kreuzberg 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13

data/vendor/kreuzberg/Cargo.toml

@@ -1,11 +1,11 @@
 [package]
 name = "kreuzberg"
-version.workspace = true
-edition.workspace = true
-rust-version.workspace = true
-authors.workspace = true
+version = "4.0.0-rc.13"
+edition = "2024"
+rust-version = "1.91"
+authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
 description = "High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 50+ formats with async/sync APIs."
-license.workspace = true
+license = "MIT"
 repository = "https://github.com/kreuzberg-dev/kreuzberg"
 homepage = "https://kreuzberg.dev"
 documentation = "https://docs.rs/kreuzberg"
@@ -26,9 +26,13 @@ tokio-runtime = ["dep:tokio"]
 
 # Format extractors
 pdf = ["dep:pdfium-render", "dep:lopdf", "dep:image"]
-pdf-static = ["pdf"] # Download + static link (no runtime dependency)
-pdf-bundled = ["pdf"] # Embed library in binary (self-contained)
-pdf-system = ["pdf"] # Use system-installed pdfium via pkg-config
+static-pdfium = ["pdf"]                               # Static link (no runtime dep) - requires PDFIUM_STATIC_LIB_PATH env var
+bundled-pdfium = ["pdf"]                              # Embed library in binary (self-contained, dynamic link)
+system-pdfium = ["pdf"]                               # Use system-installed pdfium via pkg-config
+# Legacy names for backward compatibility
+pdf-static = ["static-pdfium"]
+pdf-bundled = ["bundled-pdfium"]
+pdf-system = ["system-pdfium"]
 excel = ["dep:calamine", "dep:polars", "tokio-runtime"]
 office = [
     "dep:roxmltree",
@@ -62,7 +66,12 @@ ocr = [
 ]
 language-detection = ["dep:whatlang"]
 chunking = ["dep:text-splitter"]
-embeddings = ["dep:fastembed", "dep:reqwest", "chunking", "tokio-runtime"]
+embeddings = [
+    "dep:fastembed",
+    "dep:reqwest",
+    "chunking",
+    "tokio-runtime",
+] # Requires system ONNX Runtime
 stopwords = [] # Stopwords for keyword extraction and token reduction
 quality = ["dep:unicode-normalization", "dep:chardetng", "dep:encoding_rs", "stopwords"]
 
@@ -80,9 +89,10 @@ mcp-http = ["mcp", "api"]                                          # NEW - enabl
 otel = ["dep:opentelemetry", "dep:opentelemetry_sdk", "dep:tracing-opentelemetry"]
 
 # WASM-compatible feature bundle
-wasm-target = ["html", "xml", "email", "language-detection", "chunking", "quality"]
+wasm-target = ["pdf", "html", "xml", "email", "language-detection", "chunking", "quality"]
+wasm-threads = ["dep:wasm-bindgen-rayon"]
 
-# Convenience bundles
+# Convenience bundles (all use static PDF linking except wasm)
 full = [
     "pdf",
     "excel",
@@ -94,43 +104,56 @@ full = [
     "ocr",
     "language-detection",
     "chunking",
+    "embeddings",
     "quality",
     "keywords",
+    "api",
+    "mcp",
+    "otel",
+]
+server = ["static-pdfium", "excel", "html", "ocr", "api", "mcp"]
+cli = [
+    "static-pdfium",
+    "excel",
+    "office",
+    "html",
+    "ocr",
+    "language-detection",
+    "chunking",
+    "quality",
 ]
-server = ["pdf", "excel", "html", "ocr", "api", "mcp"]
-cli = ["pdf", "excel", "office", "html", "ocr", "language-detection", "chunking", "quality"]
 
 [build-dependencies]
-tracing = { workspace = true }
+tracing = "0.1"
 pkg-config = "0.3"             # For system pdfium detection
 
 [dependencies]
 # Core dependencies (always included)
-ahash = { workspace = true }
-async-trait = { workspace = true }
-base64 = { workspace = true }
+ahash = "0.8.12"
+async-trait = "0.1.89"
+base64 = "0.22.1"
 base64-simd = "0.8"
-hex = { workspace = true }
+hex = "0.4.3"
 lazy_static = "1.5.0"
-libc = { workspace = true }
+libc = "0.2.178"
 memchr = "2.7.6"
-num_cpus = { workspace = true }
+num_cpus = "1.17.0"
 once_cell = "1.21.3"
-paste = "1.0"
+pastey = "0.2"
 rayon = "1.11.0"
 regex = "1.12.2"
-serde = { workspace = true }
-serde_json = { workspace = true }
+serde = { version = "1.0.228", features = ["derive"] }
+serde_json = "1.0.145"
 serde_yaml_ng = "0.10.0"
-toml = "0.9.8"
+toml = "0.9.10"
 mime_guess = "2.0"
 rmp-serde = "1.3"
-thiserror = { workspace = true }
+thiserror = "2.0.17"
 tokio = { workspace = true, optional = true }
 uuid = { version = "1.19.0", features = ["v4", "js"] }
 indexmap = "2.12.1"
-tracing = { workspace = true }
-reqwest = { workspace = true, default-features = false, features = [
+tracing = "0.1"
+reqwest = { version = "0.12.25", default-features = false, features = [
     "json",
     "rustls-tls",
 ], optional = true }
@@ -143,7 +166,7 @@ roxmltree = { version = "0.21.1", optional = true }
 zip = { version = "6.0.0", optional = true }
 mail-parser = { version = "0.11.1", optional = true }
 msg_parser = { version = "0.1.1", optional = true }
-html-to-markdown-rs = { version = "2.14.2", features = ["inline-images"], optional = true }
+html-to-markdown-rs = { version = "2.14.11", default-features = false, features = ["inline-images"], optional = true }
 quick-xml = { version = "0.38.4", features = ["serialize"], optional = true }
 tar = { version = "0.4.44", optional = true }
 sevenz-rust = { version = "0.6.1", optional = true }
@@ -158,8 +181,8 @@ fb2 = { version = "0.4", optional = true }
 typst-syntax = { version = "0.14", optional = true }
 
 # Processing features (optional)
-kreuzberg-tesseract = { version = "4.0.0-rc.7", optional = true }
-image = { workspace = true, default-features = false, features = [
+kreuzberg-tesseract = { path = "../kreuzberg-tesseract", optional = true }
+image = { version = "0.25.9", default-features = false, features = [
     "png",
     "jpeg",
     "webp",
@@ -174,9 +197,9 @@ ndarray = { version = "0.17.1", optional = true }
 kamadak-exif = { version = "0.6.1", optional = true }
 whatlang = { version = "0.18.0", optional = true }
 text-splitter = { version = "0.28.0", features = ["markdown"], optional = true }
-fastembed = { version = "5.4", default-features = false, features = [
+fastembed = { version = "5.5", default-features = false, features = [
     "hf-hub-rustls-tls",
-    "ort-download-binaries",
+    "ort-load-dynamic",  # Runtime detection, requires system ONNX Runtime
 ], optional = true }
 unicode-normalization = { version = "0.1.25", optional = true }
 chardetng = { version = "0.1.17", optional = true }
@@ -187,7 +210,7 @@ rake = { version = "0.3.6", optional = true }
 axum = { version = "0.8", features = ["macros", "json", "multipart"], optional = true }
 tower = { version = "0.5", optional = true }
 tower-http = { version = "0.6", features = ["cors", "trace", "limit"], optional = true }
-rmcp = { version = "0.11.0", features = [
+rmcp = { version = "0.12.0", features = [
     "server",
     "macros",
     "base64",
@@ -202,16 +225,16 @@ tracing-opentelemetry = { version = "0.32", optional = true }
 infer = "0.19.0"
 
 [dev-dependencies]
-tempfile = { workspace = true }
+tempfile = "3.23.0"
 filetime = "0.2"
 tar = "0.4.44"
 zip = "6.0.0"
 serial_test = "3.2.0"
-anyhow = { workspace = true }
+anyhow = "1.0"
 tokio-test = "0.4"
 tracing-subscriber = { version = "0.3", features = ["env-filter"] }
-criterion = { workspace = true }
-image = { workspace = true, default-features = false, features = ["png"] }
+criterion = { version = "0.8", features = ["html_reports"] }
+image = { version = "0.25.9", default-features = false, features = ["png"] }
 
 [[bench]]
 name = "otel_overhead"
@@ -222,4 +245,4 @@ harness = false
 pprof = { version = "0.15.0", features = ["flamegraph"], optional = true }
 
 [target.'cfg(target_arch = "wasm32")'.dependencies]
-wasm-bindgen-rayon = "1.3"
+wasm-bindgen-rayon = { version = "1.3", optional = true }

data/vendor/kreuzberg/README.md

@@ -1,221 +1,230 @@
-# Kreuzberg
-
-[![Rust](https://img.shields.io/crates/v/kreuzberg?label=Rust)](https://crates.io/crates/kreuzberg)
-[![Python](https://img.shields.io/pypi/v/kreuzberg?label=Python)](https://pypi.org/project/kreuzberg/)
-[![TypeScript](https://img.shields.io/npm/v/@kreuzberg/node?label=TypeScript)](https://www.npmjs.com/package/@kreuzberg/node)
-[![WASM](https://img.shields.io/npm/v/@kreuzberg/wasm?label=WASM)](https://www.npmjs.com/package/@kreuzberg/wasm)
-[![Ruby](https://img.shields.io/gem/v/kreuzberg?label=Ruby)](https://rubygems.org/gems/kreuzberg)
-[![Java](https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java)](https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg)
-[![Go](https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go)](https://pkg.go.dev/github.com/kreuzberg-dev/kreuzberg)
-[![C#](https://img.shields.io/nuget/v/Goldziher.Kreuzberg?label=C%23)](https://www.nuget.org/packages/Goldziher.Kreuzberg/)
-
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Documentation](https://img.shields.io/badge/docs-kreuzberg.dev-blue)](https://kreuzberg.dev/)
-[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
-
-High-performance document intelligence library for Rust. Extract text, metadata, and structured information from PDFs, Office documents, images, and 56 formats.
-
-This is the core Rust library that powers the Python, TypeScript, and Ruby bindings.
-
-> **🚀 Version 4.0.0 Release Candidate**
-> This is a pre-release version. We invite you to test the library and [report any issues](https://github.com/kreuzberg-dev/kreuzberg/issues) you encounter.
->
-> **Note**: The Rust crate is not currently published to crates.io for this RC. Use git dependencies or language bindings (Python, TypeScript, Ruby) instead.
-
-## Installation
-
-```toml
-[dependencies]
-kreuzberg = "4.0"
-tokio = { version = "1", features = ["rt", "macros"] }
-```
-
-## Quick Start
-
-```rust
-use kreuzberg::{extract_file_sync, ExtractionConfig};
-
-fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig::default();
-    let result = extract_file_sync("document.pdf", None, &config)?;
-    println!("{}", result.content);
-    Ok(())
-}
-```
-
-### Async Extraction
-
-```rust
-use kreuzberg::{extract_file, ExtractionConfig};
-
-#[tokio::main]
-async fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig::default();
-    let result = extract_file("document.pdf", None, &config).await?;
-    println!("{}", result.content);
-    Ok(())
-}
-```
-
-### Batch Processing
-
-```rust
-use kreuzberg::{batch_extract_file, ExtractionConfig};
-
-#[tokio::main]
-async fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig::default();
-    let files = vec!["doc1.pdf", "doc2.pdf", "doc3.pdf"];
-    let results = batch_extract_file(&files, None, &config).await?;
-
-    for result in results {
-        println!("{}", result.content);
-    }
-    Ok(())
-}
-```
-
-## OCR with Table Extraction
-
-```rust
-use kreuzberg::{extract_file_sync, ExtractionConfig, OcrConfig, TesseractConfig};
-
-fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig {
-        ocr: Some(OcrConfig {
-            backend: "tesseract".to_string(),
-            language: "eng".to_string(),
-            tesseract_config: Some(TesseractConfig {
-                enable_table_detection: true,
-                ..Default::default()
-            }),
-        }),
-        ..Default::default()
-    };
-
-    let result = extract_file_sync("invoice.pdf", None, &config)?;
-
-    for table in &result.tables {
-        println!("{}", table.markdown);
-    }
-    Ok(())
-}
-```
-
-## Password-Protected PDFs
-
-```rust
-use kreuzberg::{extract_file_sync, ExtractionConfig, PdfConfig};
-
-fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig {
-        pdf_options: Some(PdfConfig {
-            passwords: Some(vec!["password1".to_string(), "password2".to_string()]),
-            ..Default::default()
-        }),
-        ..Default::default()
-    };
-
-    let result = extract_file_sync("protected.pdf", None, &config)?;
-    Ok(())
-}
-```
-
-## Extract from Bytes
-
-```rust
-use kreuzberg::{extract_bytes_sync, ExtractionConfig};
-use std::fs;
-
-fn main() -> kreuzberg::Result<()> {
-    let data = fs::read("document.pdf")?;
-    let config = ExtractionConfig::default();
-    let result = extract_bytes_sync(&data, "application/pdf", &config)?;
-    println!("{}", result.content);
-    Ok(())
-}
-```
-
-## Features
-
-The crate uses feature flags for optional functionality:
-
-```toml
-[dependencies]
-kreuzberg = { version = "4.0", features = ["pdf", "excel", "ocr"] }
-```
-
-### Available Features
-
-| Feature | Description | Binary Size |
-|---------|-------------|-------------|
-| `pdf` | PDF extraction via pdfium | +25MB |
-| `excel` | Excel/spreadsheet parsing | +3MB |
-| `office` | DOCX, PPTX extraction | +1MB |
-| `email` | EML, MSG extraction | +500KB |
-| `html` | HTML to markdown | +1MB |
-| `xml` | XML streaming parser | +500KB |
-| `archives` | ZIP, TAR, 7Z extraction | +2MB |
-| `ocr` | OCR with Tesseract | +5MB |
-| `language-detection` | Language detection | +100KB |
-| `chunking` | Text chunking | +200KB |
-| `quality` | Text quality processing | +500KB |
-
-### Feature Bundles
-
-```toml
-kreuzberg = { version = "4.0", features = ["full"] }
-kreuzberg = { version = "4.0", features = ["server"] }
-kreuzberg = { version = "4.0", features = ["cli"] }
-```
-
-## PDFium Linking Options
-
-When using the `pdf` feature, you can choose how PDFium is linked to your binary. Four strategies are supported:
-
-| Strategy | Feature | Use Case |
-|----------|---------|----------|
-| **Dynamic (default)** | `pdf` | Fast builds, runtime library dependency |
-| **Static** | `pdf`, `pdf-static` | Embed PDFium in binary, larger binary size |
-| **Bundled** | `pdf`, `pdf-bundled` | Self-contained per-binary copies |
-| **System** | `pdf`, `pdf-system` | Use system-installed PDFium |
-
-### Examples
-
-**Default (dynamic linking)** - Fastest compilation, requires libpdfium at runtime:
-```toml
-[dependencies]
-kreuzberg = { version = "4.0", features = ["pdf"] }
-```
-
-**Static linking** - Larger binary, no runtime dependency:
-```toml
-[dependencies]
-kreuzberg = { version = "4.0", features = ["pdf", "pdf-static"] }
-```
-
-**Bundled** - Each binary extracts its own copy:
-```toml
-[dependencies]
-kreuzberg = { version = "4.0", features = ["pdf", "pdf-bundled"] }
-```
-
-**System-installed** - Use pkg-config or manual paths:
-```toml
-[dependencies]
-kreuzberg = { version = "4.0", features = ["pdf", "pdf-system"] }
-```
-
-For comprehensive guidance on linking strategies, environment variables, and troubleshooting, see the [PDFium Linking Guide](../../docs/guides/pdfium-linking.md).
-
-**Note:** Language bindings (Python, TypeScript, Ruby, Java, Go) bundle PDFium automatically and do not expose linking options.
-
-## Documentation
-
-**[API Documentation](https://docs.rs/kreuzberg)** – Complete API reference with examples
-
-**[https://kreuzberg.dev](https://kreuzberg.dev)** – User guide and tutorials
-
-## License
-
-MIT License - see [LICENSE](../../LICENSE) for details.
+# Kreuzberg
+
+[![Rust](https://img.shields.io/crates/v/kreuzberg?label=Rust)](https://crates.io/crates/kreuzberg)
+[![Python](https://img.shields.io/pypi/v/kreuzberg?label=Python)](https://pypi.org/project/kreuzberg/)
+[![TypeScript](https://img.shields.io/npm/v/@kreuzberg/node?label=TypeScript)](https://www.npmjs.com/package/@kreuzberg/node)
+[![WASM](https://img.shields.io/npm/v/@kreuzberg/wasm?label=WASM)](https://www.npmjs.com/package/@kreuzberg/wasm)
+[![Ruby](https://img.shields.io/gem/v/kreuzberg?label=Ruby)](https://rubygems.org/gems/kreuzberg)
+[![Java](https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java)](https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg)
+[![Go](https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go)](https://pkg.go.dev/github.com/kreuzberg-dev/kreuzberg)
+[![C#](https://img.shields.io/nuget/v/Goldziher.Kreuzberg?label=C%23)](https://www.nuget.org/packages/Goldziher.Kreuzberg/)
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Documentation](https://img.shields.io/badge/docs-kreuzberg.dev-blue)](https://kreuzberg.dev/)
+[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
+
+High-performance document intelligence library for Rust. Extract text, metadata, and structured information from PDFs, Office documents, images, and 56 formats.
+
+This is the core Rust library that powers the Python, TypeScript, and Ruby bindings.
+
+> **🚀 Version 4.0.0 Release Candidate**
+> This is a pre-release version. We invite you to test the library and [report any issues](https://github.com/kreuzberg-dev/kreuzberg/issues) you encounter.
+>
+> **Note**: The Rust crate is not currently published to crates.io for this RC. Use git dependencies or language bindings (Python, TypeScript, Ruby) instead.
+
+## Installation
+
+```toml
+[dependencies]
+kreuzberg = "4.0"
+tokio = { version = "1", features = ["rt", "macros"] }
+```
+
+## System Requirements
+
+### ONNX Runtime (for embeddings)
+
+If using embeddings functionality, ONNX Runtime must be installed:
+
+```bash
+# macOS
+brew install onnxruntime
+
+# Ubuntu/Debian
+sudo apt install libonnxruntime libonnxruntime-dev
+
+# Windows (MSVC)
+scoop install onnxruntime
+# OR download from https://github.com/microsoft/onnxruntime/releases
+```
+
+Without ONNX Runtime, embeddings will raise `MissingDependencyError` with installation instructions.
+
+## Quick Start
+
+```rust
+use kreuzberg::{extract_file_sync, ExtractionConfig};
+
+fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig::default();
+    let result = extract_file_sync("document.pdf", None, &config)?;
+    println!("{}", result.content);
+    Ok(())
+}
+```
+
+### Async Extraction
+
+```rust
+use kreuzberg::{extract_file, ExtractionConfig};
+
+#[tokio::main]
+async fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig::default();
+    let result = extract_file("document.pdf", None, &config).await?;
+    println!("{}", result.content);
+    Ok(())
+}
+```
+
+### Batch Processing
+
+```rust
+use kreuzberg::{batch_extract_file, ExtractionConfig};
+
+#[tokio::main]
+async fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig::default();
+    let files = vec!["doc1.pdf", "doc2.pdf", "doc3.pdf"];
+    let results = batch_extract_file(&files, None, &config).await?;
+
+    for result in results {
+        println!("{}", result.content);
+    }
+    Ok(())
+}
+```
+
+## OCR with Table Extraction
+
+```rust
+use kreuzberg::{extract_file_sync, ExtractionConfig, OcrConfig, TesseractConfig};
+
+fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig {
+        ocr: Some(OcrConfig {
+            backend: "tesseract".to_string(),
+            language: "eng".to_string(),
+            tesseract_config: Some(TesseractConfig {
+                enable_table_detection: true,
+                ..Default::default()
+            }),
+        }),
+        ..Default::default()
+    };
+
+    let result = extract_file_sync("invoice.pdf", None, &config)?;
+
+    for table in &result.tables {
+        println!("{}", table.markdown);
+    }
+    Ok(())
+}
+```
+
+## Password-Protected PDFs
+
+```rust
+use kreuzberg::{extract_file_sync, ExtractionConfig, PdfConfig};
+
+fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig {
+        pdf_options: Some(PdfConfig {
+            passwords: Some(vec!["password1".to_string(), "password2".to_string()]),
+            ..Default::default()
+        }),
+        ..Default::default()
+    };
+
+    let result = extract_file_sync("protected.pdf", None, &config)?;
+    Ok(())
+}
+```
+
+## Extract from Bytes
+
+```rust
+use kreuzberg::{extract_bytes_sync, ExtractionConfig};
+use std::fs;
+
+fn main() -> kreuzberg::Result<()> {
+    let data = fs::read("document.pdf")?;
+    let config = ExtractionConfig::default();
+    let result = extract_bytes_sync(&data, "application/pdf", &config)?;
+    println!("{}", result.content);
+    Ok(())
+}
+```
+
+## Features
+
+The crate uses feature flags for optional functionality:
+
+```toml
+[dependencies]
+kreuzberg = { version = "4.0", features = ["pdf", "excel", "ocr"] }
+```
+
+### Available Features
+
+| Feature | Description | Binary Size |
+|---------|-------------|-------------|
+| `pdf` | PDF extraction via pdfium | +25MB |
+| `excel` | Excel/spreadsheet parsing | +3MB |
+| `office` | DOCX, PPTX extraction | +1MB |
+| `email` | EML, MSG extraction | +500KB |
+| `html` | HTML to markdown | +1MB |
+| `xml` | XML streaming parser | +500KB |
+| `archives` | ZIP, TAR, 7Z extraction | +2MB |
+| `ocr` | OCR with Tesseract | +5MB |
+| `language-detection` | Language detection | +100KB |
+| `chunking` | Text chunking | +200KB |
+| `quality` | Text quality processing | +500KB |
+
+### Feature Bundles
+
+```toml
+kreuzberg = { version = "4.0", features = ["full"] }
+kreuzberg = { version = "4.0", features = ["server"] }
+kreuzberg = { version = "4.0", features = ["cli"] }
+```
+
+## PDF Support and Linking Options
+
+Kreuzberg supports three PDFium linking strategies. **Default is `bundled-pdfium`** (best developer experience).
+
+| Strategy | Feature | Use Case | Binary Size | Runtime Deps |
+|----------|---------|----------|-------------|--------------|
+| **Bundled (default)** | `bundled-pdfium` | Development, production | +8-15MB | None |
+| **Static** | `static-pdfium` | Docker, musl, standalone binaries | +200MB | None |
+| **System** | `system-pdfium` | Package managers, distros | +2MB | libpdfium.so |
+
+### Quick Start
+
+```toml
+# Default - bundled PDFium (recommended)
+[dependencies]
+kreuzberg = "4.0"
+
+# Static linking (Docker, musl)
+[dependencies]
+kreuzberg = { version = "4.0", features = ["static-pdfium"] }
+
+# System PDFium (package managers)
+[dependencies]
+kreuzberg = { version = "4.0", features = ["system-pdfium"] }
+```
+
+For detailed information, see the [PDFium Linking Guide](../../docs/guides/pdfium-linking.md).
+
+**Note:** Language bindings (Python, TypeScript, Ruby, Java, Go) automatically bundle PDFium. No configuration needed.
+
+## Documentation
+
+**[API Documentation](https://docs.rs/kreuzberg)** – Complete API reference with examples
+
+**[https://kreuzberg.dev](https://kreuzberg.dev)** – User guide and tutorials
+
+## License
+
+MIT License - see [LICENSE](../../LICENSE) for details.