@kreuzberg/node 4.6.1 → 4.7.0

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=v4.6.1" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.7.0" 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#">
@@ -42,13 +42,16 @@
 
   <!-- Project Info -->
   <a href="https://github.com/kreuzberg-dev/kreuzberg/blob/main/LICENSE">
-    <img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License">
+    <img src="https://img.shields.io/badge/License-MIT-007ec6" alt="License">
   </a>
   <a href="https://docs.kreuzberg.dev">
-    <img src="https://img.shields.io/badge/docs-kreuzberg.dev-blue" alt="Documentation">
+    <img src="https://img.shields.io/badge/docs-kreuzberg.dev-007ec6" alt="Documentation">
+  </a>
+  <a href="https://docs.kreuzberg.dev/demo.html">
+    <img src="https://img.shields.io/badge/%E2%96%B6%EF%B8%8F_Live_Demo-007ec6" alt="Live Demo">
   </a>
   <a href="https://huggingface.co/Kreuzberg">
-    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-yellow" alt="Hugging Face">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97_Hugging_Face-007ec6" alt="Hugging Face">
   </a>
 </div>
 
@@ -61,7 +64,7 @@
 </div>
 
 
-Extract text, tables, images, and metadata from 91+ 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 91+ file formats and 248 programming languages including PDF, Office documents, and images. Native NAPI-RS bindings for Node.js with superior performance, async/await support, and TypeScript type definitions.
 
 
 ## Installation
@@ -74,6 +77,7 @@ Install via one of the supported package managers:
 
 
 **npm:**
+
 ```bash
 npm install @kreuzberg/node
 ```
@@ -82,6 +86,7 @@ npm install @kreuzberg/node
 
 
 **pnpm:**
+
 ```bash
 pnpm add @kreuzberg/node
 ```
@@ -90,6 +95,7 @@ pnpm add @kreuzberg/node
 
 
 **yarn:**
+
 ```bash
 yarn add @kreuzberg/node
 ```
@@ -107,6 +113,7 @@ yarn add @kreuzberg/node
 ### Platform Support
 
 Pre-built binaries available for:
+
 - macOS (arm64, x64)
 - Linux (x64)
 - Windows (x64)
@@ -268,12 +275,14 @@ try {
 
 
 **Performance Benefits:**
+
 - **Parallel Processing**: Multiple documents extracted simultaneously
 - **CPU Utilization**: Maximizes multi-core CPU usage for large batches
 - **Queue Management**: Automatically distributes work across available workers
 - **Resource Control**: Prevents thread exhaustion with configurable pool size
 
 **Best Practices:**
+
 - Use worker pools for batches of 10+ documents
 - Set pool size to number of CPU cores (default behavior)
 - Always close pools with `closeWorkerPool()` to prevent resource leaks
@@ -366,6 +375,19 @@ This binding uses NAPI-RS to provide native Node.js bindings with:
 | **Scientific** | `.tex`, `.latex`, `.typst`, `.jats`, `.ipynb`, `.docbook` | LaTeX, Jupyter notebooks, PubMed JATS |
 | **Documentation** | `.opml`, `.pod`, `.mdoc`, `.troff` | Technical documentation formats |
 
+#### Code Intelligence (248 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://kreuzberg.dev/reference/formats/)**
 
 ### Key Capabilities
@@ -387,6 +409,9 @@ This binding uses NAPI-RS to provide native Node.js bindings with:
 - **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 [248 programming languages](https://docs.tree-sitter-language-pack.kreuzberg.dev) via tree-sitter
+
 - **Configuration** - Fine-grained control over extraction behavior
 
 ### Performance Characteristics

package/dist/cli.js

@@ -44,8 +44,8 @@ function getDirectory() {
     return (0, import_node_path.dirname)(__filename);
   }
   try {
-    const url = eval("import.meta.url");
-    return (0, import_node_path.dirname)((0, import_node_url.fileURLToPath)(url));
+    const getUrl = new Function("return import.meta.url");
+    return (0, import_node_path.dirname)((0, import_node_url.fileURLToPath)(getUrl()));
   } catch {
     return process.cwd();
   }

package/dist/cli.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../typescript/cli.ts"],"sourcesContent":["#!/usr/bin/env node\n\n/**\n * Proxy entry point that forwards to the Rust-based Kreuzberg CLI.\n *\n * This keeps `npx kreuzberg` working without shipping an additional TypeScript CLI implementation.\n */\n\nimport { spawnSync } from \"node:child_process\";\nimport { existsSync } from \"node:fs\";\nimport { dirname, join } from \"node:path\";\nimport { fileURLToPath } from \"node:url\";\nimport which from \"which\";\n\ndeclare global {\n\tvar __filename: string | undefined;\n\tvar __dirname: string | undefined;\n}\n\nfunction getDirectory(): string {\n\t// In CJS, __filename will be defined\n\tif (typeof __filename !== \"undefined\") {\n\t\treturn dirname(__filename);\n\t}\n\t// Fallback for ESM\n\ttry {\n\t\t// Use eval to avoid esbuild warnings about import.meta in CJS builds\n\t\t// biome-ignore lint/security/noGlobalEval: Required to handle both CJS and ESM contexts at runtime\n\t\tconst url = eval(\"import.meta.url\");\n\t\treturn dirname(fileURLToPath(url));\n\t} catch {\n\t\treturn process.cwd();\n\t}\n}\n\nfunction main(argv: string[]): number {\n\tconst args = argv.slice(2);\n\n\tlet cliPath: string | undefined;\n\ttry {\n\t\tcliPath = which.sync(\"kreuzberg-cli\");\n\t} catch {}\n\n\tif (!cliPath) {\n\t\tconst __dirname = getDirectory();\n\t\tconst devBinary = join(__dirname, \"..\", \"..\", \"..\", \"target\", \"release\", \"kreuzberg\");\n\t\tif (existsSync(devBinary)) {\n\t\t\tcliPath = devBinary;\n\t\t}\n\t}\n\n\tif (!cliPath) {\n\t\tconsole.error(\n\t\t\t\"The embedded Kreuzberg CLI binary could not be located. \" +\n\t\t\t\t\"This indicates a packaging issue; please open an issue at \" +\n\t\t\t\t\"https://github.com/kreuzberg-dev/kreuzberg/issues so we can investigate.\",\n\t\t);\n\t\treturn 1;\n\t}\n\n\tconst result = spawnSync(cliPath, args, {\n\t\tstdio: \"inherit\",\n\t\tshell: false,\n\t});\n\n\tif (result.error) {\n\t\tconsole.error(`Failed to execute kreuzberg-cli: ${result.error.message}`);\n\t\treturn 1;\n\t}\n\n\treturn result.status ?? 1;\n}\n\nif (require.main === module) {\n\tprocess.exit(main(process.argv));\n}\n\nexport { main };\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAQA,gCAA0B;AAC1B,qBAA2B;AAC3B,uBAA8B;AAC9B,sBAA8B;AAC9B,mBAAkB;AAOlB,SAAS,eAAuB;AAE/B,MAAI,OAAO,eAAe,aAAa;AACtC,eAAO,0BAAQ,UAAU;AAAA,EAC1B;AAEA,MAAI;AAGH,UAAM,MAAM,KAAK,iBAAiB;AAClC,eAAO,8BAAQ,+BAAc,GAAG,CAAC;AAAA,EAClC,QAAQ;AACP,WAAO,QAAQ,IAAI;AAAA,EACpB;AACD;AAEA,SAAS,KAAK,MAAwB;AACrC,QAAM,OAAO,KAAK,MAAM,CAAC;AAEzB,MAAI;AACJ,MAAI;AACH,cAAU,aAAAA,QAAM,KAAK,eAAe;AAAA,EACrC,QAAQ;AAAA,EAAC;AAET,MAAI,CAAC,SAAS;AACb,UAAM,YAAY,aAAa;AAC/B,UAAM,gBAAY,uBAAK,WAAW,MAAM,MAAM,MAAM,UAAU,WAAW,WAAW;AACpF,YAAI,2BAAW,SAAS,GAAG;AAC1B,gBAAU;AAAA,IACX;AAAA,EACD;AAEA,MAAI,CAAC,SAAS;AACb,YAAQ;AAAA,MACP;AAAA,IAGD;AACA,WAAO;AAAA,EACR;AAEA,QAAM,aAAS,qCAAU,SAAS,MAAM;AAAA,IACvC,OAAO;AAAA,IACP,OAAO;AAAA,EACR,CAAC;AAED,MAAI,OAAO,OAAO;AACjB,YAAQ,MAAM,oCAAoC,OAAO,MAAM,OAAO,EAAE;AACxE,WAAO;AAAA,EACR;AAEA,SAAO,OAAO,UAAU;AACzB;AAEA,IAAI,QAAQ,SAAS,QAAQ;AAC5B,UAAQ,KAAK,KAAK,QAAQ,IAAI,CAAC;AAChC;","names":["which"]}
+{"version":3,"sources":["../typescript/cli.ts"],"sourcesContent":["#!/usr/bin/env node\n\n/**\n * Proxy entry point that forwards to the Rust-based Kreuzberg CLI.\n *\n * This keeps `npx kreuzberg` working without shipping an additional TypeScript CLI implementation.\n */\n\nimport { spawnSync } from \"node:child_process\";\nimport { existsSync } from \"node:fs\";\nimport { dirname, join } from \"node:path\";\nimport { fileURLToPath } from \"node:url\";\nimport which from \"which\";\n\ndeclare global {\n\tvar __filename: string | undefined;\n\tvar __dirname: string | undefined;\n}\n\nfunction getDirectory(): string {\n\t// In CJS, __filename will be defined\n\tif (typeof __filename !== \"undefined\") {\n\t\treturn dirname(__filename);\n\t}\n\t// Fallback for ESM: use Function constructor to avoid static analysis warnings\n\ttry {\n\t\tconst getUrl = new Function(\"return import.meta.url\");\n\t\treturn dirname(fileURLToPath(getUrl()));\n\t} catch {\n\t\treturn process.cwd();\n\t}\n}\n\nfunction main(argv: string[]): number {\n\tconst args = argv.slice(2);\n\n\tlet cliPath: string | undefined;\n\ttry {\n\t\tcliPath = which.sync(\"kreuzberg-cli\");\n\t} catch {}\n\n\tif (!cliPath) {\n\t\tconst __dirname = getDirectory();\n\t\tconst devBinary = join(__dirname, \"..\", \"..\", \"..\", \"target\", \"release\", \"kreuzberg\");\n\t\tif (existsSync(devBinary)) {\n\t\t\tcliPath = devBinary;\n\t\t}\n\t}\n\n\tif (!cliPath) {\n\t\tconsole.error(\n\t\t\t\"The embedded Kreuzberg CLI binary could not be located. \" +\n\t\t\t\t\"This indicates a packaging issue; please open an issue at \" +\n\t\t\t\t\"https://github.com/kreuzberg-dev/kreuzberg/issues so we can investigate.\",\n\t\t);\n\t\treturn 1;\n\t}\n\n\tconst result = spawnSync(cliPath, args, {\n\t\tstdio: \"inherit\",\n\t\tshell: false,\n\t});\n\n\tif (result.error) {\n\t\tconsole.error(`Failed to execute kreuzberg-cli: ${result.error.message}`);\n\t\treturn 1;\n\t}\n\n\treturn result.status ?? 1;\n}\n\nif (require.main === module) {\n\tprocess.exit(main(process.argv));\n}\n\nexport { main };\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAQA,gCAA0B;AAC1B,qBAA2B;AAC3B,uBAA8B;AAC9B,sBAA8B;AAC9B,mBAAkB;AAOlB,SAAS,eAAuB;AAE/B,MAAI,OAAO,eAAe,aAAa;AACtC,eAAO,0BAAQ,UAAU;AAAA,EAC1B;AAEA,MAAI;AACH,UAAM,SAAS,IAAI,SAAS,wBAAwB;AACpD,eAAO,8BAAQ,+BAAc,OAAO,CAAC,CAAC;AAAA,EACvC,QAAQ;AACP,WAAO,QAAQ,IAAI;AAAA,EACpB;AACD;AAEA,SAAS,KAAK,MAAwB;AACrC,QAAM,OAAO,KAAK,MAAM,CAAC;AAEzB,MAAI;AACJ,MAAI;AACH,cAAU,aAAAA,QAAM,KAAK,eAAe;AAAA,EACrC,QAAQ;AAAA,EAAC;AAET,MAAI,CAAC,SAAS;AACb,UAAM,YAAY,aAAa;AAC/B,UAAM,gBAAY,uBAAK,WAAW,MAAM,MAAM,MAAM,UAAU,WAAW,WAAW;AACpF,YAAI,2BAAW,SAAS,GAAG;AAC1B,gBAAU;AAAA,IACX;AAAA,EACD;AAEA,MAAI,CAAC,SAAS;AACb,YAAQ;AAAA,MACP;AAAA,IAGD;AACA,WAAO;AAAA,EACR;AAEA,QAAM,aAAS,qCAAU,SAAS,MAAM;AAAA,IACvC,OAAO;AAAA,IACP,OAAO;AAAA,EACR,CAAC;AAED,MAAI,OAAO,OAAO;AACjB,YAAQ,MAAM,oCAAoC,OAAO,MAAM,OAAO,EAAE;AACxE,WAAO;AAAA,EACR;AAEA,SAAO,OAAO,UAAU;AACzB;AAEA,IAAI,QAAQ,SAAS,QAAQ;AAC5B,UAAQ,KAAK,KAAK,QAAQ,IAAI,CAAC;AAChC;","names":["which"]}

package/dist/cli.mjs

@@ -17,8 +17,8 @@ function getDirectory() {
     return dirname(__filename);
   }
   try {
-    const url = eval("import.meta.url");
-    return dirname(fileURLToPath(url));
+    const getUrl = new Function("return import.meta.url");
+    return dirname(fileURLToPath(getUrl()));
   } catch {
     return process.cwd();
   }

package/dist/cli.mjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../typescript/cli.ts"],"sourcesContent":["#!/usr/bin/env node\n\n/**\n * Proxy entry point that forwards to the Rust-based Kreuzberg CLI.\n *\n * This keeps `npx kreuzberg` working without shipping an additional TypeScript CLI implementation.\n */\n\nimport { spawnSync } from \"node:child_process\";\nimport { existsSync } from \"node:fs\";\nimport { dirname, join } from \"node:path\";\nimport { fileURLToPath } from \"node:url\";\nimport which from \"which\";\n\ndeclare global {\n\tvar __filename: string | undefined;\n\tvar __dirname: string | undefined;\n}\n\nfunction getDirectory(): string {\n\t// In CJS, __filename will be defined\n\tif (typeof __filename !== \"undefined\") {\n\t\treturn dirname(__filename);\n\t}\n\t// Fallback for ESM\n\ttry {\n\t\t// Use eval to avoid esbuild warnings about import.meta in CJS builds\n\t\t// biome-ignore lint/security/noGlobalEval: Required to handle both CJS and ESM contexts at runtime\n\t\tconst url = eval(\"import.meta.url\");\n\t\treturn dirname(fileURLToPath(url));\n\t} catch {\n\t\treturn process.cwd();\n\t}\n}\n\nfunction main(argv: string[]): number {\n\tconst args = argv.slice(2);\n\n\tlet cliPath: string | undefined;\n\ttry {\n\t\tcliPath = which.sync(\"kreuzberg-cli\");\n\t} catch {}\n\n\tif (!cliPath) {\n\t\tconst __dirname = getDirectory();\n\t\tconst devBinary = join(__dirname, \"..\", \"..\", \"..\", \"target\", \"release\", \"kreuzberg\");\n\t\tif (existsSync(devBinary)) {\n\t\t\tcliPath = devBinary;\n\t\t}\n\t}\n\n\tif (!cliPath) {\n\t\tconsole.error(\n\t\t\t\"The embedded Kreuzberg CLI binary could not be located. \" +\n\t\t\t\t\"This indicates a packaging issue; please open an issue at \" +\n\t\t\t\t\"https://github.com/kreuzberg-dev/kreuzberg/issues so we can investigate.\",\n\t\t);\n\t\treturn 1;\n\t}\n\n\tconst result = spawnSync(cliPath, args, {\n\t\tstdio: \"inherit\",\n\t\tshell: false,\n\t});\n\n\tif (result.error) {\n\t\tconsole.error(`Failed to execute kreuzberg-cli: ${result.error.message}`);\n\t\treturn 1;\n\t}\n\n\treturn result.status ?? 1;\n}\n\nif (require.main === module) {\n\tprocess.exit(main(process.argv));\n}\n\nexport { main };\n"],"mappings":";;;;;;;;;AAQA,SAAS,iBAAiB;AAC1B,SAAS,kBAAkB;AAC3B,SAAS,SAAS,YAAY;AAC9B,SAAS,qBAAqB;AAC9B,OAAO,WAAW;AAOlB,SAAS,eAAuB;AAE/B,MAAI,OAAO,eAAe,aAAa;AACtC,WAAO,QAAQ,UAAU;AAAA,EAC1B;AAEA,MAAI;AAGH,UAAM,MAAM,KAAK,iBAAiB;AAClC,WAAO,QAAQ,cAAc,GAAG,CAAC;AAAA,EAClC,QAAQ;AACP,WAAO,QAAQ,IAAI;AAAA,EACpB;AACD;AAEA,SAAS,KAAK,MAAwB;AACrC,QAAM,OAAO,KAAK,MAAM,CAAC;AAEzB,MAAI;AACJ,MAAI;AACH,cAAU,MAAM,KAAK,eAAe;AAAA,EACrC,QAAQ;AAAA,EAAC;AAET,MAAI,CAAC,SAAS;AACb,UAAM,YAAY,aAAa;AAC/B,UAAM,YAAY,KAAK,WAAW,MAAM,MAAM,MAAM,UAAU,WAAW,WAAW;AACpF,QAAI,WAAW,SAAS,GAAG;AAC1B,gBAAU;AAAA,IACX;AAAA,EACD;AAEA,MAAI,CAAC,SAAS;AACb,YAAQ;AAAA,MACP;AAAA,IAGD;AACA,WAAO;AAAA,EACR;AAEA,QAAM,SAAS,UAAU,SAAS,MAAM;AAAA,IACvC,OAAO;AAAA,IACP,OAAO;AAAA,EACR,CAAC;AAED,MAAI,OAAO,OAAO;AACjB,YAAQ,MAAM,oCAAoC,OAAO,MAAM,OAAO,EAAE;AACxE,WAAO;AAAA,EACR;AAEA,SAAO,OAAO,UAAU;AACzB;AAEA,IAAI,UAAQ,SAAS,QAAQ;AAC5B,UAAQ,KAAK,KAAK,QAAQ,IAAI,CAAC;AAChC;","names":[]}
+{"version":3,"sources":["../typescript/cli.ts"],"sourcesContent":["#!/usr/bin/env node\n\n/**\n * Proxy entry point that forwards to the Rust-based Kreuzberg CLI.\n *\n * This keeps `npx kreuzberg` working without shipping an additional TypeScript CLI implementation.\n */\n\nimport { spawnSync } from \"node:child_process\";\nimport { existsSync } from \"node:fs\";\nimport { dirname, join } from \"node:path\";\nimport { fileURLToPath } from \"node:url\";\nimport which from \"which\";\n\ndeclare global {\n\tvar __filename: string | undefined;\n\tvar __dirname: string | undefined;\n}\n\nfunction getDirectory(): string {\n\t// In CJS, __filename will be defined\n\tif (typeof __filename !== \"undefined\") {\n\t\treturn dirname(__filename);\n\t}\n\t// Fallback for ESM: use Function constructor to avoid static analysis warnings\n\ttry {\n\t\tconst getUrl = new Function(\"return import.meta.url\");\n\t\treturn dirname(fileURLToPath(getUrl()));\n\t} catch {\n\t\treturn process.cwd();\n\t}\n}\n\nfunction main(argv: string[]): number {\n\tconst args = argv.slice(2);\n\n\tlet cliPath: string | undefined;\n\ttry {\n\t\tcliPath = which.sync(\"kreuzberg-cli\");\n\t} catch {}\n\n\tif (!cliPath) {\n\t\tconst __dirname = getDirectory();\n\t\tconst devBinary = join(__dirname, \"..\", \"..\", \"..\", \"target\", \"release\", \"kreuzberg\");\n\t\tif (existsSync(devBinary)) {\n\t\t\tcliPath = devBinary;\n\t\t}\n\t}\n\n\tif (!cliPath) {\n\t\tconsole.error(\n\t\t\t\"The embedded Kreuzberg CLI binary could not be located. \" +\n\t\t\t\t\"This indicates a packaging issue; please open an issue at \" +\n\t\t\t\t\"https://github.com/kreuzberg-dev/kreuzberg/issues so we can investigate.\",\n\t\t);\n\t\treturn 1;\n\t}\n\n\tconst result = spawnSync(cliPath, args, {\n\t\tstdio: \"inherit\",\n\t\tshell: false,\n\t});\n\n\tif (result.error) {\n\t\tconsole.error(`Failed to execute kreuzberg-cli: ${result.error.message}`);\n\t\treturn 1;\n\t}\n\n\treturn result.status ?? 1;\n}\n\nif (require.main === module) {\n\tprocess.exit(main(process.argv));\n}\n\nexport { main };\n"],"mappings":";;;;;;;;;AAQA,SAAS,iBAAiB;AAC1B,SAAS,kBAAkB;AAC3B,SAAS,SAAS,YAAY;AAC9B,SAAS,qBAAqB;AAC9B,OAAO,WAAW;AAOlB,SAAS,eAAuB;AAE/B,MAAI,OAAO,eAAe,aAAa;AACtC,WAAO,QAAQ,UAAU;AAAA,EAC1B;AAEA,MAAI;AACH,UAAM,SAAS,IAAI,SAAS,wBAAwB;AACpD,WAAO,QAAQ,cAAc,OAAO,CAAC,CAAC;AAAA,EACvC,QAAQ;AACP,WAAO,QAAQ,IAAI;AAAA,EACpB;AACD;AAEA,SAAS,KAAK,MAAwB;AACrC,QAAM,OAAO,KAAK,MAAM,CAAC;AAEzB,MAAI;AACJ,MAAI;AACH,cAAU,MAAM,KAAK,eAAe;AAAA,EACrC,QAAQ;AAAA,EAAC;AAET,MAAI,CAAC,SAAS;AACb,UAAM,YAAY,aAAa;AAC/B,UAAM,YAAY,KAAK,WAAW,MAAM,MAAM,MAAM,UAAU,WAAW,WAAW;AACpF,QAAI,WAAW,SAAS,GAAG;AAC1B,gBAAU;AAAA,IACX;AAAA,EACD;AAEA,MAAI,CAAC,SAAS;AACb,YAAQ;AAAA,MACP;AAAA,IAGD;AACA,WAAO;AAAA,EACR;AAEA,QAAM,SAAS,UAAU,SAAS,MAAM;AAAA,IACvC,OAAO;AAAA,IACP,OAAO;AAAA,EACR,CAAC;AAED,MAAI,OAAO,OAAO;AACjB,YAAQ,MAAM,oCAAoC,OAAO,MAAM,OAAO,EAAE;AACxE,WAAO;AAAA,EACR;AAEA,SAAO,OAAO,UAAU;AACzB;AAEA,IAAI,UAAQ,SAAS,QAAQ;AAC5B,UAAQ,KAAK,KAAK,QAAQ,IAAI,CAAC;AAChC;","names":[]}

package/dist/index.d.mts

@@ -297,6 +297,97 @@ declare function batchExtractBytesSync(dataList: Uint8Array[], mimeTypes: string
  */
 declare function batchExtractBytes(dataList: Uint8Array[], mimeTypes: string[], config?: ExtractionConfig | null): Promise<ExtractionResult[]>;
 
+/**
+ * PDF page rendering functions.
+ *
+ * Render individual PDF pages or iterate over all pages as PNG images.
+ */
+/**
+ * Render a single PDF page to a PNG buffer (synchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param pageIndex - Zero-based page index
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Buffer containing PNG image data
+ */
+declare function renderPdfPageSync(filePath: string, pageIndex: number, options?: {
+    dpi?: number;
+}): Buffer;
+/**
+ * Render a single PDF page to a PNG buffer (asynchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param pageIndex - Zero-based page index
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Promise resolving to a Buffer containing PNG image data
+ */
+declare function renderPdfPage(filePath: string, pageIndex: number, options?: {
+    dpi?: number;
+}): Promise<Buffer>;
+/** A rendered PDF page with its index and PNG data. */
+interface PdfPageResult {
+    pageIndex: number;
+    data: Buffer;
+}
+/**
+ * Collect all PDF pages as PNG images (synchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Array of PdfPageResult objects
+ */
+declare function iteratePdfPagesSync(filePath: string, options?: {
+    dpi?: number;
+}): PdfPageResult[];
+/**
+ * Collect all PDF pages as PNG images (asynchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Promise resolving to an array of PdfPageResult objects
+ */
+declare function iteratePdfPages(filePath: string, options?: {
+    dpi?: number;
+}): Promise<PdfPageResult[]>;
+/**
+ * Get the number of pages in a PDF file.
+ *
+ * @param filePath - Path to the PDF file
+ * @returns Number of pages
+ */
+declare function pdfPageCount(filePath: string): number;
+/**
+ * Lazy PDF page iterator. Renders one page at a time via `.next()`.
+ * Call `.close()` when done to free native resources.
+ *
+ * @example
+ * ```typescript
+ * const iter = new PdfPageIterator("doc.pdf", { dpi: 150 });
+ * let result;
+ * while ((result = iter.next()) !== null) {
+ *     const { pageIndex, data } = result;
+ *     // process page...
+ * }
+ * iter.close();
+ * ```
+ */
+declare class PdfPageIterator {
+    private inner;
+    constructor(filePath: string, options?: {
+        dpi?: number;
+    });
+    /** Advance and return the next page, or null when exhausted. */
+    next(): PdfPageResult | null;
+    /** Total number of pages in the PDF. */
+    pageCount(): number;
+    /** Free native resources. Safe to call multiple times. */
+    close(): void;
+}
+
 /**
  * Single-document extraction APIs.
  *
@@ -1191,6 +1282,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.6.1";
+declare const __version__ = "4.7.0";
 
-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 };
+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 };

package/dist/index.d.ts

@@ -297,6 +297,97 @@ declare function batchExtractBytesSync(dataList: Uint8Array[], mimeTypes: string
  */
 declare function batchExtractBytes(dataList: Uint8Array[], mimeTypes: string[], config?: ExtractionConfig | null): Promise<ExtractionResult[]>;
 
+/**
+ * PDF page rendering functions.
+ *
+ * Render individual PDF pages or iterate over all pages as PNG images.
+ */
+/**
+ * Render a single PDF page to a PNG buffer (synchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param pageIndex - Zero-based page index
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Buffer containing PNG image data
+ */
+declare function renderPdfPageSync(filePath: string, pageIndex: number, options?: {
+    dpi?: number;
+}): Buffer;
+/**
+ * Render a single PDF page to a PNG buffer (asynchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param pageIndex - Zero-based page index
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Promise resolving to a Buffer containing PNG image data
+ */
+declare function renderPdfPage(filePath: string, pageIndex: number, options?: {
+    dpi?: number;
+}): Promise<Buffer>;
+/** A rendered PDF page with its index and PNG data. */
+interface PdfPageResult {
+    pageIndex: number;
+    data: Buffer;
+}
+/**
+ * Collect all PDF pages as PNG images (synchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Array of PdfPageResult objects
+ */
+declare function iteratePdfPagesSync(filePath: string, options?: {
+    dpi?: number;
+}): PdfPageResult[];
+/**
+ * Collect all PDF pages as PNG images (asynchronous).
+ *
+ * @param filePath - Path to the PDF file
+ * @param options - Optional settings
+ * @param options.dpi - DPI for rendering (default 150)
+ * @returns Promise resolving to an array of PdfPageResult objects
+ */
+declare function iteratePdfPages(filePath: string, options?: {
+    dpi?: number;
+}): Promise<PdfPageResult[]>;
+/**
+ * Get the number of pages in a PDF file.
+ *
+ * @param filePath - Path to the PDF file
+ * @returns Number of pages
+ */
+declare function pdfPageCount(filePath: string): number;
+/**
+ * Lazy PDF page iterator. Renders one page at a time via `.next()`.
+ * Call `.close()` when done to free native resources.
+ *
+ * @example
+ * ```typescript
+ * const iter = new PdfPageIterator("doc.pdf", { dpi: 150 });
+ * let result;
+ * while ((result = iter.next()) !== null) {
+ *     const { pageIndex, data } = result;
+ *     // process page...
+ * }
+ * iter.close();
+ * ```
+ */
+declare class PdfPageIterator {
+    private inner;
+    constructor(filePath: string, options?: {
+        dpi?: number;
+    });
+    /** Advance and return the next page, or null when exhausted. */
+    next(): PdfPageResult | null;
+    /** Total number of pages in the PDF. */
+    pageCount(): number;
+    /** Free native resources. Safe to call multiple times. */
+    close(): void;
+}
+
 /**
  * Single-document extraction APIs.
  *
@@ -1191,6 +1282,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.6.1";
+declare const __version__ = "4.7.0";
 
-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 };
+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 };

package/dist/index.js

@@ -28,6 +28,7 @@ __export(index_exports, {
   MissingDependencyError: () => MissingDependencyError,
   OcrError: () => OcrError,
   ParsingError: () => ParsingError,
+  PdfPageIterator: () => PdfPageIterator,
   PluginError: () => PluginError,
   ValidationError: () => ValidationError,
   __resetBindingForTests: () => __resetBindingForTests,
@@ -59,6 +60,8 @@ __export(index_exports, {
   getLastErrorCode: () => getLastErrorCode,
   getLastPanicContext: () => getLastPanicContext,
   getWorkerPoolStats: () => getWorkerPoolStats,
+  iteratePdfPages: () => iteratePdfPages,
+  iteratePdfPagesSync: () => iteratePdfPagesSync,
   listDocumentExtractors: () => listDocumentExtractors,
   listEmbeddingPresets: () => listEmbeddingPresets,
   listOcrBackends: () => listOcrBackends,
@@ -66,9 +69,12 @@ __export(index_exports, {
   listValidators: () => listValidators,
   loadConfigFile: () => loadConfigFile,
   loadConfigFromPath: () => loadConfigFromPath,
+  pdfPageCount: () => pdfPageCount,
   registerOcrBackend: () => registerOcrBackend,
   registerPostProcessor: () => registerPostProcessor,
   registerValidator: () => registerValidator,
+  renderPdfPage: () => renderPdfPage,
+  renderPdfPageSync: () => renderPdfPageSync,
   unregisterDocumentExtractor: () => unregisterDocumentExtractor,
   unregisterOcrBackend: () => unregisterOcrBackend,
   unregisterPostProcessor: () => unregisterPostProcessor,
@@ -579,6 +585,7 @@ function convertChunk(rawChunk) {
   if (!rawChunk || typeof rawChunk !== "object") {
     return {
       content: "",
+      chunkType: null,
       metadata: {
         byteStart: 0,
         byteEnd: 0,
@@ -592,26 +599,17 @@ function convertChunk(rawChunk) {
   const chunk = rawChunk;
   const metadata = chunk["metadata"] ?? {};
   return {
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     content: chunk["content"] ?? "",
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
+    chunkType: chunk["chunk_type"] ?? chunk["chunkType"] ?? null,
     embedding: chunk["embedding"] ?? null,
     metadata: {
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       byteStart: metadata["byte_start"] ?? metadata["charStart"] ?? 0,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       byteEnd: metadata["byte_end"] ?? metadata["charEnd"] ?? 0,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       tokenCount: metadata["token_count"] ?? metadata["tokenCount"] ?? null,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       chunkIndex: metadata["chunk_index"] ?? metadata["chunkIndex"] ?? 0,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       totalChunks: metadata["total_chunks"] ?? metadata["totalChunks"] ?? 0,
-      // 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,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       headingContext: (() => {
         const hc = metadata["heading_context"] ?? metadata["headingContext"];
         if (!hc) return null;
@@ -621,9 +619,7 @@ function convertChunk(rawChunk) {
           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"] ?? ""
             };
           })
@@ -644,22 +640,14 @@ function convertElement(rawElement) {
   const element = rawElement;
   const elementMetadata = element["metadata"] ?? {};
   return {
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     elementId: element["element_id"] ?? element["elementId"] ?? "",
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     elementType: element["element_type"] ?? element["elementType"] ?? "narrative_text",
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     text: element["text"] ?? "",
     metadata: {
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       pageNumber: elementMetadata["page_number"] ?? elementMetadata["pageNumber"] ?? null,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       filename: elementMetadata["filename"] ?? null,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       coordinates: elementMetadata["coordinates"] ? elementMetadata["coordinates"] : null,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       elementIndex: elementMetadata["element_index"] ?? elementMetadata["elementIndex"] ?? null,
-      // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
       additional: elementMetadata["additional"] ?? {}
     }
   };
@@ -682,27 +670,16 @@ function convertImage(rawImage) {
   }
   const image = rawImage;
   return {
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     data: ensureUint8Array(image["data"]),
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     format: image["format"] ?? "unknown",
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     imageIndex: image["imageIndex"] ?? 0,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     pageNumber: image["pageNumber"] ?? null,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     width: image["width"] ?? null,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     height: image["height"] ?? null,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     colorspace: image["colorspace"] ?? null,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     bitsPerComponent: image["bitsPerComponent"] ?? null,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     isMask: image["isMask"] ?? false,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     description: image["description"] ?? null,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     ocrResult: image["ocrResult"] ? convertResult(image["ocrResult"]) : null
   };
 }
@@ -717,15 +694,10 @@ function convertPageContent(rawPage) {
   }
   const page = rawPage;
   return {
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     pageNumber: page["pageNumber"] ?? 0,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     content: page["content"] ?? "",
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     tables: Array.isArray(page["tables"]) ? page["tables"] : [],
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     images: Array.isArray(page["images"]) ? page["images"].map((image) => convertImage(image)) : [],
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     isBlank: page["isBlank"] ?? null
   };
 }
@@ -748,20 +720,15 @@ function convertResult(rawResult) {
   const metadata = result["metadata"];
   const metadataValue = typeof metadata === "string" ? parseMetadata(metadata) : metadata ?? {};
   const returnObj = {
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     content: result["content"] ?? "",
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     mimeType: result["mimeType"] ?? "application/octet-stream",
     metadata: metadataValue,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     tables: Array.isArray(result["tables"]) ? result["tables"] : [],
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     detectedLanguages: Array.isArray(result["detectedLanguages"]) ? result["detectedLanguages"] : null,
     chunks: null,
     images: null,
     elements: null,
     pages: null,
-    // biome-ignore lint/complexity/useLiteralKeys: required for strict TypeScript noPropertyAccessFromIndexSignature
     document: result["document"] ?? null
   };
   const chunksData = result["chunks"];
@@ -833,6 +800,42 @@ async function batchExtractBytes(dataList, mimeTypes, config = null) {
   return rawResults.map(convertResult);
 }
 
+// typescript/extraction/render.ts
+function renderPdfPageSync(filePath, pageIndex, options) {
+  return getBinding().renderPdfPageSync(filePath, pageIndex, options?.dpi ?? null);
+}
+async function renderPdfPage(filePath, pageIndex, options) {
+  return getBinding().renderPdfPage(filePath, pageIndex, options?.dpi ?? null);
+}
+function iteratePdfPagesSync(filePath, options) {
+  return getBinding().iteratePdfPagesSync(filePath, options?.dpi ?? null);
+}
+async function iteratePdfPages(filePath, options) {
+  return getBinding().iteratePdfPages(filePath, options?.dpi ?? null);
+}
+function pdfPageCount(filePath) {
+  return getBinding().pdfPageCount(filePath);
+}
+var PdfPageIterator = class {
+  inner;
+  constructor(filePath, options) {
+    const Ctor = getBinding().JsPdfPageIterator;
+    this.inner = new Ctor(filePath, options?.dpi ?? null);
+  }
+  /** Advance and return the next page, or null when exhausted. */
+  next() {
+    return this.inner.next();
+  }
+  /** Total number of pages in the PDF. */
+  pageCount() {
+    return this.inner.pageCount();
+  }
+  /** Free native resources. Safe to call multiple times. */
+  close() {
+    this.inner.close();
+  }
+};
+
 // typescript/extraction/single.ts
 var import_node_fs = require("fs");
 function extractFileSync(filePath, mimeTypeOrConfig, maybeConfig) {
@@ -1231,7 +1234,7 @@ function getEmbeddingPreset(name) {
 }
 
 // typescript/index.ts
-var __version__ = "4.6.1";
+var __version__ = "4.7.0";
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
   CacheError,
@@ -1242,6 +1245,7 @@ var __version__ = "4.6.1";
   MissingDependencyError,
   OcrError,
   ParsingError,
+  PdfPageIterator,
   PluginError,
   ValidationError,
   __resetBindingForTests,
@@ -1273,6 +1277,8 @@ var __version__ = "4.6.1";
   getLastErrorCode,
   getLastPanicContext,
   getWorkerPoolStats,
+  iteratePdfPages,
+  iteratePdfPagesSync,
   listDocumentExtractors,
   listEmbeddingPresets,
   listOcrBackends,
@@ -1280,9 +1286,12 @@ var __version__ = "4.6.1";
   listValidators,
   loadConfigFile,
   loadConfigFromPath,
+  pdfPageCount,
   registerOcrBackend,
   registerPostProcessor,
   registerValidator,
+  renderPdfPage,
+  renderPdfPageSync,
   unregisterDocumentExtractor,
   unregisterOcrBackend,
   unregisterPostProcessor,