Nomad changes

crates/kreuzberg-wasm/Cargo.toml

@@ -0,0 +1,47 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# Issues & docs: https://github.com/kreuzberg-dev/alef
+
+[package]
+name = "kreuzberg-wasm"
+version = "5.0.0-rc.3"
+edition = "2024"
+license = "Elastic-2.0"
+description = "High-performance document intelligence library"
+repository = "https://github.com/kreuzberg-dev/kreuzberg"
+keywords = ["document", "extraction", "pdf", "ocr", "text"]
+
+[package.metadata.cargo-machete]
+ignored = [
+    "futures",
+    "futures-util",
+    "js-sys",
+    "wasm-bindgen-futures",
+    "serde",
+    "serde_json",
+]
+
+[package.metadata.wasm-pack.profile.release]
+wasm-opt = false
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+async-trait = "0.1"
+futures = "0.3"
+futures-util = "0.3"
+js-sys = "0.3"
+kreuzberg = { path = "../kreuzberg", default-features = false, features = ["wasm-target"] }
+serde = { version = "1", features = ["derive"] }
+serde-wasm-bindgen = "0.6"
+serde_json = "1"
+wasm-bindgen = "0.2"
+wasm-bindgen-futures = "0.4"
+
+[target.'cfg(target_arch = "wasm32")'.dependencies]
+getrandom = { version = "0.4", features = ["wasm_js"] }
+getrandom_03 = { package = "getrandom", version = "0.3", features = ["wasm_js"] }
+getrandom_02 = { package = "getrandom", version = "0.2", features = ["js"] }

crates/kreuzberg-wasm/LICENSE

@@ -0,0 +1,93 @@
+Elastic License 2.0 (ELv2)
+
+Copyright 2025-2026 Kreuzberg, Inc.
+
+Acceptance
+
+By using the software, you agree to all of the terms and conditions below.
+
+Copyright License
+
+The licensor grants you a non-exclusive, royalty-free, worldwide,
+non-sublicensable, non-transferable license to use, copy, distribute, make
+available, and prepare derivative works of the software, in each case subject to
+the limitations and conditions below.
+
+Limitations
+
+You may not provide the software to third parties as a hosted or managed
+service, where the service provides users with access to any substantial set of
+the features or functionality of the software.
+
+You may not move, change, disable, or circumvent the license key functionality
+in the software, and you may not remove or obscure any functionality in the
+software that is protected by the license key.
+
+You may not alter, remove, or obscure any licensing, copyright, or other notices
+of the licensor in the software. Any use of the licensor's trademarks is subject
+to applicable law.
+
+Patents
+
+The licensor grants you a license, under any patent claims the licensor can
+license, or becomes able to license, to make, have made, use, sell, offer for
+sale, import and have imported the software, in each case subject to the
+limitations and conditions in this license. This license does not cover any
+patent claims that you cause to be infringed by modifications or additions to the
+software. If you or your company make any written claim that the software
+infringes or contributes to infringement of any patent, your patent license for
+the software granted under these terms ends immediately. If your company makes
+such a claim, your patent license ends immediately for work on behalf of your
+company.
+
+Notices
+
+You must ensure that anyone who gets a copy of any part of the software from you
+also gets a copy of these terms.
+
+If you modify the software, you must include in any modified copies of the
+software prominent notices stating that you have modified the software.
+
+No Other Rights
+
+These terms do not imply any licenses other than those expressly granted in
+these terms.
+
+Termination
+
+If you use the software in violation of these terms, such use is not licensed,
+and your licenses will automatically terminate. If the licensor provides you with
+a notice of your violation, and you cease all violation of this license no later
+than 30 days after you receive that notice, your licenses will be reinstated
+retroactively. However, if you violate these terms after such reinstatement, any
+additional violation of these terms will cause your licenses to terminate
+automatically and permanently.
+
+No Liability
+
+As far as the law allows, the software comes as is, without any warranty or
+condition, and the licensor will not be liable to you for any damages arising out
+of these terms or the use or nature of the software, under any kind of legal
+claim.
+
+Definitions
+
+The licensor is the entity offering these terms, and the software is the
+software the licensor makes available under these terms, including any portion
+of it.
+
+you refers to the individual or entity agreeing to these terms.
+
+your company is any legal entity, sole proprietorship, or other kind of
+organization that you work for, plus all organizations that have control over,
+are under the control of, or are under common control with that organization.
+control means ownership of substantially all the assets of an entity, or the
+power to direct its management and policies by vote, contract, or otherwise.
+Control can be direct or indirect.
+
+your licenses are all the licenses granted to you for the software under these
+terms.
+
+use means anything you do with the software requiring one of your licenses.
+
+trademark means trademarks, service marks, and similar rights.

crates/kreuzberg-wasm/README.md

@@ -0,0 +1,498 @@
+# WebAssembly
+
+<div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
+  <a href="https://github.com/kreuzberg-dev/alef">
+    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+  </a>
+  <!-- Language Bindings -->
+  <a href="https://crates.io/crates/kreuzberg">
+    <img src="https://img.shields.io/crates/v/kreuzberg?label=Rust&color=007ec6" alt="Rust">
+  </a>
+  <a href="https://pypi.org/project/kreuzberg/">
+    <img src="https://img.shields.io/pypi/v/kreuzberg?label=Python&color=007ec6" alt="Python">
+  </a>
+  <a href="https://www.npmjs.com/package/@kreuzberg/node">
+    <img src="https://img.shields.io/npm/v/@kreuzberg/node?label=Node.js&color=007ec6" alt="Node.js">
+  </a>
+  <a href="https://www.npmjs.com/package/@kreuzberg/wasm">
+    <img src="https://img.shields.io/npm/v/@kreuzberg/wasm?label=WASM&color=007ec6" alt="WASM">
+  </a>
+  <a href="https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg">
+    <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/tree/main/packages/go/v5">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v5*" 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#">
+  </a>
+  <a href="https://packagist.org/packages/kreuzberg/kreuzberg">
+    <img src="https://img.shields.io/packagist/v/kreuzberg/kreuzberg?label=PHP&color=007ec6" alt="PHP">
+  </a>
+  <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://hex.pm/packages/kreuzberg">
+    <img src="https://img.shields.io/hexpm/v/kreuzberg?label=Elixir&color=007ec6" alt="Elixir">
+  </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://pub.dev/packages/kreuzberg">
+    <img src="https://img.shields.io/pub/v/kreuzberg?label=Dart&color=007ec6" alt="Dart">
+  </a>
+  <a href="https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg-android">
+    <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg-android?label=Kotlin&color=007ec6" alt="Kotlin">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/tree/main/packages/swift">
+    <img src="https://img.shields.io/badge/Swift-SPM-007ec6" alt="Swift">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/tree/main/packages/zig">
+    <img src="https://img.shields.io/badge/Zig-package-007ec6" alt="Zig">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
+    <img src="https://img.shields.io/badge/C-FFI-007ec6" alt="C FFI">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/kreuzberg">
+    <img src="https://img.shields.io/badge/Docker-ghcr.io-007ec6?logo=docker&logoColor=white" alt="Docker">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/charts%2Fkreuzberg">
+    <img src="https://img.shields.io/badge/Helm-ghcr.io-007ec6?logo=helm&logoColor=white" alt="Helm">
+  </a>
+
+  <!-- Project Info -->
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/License-Elastic--2.0-007ec6" alt="License">
+  </a>
+  <a href="https://docs.kreuzberg.dev">
+    <img src="https://img.shields.io/badge/Docs-kreuzberg-007ec6" alt="Documentation">
+  </a>
+  <a href="https://huggingface.co/Kreuzberg">
+    <img src="https://img.shields.io/badge/Hugging%20Face-Kreuzberg-007ec6" alt="Hugging Face">
+  </a>
+</div>
+
+<div align="center" style="margin: 24px 0 0;">
+  <a href="https://kreuzberg.dev">
+    <img alt="Kreuzberg" src="https://github.com/user-attachments/assets/419fc06c-8313-4324-b159-4b4d3cfce5c0" />
+  </a>
+</div>
+
+<div align="center" style="display: flex; flex-wrap: wrap; gap: 12px; justify-content: center; margin: 28px 0 24px;">
+  <a href="https://discord.gg/xt9WY3GnKR">
+    <img height="22" src="https://img.shields.io/badge/Discord-Chat-007ec6?logo=discord&logoColor=white" alt="Join Discord">
+  </a>
+  <a href="https://docs.kreuzberg.dev/demo.html">
+    <img height="22" src="https://img.shields.io/badge/Live%20Demo-Open-007ec6?logo=webassembly&logoColor=white" alt="Live Demo">
+  </a>
+</div>
+
+Extract text, tables, images, and metadata from 90+ file formats and 300+ programming languages including PDF, Office documents, and images. WebAssembly bindings for browsers, Deno, and Cloudflare Workers with portable deployment and multi-threading support.
+
+## What This Package Provides
+
+- **Document intelligence core** — extract text, tables, images, metadata, entities, keywords, and code intelligence from one API.
+- **Format coverage** — PDF, Office, images, HTML/XML, email, archives, notebooks, citations, scientific formats, and plain text.
+- **OCR choices** — Tesseract, PaddleOCR, EasyOCR where supported, VLM OCR through liter-llm, and plugin hooks for custom backends.
+- **Same engine as every binding** — Rust, Python, Node.js, Go, Java, PHP, Ruby, .NET, Elixir, R, WASM, Kotlin Android, Swift, Dart, Zig, and C FFI share the same Rust implementation.
+- **WASM package** — browser and edge-compatible extraction where native libraries are unavailable.
+
+## Installation
+
+### Package Installation
+
+```bash
+pnpm add @kreuzberg/wasm
+```
+
+### System Requirements
+- Modern browser with WebAssembly support, or Deno 1.0+, or Cloudflare Workers
+- Optional: [Tesseract WASM](https://github.com/naptha/tesseract.js) for OCR functionality
+
+## Quick Start
+
+### Basic Extraction
+
+Extract text, metadata, and structure from any supported document format:
+
+```ts
+import { extractBytes, initWasm } from "@kreuzberg/wasm";
+
+async function main() {
+  await initWasm();
+
+  const buffer = await fetch("document.pdf").then((r) => r.arrayBuffer());
+  const bytes = new Uint8Array(buffer);
+
+  const result = await extractBytes(bytes, "application/pdf");
+
+  console.log("Extracted content:");
+  console.log(result.content);
+  console.log("MIME type:", result.mimeType);
+  console.log("Metadata:", result.metadata);
+}
+
+main().catch(console.error);
+```
+
+### Common Use Cases
+
+#### Extract with Custom Configuration
+
+Most use cases benefit from configuration to control extraction behavior:
+
+**With OCR (for scanned documents):**
+
+```ts
+import { enableOcr, extractBytes, initWasm } from "@kreuzberg/wasm";
+
+async function extractWithOcr() {
+  await initWasm();
+
+  try {
+    await enableOcr();
+    console.log("OCR enabled successfully");
+  } catch (error) {
+    console.error("Failed to enable OCR:", error);
+    return;
+  }
+
+  const bytes = new Uint8Array(await fetch("scanned-page.png").then((r) => r.arrayBuffer()));
+
+  const result = await extractBytes(bytes, "image/png", {
+    ocr: {
+      backend: "tesseract-wasm",
+      language: "eng",
+    },
+  });
+
+  console.log("Extracted text:");
+  console.log(result.content);
+}
+
+extractWithOcr().catch(console.error);
+```
+
+#### Table Extraction
+
+See [Configuration Guide](https://docs.kreuzberg.dev/guides/configuration/) for table extraction options.
+
+#### Processing Multiple Files
+
+```ts
+import { extractBytes, initWasm } from "@kreuzberg/wasm";
+
+interface DocumentJob {
+  name: string;
+  bytes: Uint8Array;
+  mimeType: string;
+}
+
+async function _processBatch(documents: DocumentJob[], concurrency: number = 3) {
+  await initWasm();
+
+  const results: Record<string, string> = {};
+  const queue = [...documents];
+
+  const workers = Array(concurrency)
+    .fill(null)
+    .map(async () => {
+      while (queue.length > 0) {
+        const doc = queue.shift();
+        if (!doc) break;
+
+        try {
+          const result = await extractBytes(doc.bytes, doc.mimeType);
+          results[doc.name] = result.content;
+        } catch (error) {
+          console.error(`Failed to process ${doc.name}:`, error);
+        }
+      }
+    });
+
+  await Promise.all(workers);
+  return results;
+}
+```
+
+#### Async Processing
+
+For non-blocking document processing:
+
+```ts
+import { extractBytes, getWasmCapabilities, initWasm } from "@kreuzberg/wasm";
+
+async function extractDocuments(files: Uint8Array[], mimeTypes: string[]) {
+  const caps = getWasmCapabilities();
+  if (!caps.hasWasm) {
+    throw new Error("WebAssembly not supported");
+  }
+
+  await initWasm();
+
+  const results = await Promise.all(
+    files.map((bytes, index) => extractBytes(bytes, mimeTypes[index])),
+  );
+
+  return results.map((r) => ({
+    content: r.content,
+    pageCount: r.metadata?.pageCount,
+  }));
+}
+
+const fileBytes = [new Uint8Array([1, 2, 3])];
+const mimes = ["application/pdf"];
+
+extractDocuments(fileBytes, mimes)
+  .then((results) => console.log(results))
+  .catch(console.error);
+```
+
+### Next Steps
+
+- **[Installation Guide](https://docs.kreuzberg.dev/getting-started/installation/)** - Platform-specific setup
+- **[API Documentation](https://docs.kreuzberg.dev/reference/api-python/)** - Complete API reference
+- **[Examples & Guides](https://docs.kreuzberg.dev/)** - Full code examples and usage guides
+- **[Configuration Guide](https://docs.kreuzberg.dev/guides/configuration/)** - Advanced configuration options
+
+## Features
+
+### Supported File Formats (90+)
+
+90+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+
+#### Office Documents
+
+| Category | Formats | Capabilities |
+|----------|---------|--------------|
+| **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)
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Raster** | `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp`, `.bmp`, `.tiff`, `.tif` | OCR, table detection, EXIF metadata, dimensions, color space |
+| **Advanced** | `.jp2`, `.jpx`, `.jpm`, `.mj2`, `.jbig2`, `.jb2`, `.pnm`, `.pbm`, `.pgm`, `.ppm` | OCR via hayro-jpeg2000 (pure Rust decoder), JBIG2 support, table detection, format-specific metadata |
+| **Vector** | `.svg` | DOM parsing, embedded text, graphics metadata |
+
+#### Web & Data
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Markup** | `.html`, `.htm`, `.xhtml`, `.xml`, `.svg` | DOM parsing, metadata (Open Graph, Twitter Card), link extraction |
+| **Structured Data** | `.json`, `.yaml`, `.yml`, `.toml`, `.csv`, `.tsv` | Schema detection, nested structures, validation |
+| **Text & Markdown** | `.txt`, `.md`, `.markdown`, `.djot`, `.rst`, `.org`, `.rtf` | CommonMark, GFM, Djot, reStructuredText, Org Mode |
+
+#### Email & Archives
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Email** | `.eml`, `.msg` | Headers, body (HTML/plain), attachments, threading |
+| **Archives** | `.zip`, `.tar`, `.tgz`, `.gz`, `.7z` | File listing, nested archives, metadata |
+
+#### Academic & Scientific
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Citations** | `.bib`, `.biblatex`, `.ris`, `.nbib`, `.enw`, `.csl` | Structured parsing: RIS (structured), PubMed/MEDLINE, EndNote XML (structured), BibTeX, CSL JSON |
+| **Scientific** | `.tex`, `.latex`, `.typst`, `.jats`, `.ipynb`, `.docbook` | LaTeX, Jupyter notebooks, PubMed JATS |
+| **Documentation** | `.opml`, `.pod`, `.mdoc`, `.troff` | Technical documentation formats |
+
+#### Code Intelligence (300+ Languages)
+
+| Feature | Description |
+|---------|-------------|
+| **Structure Extraction** | Functions, classes, methods, structs, interfaces, enums |
+| **Import/Export Analysis** | Module dependencies, re-exports, wildcard imports |
+| **Symbol Extraction** | Variables, constants, type aliases, properties |
+| **Docstring Parsing** | Google, NumPy, Sphinx, JSDoc, RustDoc, and 10+ formats |
+| **Diagnostics** | Parse errors with line/column positions |
+| **Syntax-Aware Chunking** | Split code by semantic boundaries, not arbitrary byte offsets |
+
+Powered by [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — [documentation](https://docs.tree-sitter-language-pack.kreuzberg.dev).
+
+**[Complete Format Reference](https://docs.kreuzberg.dev/reference/formats/)**
+
+### Key Capabilities
+
+- **Text Extraction** - Extract all text content with position and formatting information
+- **Metadata Extraction** - Retrieve document properties, creation date, author, etc.
+- **Table Extraction** - Parse tables with structure and cell content preservation
+- **Image Extraction** - Extract embedded images and render page previews
+- **OCR Support** - Integrate multiple OCR backends for scanned documents
+- **Async/Await** - Non-blocking document processing with concurrent operations
+- **Plugin System** - Extensible post-processing for custom text transformation
+- **Batch Processing** - Efficiently process multiple documents in parallel
+- **Memory Efficient** - Stream large files without loading entirely into memory
+- **Language Detection** - Detect and support multiple languages in documents
+- **Code Intelligence** - Extract structure, imports, exports, symbols, and docstrings from [300+ programming languages](https://docs.tree-sitter-language-pack.kreuzberg.dev) via tree-sitter
+- **Configuration** - Fine-grained control over extraction behavior
+
+### Performance Characteristics
+
+| Format | Speed | Memory | Notes |
+|--------|-------|--------|-------|
+| **PDF (text)** | 10-100 MB/s | ~50MB per doc | Fastest extraction |
+| **Office docs** | 20-200 MB/s | ~100MB per doc | DOCX, XLSX, PPTX |
+| **Images (OCR)** | 1-5 MB/s | Variable | Depends on OCR backend |
+| **Archives** | 5-50 MB/s | ~200MB per doc | ZIP, TAR, etc. |
+| **Web formats** | 50-200 MB/s | Streaming | HTML, XML, JSON |
+
+## OCR Support
+
+Kreuzberg supports multiple OCR backends for extracting text from scanned documents and images:
+
+- **Tesseract-Wasm**
+
+### OCR Configuration Example
+
+```ts
+import { enableOcr, extractBytes, initWasm } from "@kreuzberg/wasm";
+
+async function extractWithOcr() {
+  await initWasm();
+
+  try {
+    await enableOcr();
+    console.log("OCR enabled successfully");
+  } catch (error) {
+    console.error("Failed to enable OCR:", error);
+    return;
+  }
+
+  const bytes = new Uint8Array(await fetch("scanned-page.png").then((r) => r.arrayBuffer()));
+
+  const result = await extractBytes(bytes, "image/png", {
+    ocr: {
+      backend: "tesseract-wasm",
+      language: "eng",
+    },
+  });
+
+  console.log("Extracted text:");
+  console.log(result.content);
+}
+
+extractWithOcr().catch(console.error);
+```
+
+## Async Support
+
+This binding provides full async/await support for non-blocking document processing:
+
+```ts
+import { extractBytes, getWasmCapabilities, initWasm } from "@kreuzberg/wasm";
+
+async function extractDocuments(files: Uint8Array[], mimeTypes: string[]) {
+  const caps = getWasmCapabilities();
+  if (!caps.hasWasm) {
+    throw new Error("WebAssembly not supported");
+  }
+
+  await initWasm();
+
+  const results = await Promise.all(
+    files.map((bytes, index) => extractBytes(bytes, mimeTypes[index])),
+  );
+
+  return results.map((r) => ({
+    content: r.content,
+    pageCount: r.metadata?.pageCount,
+  }));
+}
+
+const fileBytes = [new Uint8Array([1, 2, 3])];
+const mimes = ["application/pdf"];
+
+extractDocuments(fileBytes, mimes)
+  .then((results) => console.log(results))
+  .catch(console.error);
+```
+
+## Plugin System
+
+Kreuzberg supports extensible post-processing plugins for custom text transformation and filtering.
+
+For detailed plugin documentation, visit [Plugin System Guide](https://docs.kreuzberg.dev/guides/plugins/).
+
+## Batch Processing
+
+Process multiple documents efficiently:
+
+```ts
+import { extractBytes, initWasm } from "@kreuzberg/wasm";
+
+interface DocumentJob {
+  name: string;
+  bytes: Uint8Array;
+  mimeType: string;
+}
+
+async function _processBatch(documents: DocumentJob[], concurrency: number = 3) {
+  await initWasm();
+
+  const results: Record<string, string> = {};
+  const queue = [...documents];
+
+  const workers = Array(concurrency)
+    .fill(null)
+    .map(async () => {
+      while (queue.length > 0) {
+        const doc = queue.shift();
+        if (!doc) break;
+
+        try {
+          const result = await extractBytes(doc.bytes, doc.mimeType);
+          results[doc.name] = result.content;
+        } catch (error) {
+          console.error(`Failed to process ${doc.name}:`, error);
+        }
+      }
+    });
+
+  await Promise.all(workers);
+  return results;
+}
+```
+
+## Configuration
+
+For advanced configuration options including language detection, table extraction, OCR settings, and more:
+
+**[Configuration Guide](https://docs.kreuzberg.dev/guides/configuration/)**
+
+## Documentation
+
+- **[Official Documentation](https://docs.kreuzberg.dev/)**
+- **[API Reference](https://docs.kreuzberg.dev/reference/api-python/)**
+- **[Examples & Guides](https://docs.kreuzberg.dev/)**
+
+## Contributing
+
+Contributions are welcome! See [Contributing Guide](https://github.com/kreuzberg-dev/kreuzberg/blob/main/CONTRIBUTING.md).
+
+## Part of Kreuzberg.dev
+
+- [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
+- [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
+- [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
+- [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
+- [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces this README and all per-language bindings.
+- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
+
+## License
+
+Elastic-2.0 License — see [LICENSE](../../LICENSE) for details.
+
+## Support
+
+- **Discord Community**: [Join our Discord](https://discord.gg/xt9WY3GnKR)
+- **GitHub Issues**: [Report bugs](https://github.com/kreuzberg-dev/kreuzberg/issues)
+- **Discussions**: [Ask questions](https://github.com/kreuzberg-dev/kreuzberg/discussions)

crates/kreuzberg-wasm/package.json

@@ -0,0 +1,38 @@
+{
+  "name": "@kreuzberg/wasm",
+  "version": "5.0.0-rc.3",
+  "private": false,
+  "description": "High-performance document intelligence library",
+  "license": "Elastic-2.0",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/kreuzberg-dev/kreuzberg",
+    "directory": "crates/kreuzberg-wasm"
+  },
+  "publishConfig": {
+    "access": "public"
+  },
+  "type": "module",
+  "files": [
+    "pkg",
+    "*.wasm",
+    "*.d.ts",
+    "README.md"
+  ],
+  "main": "pkg/nodejs/kreuzberg_wasm.js",
+  "module": "pkg/web/kreuzberg_wasm.js",
+  "types": "pkg/nodejs/kreuzberg_wasm.d.ts",
+  "scripts": {
+    "build": "wasm-pack build --target nodejs --out-dir pkg/nodejs",
+    "build:ci": "wasm-pack build --release --target nodejs --out-dir pkg/nodejs",
+    "build:wasm:web": "wasm-pack build --release --target web --out-dir pkg/web",
+    "build:wasm:bundler": "wasm-pack build --release --target bundler --out-dir pkg/bundler",
+    "build:wasm:nodejs": "wasm-pack build --release --target nodejs --out-dir pkg/nodejs",
+    "build:wasm:deno": "wasm-pack build --release --target deno --out-dir pkg/deno",
+    "build:all": "npm run build:wasm:web && npm run build:wasm:bundler && npm run build:wasm:nodejs && npm run build:wasm:deno && find pkg -name .gitignore -delete",
+    "test": "vitest run",
+    "test:watch": "vitest watch",
+    "test:coverage": "vitest run --coverage",
+    "clean": "rm -rf pkg dist"
+  }
+}