fix: PyMuPDF Reader broken (run-llama#547)

Tachikoma000 · Sep 28, 2023 · 03fd5e4 · 03fd5e4
1 parent 2086fb2
commit 03fd5e4
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 1 deletion.
diff --git a/llama_hub/file/pymu_pdf/README.md b/llama_hub/file/pymu_pdf/README.md
@@ -13,7 +13,7 @@ from llama_index import download_loader
 PyMuPDFReader = download_loader("PyMuPDFReader")
 
 loader = PyMuPDFReader()
-documents = loader.load(file_path=Path('./article.pdf'), metadata=True)
+documents = loader.load_data(file_path=Path('./article.pdf'), metadata=True)
 ```
 
 This loader is designed to be used as a way to load data into [LlamaIndex](https://github.com/jerryjliu/gpt_index/tree/main/gpt_index) and/or subsequently used as a Tool in a [LangChain](https://github.com/hwchase17/langchain) Agent. See [here](https://github.com/emptycrown/llama-hub/tree/main) for examples.
diff --git a/llama_hub/file/pymu_pdf/base.py b/llama_hub/file/pymu_pdf/base.py
@@ -9,6 +9,15 @@
 class PyMuPDFReader(BaseReader):
     """Read PDF files using PyMuPDF library."""
 
+    def load_data(
+        self,
+        file_path: Union[Path, str],
+        metadata: bool = True,
+        extra_info: Optional[Dict] = None,
+    ) -> List[Document]:
+        """Loads list of documents from PDF file and also accepts extra information in dict format."""
+        return self.load(file_path, metadata=metadata, extra_info=extra_info)
+
     def load(
         self,
         file_path: Union[Path, str],