ var ErrorCode = /* @__PURE__ */ ((ErrorCode2) => {
   ErrorCode2[ErrorCode2["ParsingError"] = 5] = "ParsingError";
   ErrorCode2[ErrorCode2["OcrError"] = 6] = "OcrError";
   ErrorCode2[ErrorCode2["MissingDependency"] = 7] = "MissingDependency";
+  ErrorCode2[ErrorCode2["Embedding"] = 8] = "Embedding";
   return ErrorCode2;
 })(ErrorCode || {});
 var KreuzbergError = class _KreuzbergError extends Error {
@@ -310,6 +314,13 @@ var MissingDependencyError = class _MissingDependencyError extends KreuzbergErro
     Object.setPrototypeOf(this, _MissingDependencyError.prototype);
   }
 };
+var EmbeddingError = class _EmbeddingError extends KreuzbergError {
+  constructor(message, panicContext) {
+    super(message, panicContext);
+    this.name = "EmbeddingError";
+    Object.setPrototypeOf(this, _EmbeddingError.prototype);
+  }
+};
 
 // typescript/core/assertions.ts
 function assertUint8Array(value, name) {
@@ -1232,12 +1243,21 @@ function getEmbeddingPreset(name) {
   const result = binding2.getEmbeddingPreset(name);
   return result;
 }
+function embedSync(texts, config) {
+  const binding2 = getBinding();
+  return binding2.embedSync(texts, config ?? null);
+}
+async function embed(texts, config) {
+  const binding2 = getBinding();
+  return binding2.embed(texts, config ?? null);
+}
 
 // typescript/index.ts
-var __version__ = "4.7.3";
+var __version__ = "4.8.0";
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
   CacheError,
+  EmbeddingError,
   ErrorCode,
   ExtractionConfig,
   ImageProcessingError,
@@ -1265,6 +1285,8 @@ var __version__ = "4.7.3";
   createWorkerPool,
   detectMimeType,
   detectMimeTypeFromPath,
+  embed,
+  embedSync,
   extractBytes,
   extractBytesSync,
   extractFile,