@kreuzberg/wasm 4.0.0-rc.10 → 4.0.0-rc.12

package/README.md

@@ -88,6 +88,55 @@ yarn add @kreuzberg/wasm
 import { extractBytes } from "npm:@kreuzberg/wasm@^4.0.0";
 ```
 
+## PDF Support and PDFium Initialization
+
+**IMPORTANT**: PDF extraction requires a one-time initialization step to load the PDFium WASM module.
+
+### Why PDFium Initialization is Needed
+
+Kreuzberg uses the high-performance PDFium library (from Google Chrome) for PDF processing. In WASM environments, PDFium runs as a separate WASM module that must be loaded and bound to the main kreuzberg module before PDF extraction can work.
+
+### How to Initialize PDFium
+
+```javascript
+import init, { initialize_pdfium_render, extractBytes } from '@kreuzberg/wasm';
+import pdfiumModule from '@kreuzberg/wasm/pdfium.js';
+
+// Step 1: Initialize kreuzberg WASM
+await init();
+
+// Step 2: Load PDFium WASM module
+const pdfium = await pdfiumModule();
+
+// Step 3: Bind kreuzberg to PDFium (required before any PDF operations)
+const success = initialize_pdfium_render(pdfium, wasm, false);
+if (!success) {
+    throw new Error('Failed to initialize PDFium');
+}
+
+// Step 4: Now PDF extraction works
+const pdfBytes = new Uint8Array(await pdfFile.arrayBuffer());
+const result = await extractBytes(pdfBytes);
+console.log(result.text);
+```
+
+### Error: "PdfiumWASMModuleNotConfigured"
+
+If you see this error, it means `initialize_pdfium_render()` was not called before attempting PDF extraction. Make sure to follow the initialization sequence above.
+
+### PDFium Files Location
+
+The PDFium WASM files (`pdfium.js`, `pdfium.wasm`) should be included in the `@kreuzberg/wasm` package. If they're missing:
+
+1. Check your `node_modules/@kreuzberg/wasm/` directory
+2. Ensure both `pdfium.js` and `pdfium.wasm` are present
+3. If missing, reinstall the package
+
+For self-hosted builds, copy the files from:
+```bash
+target/wasm32-unknown-unknown/release/build/kreuzberg-*/out/pdfium/release/node/
+```
+
 ## Quick Start
 
 ### Browser (ESM)

package/dist/index.cjs

@@ -4026,6 +4026,25 @@ var wasm = null;
 var initialized = false;
 var initializationError = null;
 var initializationPromise = null;
+async function initializePdfiumAsync(wasmModule) {
+  if (!wasmModule || typeof wasmModule.initialize_pdfium_render !== "function") {
+    return;
+  }
+  if (!isBrowser()) {
+    console.debug("PDFium initialization skipped (non-browser environment)");
+    return;
+  }
+  try {
+    const pdfiumModule = await import("./pdfium.js");
+    const pdfium = typeof pdfiumModule.default === "function" ? await pdfiumModule.default() : pdfiumModule;
+    const success = wasmModule.initialize_pdfium_render(pdfium, wasmModule, false);
+    if (!success) {
+      console.warn("PDFium initialization returned false");
+    }
+  } catch (error) {
+    console.debug("PDFium initialization error:", error);
+  }
+}
 async function initWasm() {
   if (initialized) {
     return;
@@ -4040,7 +4059,7 @@ async function initWasm() {
       }
       let wasmModule;
       try {
-        wasmModule = await import("../pkg/kreuzberg_wasm.js");
+        wasmModule = await import("./pkg/kreuzberg_wasm.js");
       } catch {
         wasmModule = await import("./kreuzberg_wasm.js");
       }
@@ -4048,6 +4067,11 @@ async function initWasm() {
       if (wasm && typeof wasm.default === "function") {
         await wasm.default();
       }
+      if (isBrowser() && wasm && typeof wasm.initialize_pdfium_render === "function") {
+        initializePdfiumAsync(wasm).catch((error) => {
+          console.warn("PDFium auto-initialization failed (PDF extraction disabled):", error);
+        });
+      }
       initialized = true;
       initializationError = null;
     } catch (error) {