Merge pull request #622 from hwchase17/nc/custom-pdfjs

Allow passing a custom pdfjs build

Author: nfcampos

docs/docs/modules/indexes/document_loaders/examples/file_loaders/pdf.md

@@ -33,3 +33,16 @@ const loader = new PDFLoader("src/document_loaders/example_data/example.pdf", {
 
 const docs = await loader.load();
 ```
+
+# Usage, legacy environments
+
+In legacy environments, you can use the `pdfjs` option to provide a function that returns a promise that resolves to the `PDFJS` object. This is useful if you want to use a custom build of `pdfjs-dist` or if you want to use a different version of `pdfjs-dist`. Eg. here we use the legacy build of `pdfjs-dist`, which includes several polyfills that are not included in the default build.
+
+```typescript
+import { PDFLoader } from "langchain/document_loaders";
+
+const loader = new PDFLoader("src/document_loaders/example_data/example.pdf", {
+  pdfjs: () =>
+    import("pdfjs-dist/legacy/build/pdf.js").then((mod) => mod.default),
+});
+```

langchain/src/document_loaders/pdf.ts

@@ -5,16 +5,22 @@ import { BufferLoader } from "./buffer.js";
 export class PDFLoader extends BufferLoader {
   private splitPages: boolean;
 
-  constructor(filePathOrBlob: string | Blob, { splitPages = true } = {}) {
+  private pdfjs: typeof PDFLoaderImports;
+
+  constructor(
+    filePathOrBlob: string | Blob,
+    { splitPages = true, pdfjs = PDFLoaderImports } = {}
+  ) {
     super(filePathOrBlob);
     this.splitPages = splitPages;
+    this.pdfjs = pdfjs;
   }
 
   public async parse(
     raw: Buffer,
     metadata: Document["metadata"]
   ): Promise<Document[]> {
-    const { getDocument, version } = await PDFLoaderImports();
+    const { getDocument, version } = await this.pdfjs();
     const pdf = await getDocument({
       data: new Uint8Array(raw.buffer),
       useWorkerFetch: false,

langchain/src/document_loaders/tests/pdf.test.ts

@@ -26,3 +26,18 @@ test("Test PDF loader from file to single document", async () => {
   expect(docs.length).toBe(1);
   expect(docs[0].pageContent).toContain("Attention Is All You Need");
 });
+
+test("Test PDF loader from file using custom pdfjs", async () => {
+  const filePath = path.resolve(
+    path.dirname(url.fileURLToPath(import.meta.url)),
+    "./example_data/1706.03762.pdf"
+  );
+  const loader = new PDFLoader(filePath, {
+    pdfjs: () =>
+      import("pdfjs-dist/legacy/build/pdf.js").then((mod) => mod.default),
+  });
+  const docs = await loader.load();
+
+  expect(docs.length).toBe(15);
+  expect(docs[0].pageContent).toContain("Attention Is All You Need");
+});