@kreuzberg/node 4.4.4 → 4.4.6

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=v4.4.4" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.4.6" 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#">
@@ -33,6 +33,9 @@
   <a href="https://rubygems.org/gems/kreuzberg">
     <img src="https://img.shields.io/gem/v/kreuzberg?label=Ruby&color=007ec6" alt="Ruby">
   </a>
+  <a href="https://kreuzberg-dev.r-universe.dev/kreuzberg">
+    <img src="https://img.shields.io/badge/R-kreuzberg-007ec6" alt="R">
+  </a>
   <a href="https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/kreuzberg">
     <img src="https://img.shields.io/badge/Docker-007ec6?logo=docker&logoColor=white" alt="Docker">
   </a>
@@ -55,7 +58,7 @@
 </div>
 
 
-Extract text, tables, images, and metadata from 75+ file formats including PDF, Office documents, and images. Native NAPI-RS bindings for Node.js with superior performance, async/await support, and TypeScript type definitions.
+Extract text, tables, images, and metadata from 88+ file formats including PDF, Office documents, and images. Native NAPI-RS bindings for Node.js with superior performance, async/await support, and TypeScript type definitions.
 
 
 ## Installation
@@ -95,16 +98,9 @@ yarn add @kreuzberg/node
 ### System Requirements
 
 - **Node.js 22+** required (NAPI-RS native bindings)
-- Optional: [ONNX Runtime](https://github.com/microsoft/onnxruntime/releases) version 1.24+ for embeddings support
+- Optional: [ONNX Runtime](https://github.com/microsoft/onnxruntime/releases) version 1.22.x for embeddings support
 - Optional: [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) for OCR functionality
 
-**Format Support Notes:**
-- Legacy formats (DOC, XLS, PPT) are now extracted natively without external tools
-- Modern Office formats (DOCX, XLSX, PPTX) are fully supported
-- WASM binding supports all document formats via in-memory parsing
-
-
-
 ### Platform Support
 
 Pre-built binaries available for:
@@ -320,19 +316,21 @@ This binding uses NAPI-RS to provide native Node.js bindings with:
 
 ## Features
 
-### Supported File Formats (75+)
+### Supported File Formats (88+)
 
-75+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+88+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
 
 #### Office Documents
 
 | Category | Formats | Capabilities |
 |----------|---------|--------------|
-| **Word Processing** | `.docx`, `.odt` | Full text, tables, images, metadata, styles |
-| **Spreadsheets** | `.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.xla`, `.xlam`, `.xltm`, `.ods` | Sheet data, formulas, cell metadata, charts |
-| **Presentations** | `.pptx`, `.ppt`, `.ppsx` | Slides, speaker notes, images, metadata |
+| **Word Processing** | `.docx`, `.docm`, `.dotx`, `.dotm`, `.dot`, `.odt` | Full text, tables, images, metadata, styles |
+| **Spreadsheets** | `.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.xla`, `.xlam`, `.xltm`, `.xltx`, `.xlt`, `.ods` | Sheet data, formulas, cell metadata, charts |
+| **Presentations** | `.pptx`, `.pptm`, `.ppsx`, `.potx`, `.potm`, `.pot`, `.ppt` | Slides, speaker notes, images, metadata |
 | **PDF** | `.pdf` | Text, tables, images, metadata, OCR support |
 | **eBooks** | `.epub`, `.fb2` | Chapters, metadata, embedded resources |
+| **Database** | `.dbf` | Table data extraction, field type support |
+| **Hangul** | `.hwp`, `.hwpx` | Korean document format, text extraction |
 
 #### Images (OCR-Enabled)
 

package/dist/index.d.mts

@@ -1191,6 +1191,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.4.4";
+declare const __version__ = "4.4.6";
 
 export { type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, 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, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, registerOcrBackend, registerPostProcessor, registerValidator, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };

package/dist/index.d.ts

@@ -1191,6 +1191,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.4.4";
+declare const __version__ = "4.4.6";
 
 export { type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, 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, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, registerOcrBackend, registerPostProcessor, registerValidator, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };

package/dist/index.js

@@ -368,6 +368,9 @@ function normalizeChunkingConfig(chunking) {
   setIfDefined(normalized, "preset", chunking.preset);
   setIfDefined(normalized, "embedding", chunking.embedding);
   setIfDefined(normalized, "enabled", chunking.enabled);
+  setIfDefined(normalized, "sizingType", chunking.sizingType);
+  setIfDefined(normalized, "sizingModel", chunking.sizingModel);
+  setIfDefined(normalized, "sizingCacheDir", chunking.sizingCacheDir);
   return normalized;
 }
 function normalizeImageExtractionConfig(images) {
@@ -594,7 +597,25 @@ function convertChunk(rawChunk) {
       // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       firstPage: metadata["first_page"] ?? metadata["firstPage"] ?? null,
       // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
-      lastPage: metadata["last_page"] ?? metadata["lastPage"] ?? null
+      lastPage: metadata["last_page"] ?? metadata["lastPage"] ?? null,
+      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
+      headingContext: (() => {
+        const hc = metadata["heading_context"] ?? metadata["headingContext"];
+        if (!hc) return null;
+        const headings = hc["headings"];
+        if (!Array.isArray(headings)) return null;
+        return {
+          headings: headings.map((h) => {
+            const heading = h;
+            return {
+              // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
+              level: heading["level"] ?? 0,
+              // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
+              text: heading["text"] ?? ""
+            };
+          })
+        };
+      })()
     }
   };
 }
@@ -1197,7 +1218,7 @@ function getEmbeddingPreset(name) {
 }
 
 // typescript/index.ts
-var __version__ = "4.4.4";
+var __version__ = "4.4.6";
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
   CacheError,