pdfminer (#1003)

docs/modules/document_loaders/examples/pdf.ipynb

@@ -167,10 +167,48 @@
     "data = loader.load()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "21998d18",
+   "metadata": {},
+   "source": [
+    "## Using PDFMiner"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2f0cc9ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import PDFMinerLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "42b531e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = PDFMinerLoader(\"example_data/layout-parser-paper.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "010d5cdd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "54fb6b62",
+   "id": "7301c473",
    "metadata": {},
    "outputs": [],
    "source": []

langchain/document_loaders/__init__.py

@@ -17,7 +17,7 @@ from langchain.document_loaders.notion import NotionDirectoryLoader
 from langchain.document_loaders.obsidian import ObsidianLoader
 from langchain.document_loaders.online_pdf import OnlinePDFLoader
 from langchain.document_loaders.paged_pdf import PagedPDFSplitter
-from langchain.document_loaders.pdf import UnstructuredPDFLoader
+from langchain.document_loaders.pdf import PDFMinerLoader, UnstructuredPDFLoader
 from langchain.document_loaders.powerpoint import UnstructuredPowerPointLoader
 from langchain.document_loaders.readthedocs import ReadTheDocsLoader
 from langchain.document_loaders.roam import RoamLoader
@@ -58,4 +58,5 @@ __all__ = [
     "EveryNoteLoader",
     "AirbyteJSONLoader",
     "OnlinePDFLoader",
+    "PDFMinerLoader",
 ]

langchain/document_loaders/pdf.py

@@ -27,3 +27,26 @@ class UnstructuredPDFLoader(BaseLoader):
         text = "\n\n".join([str(el) for el in elements])
         metadata = {"source": self.file_path}
         return [Document(page_content=text, metadata=metadata)]
+
+
+class PDFMinerLoader(BaseLoader):
+    """Loader that uses PDFMiner to load PDF files."""
+
+    def __init__(self, file_path: str):
+        """Initialize with file path."""
+        try:
+            from pdfminer.high_level import extract_text  # noqa:F401
+        except ImportError:
+            raise ValueError(
+                "pdfminer package not found, please install it with "
+                "`pip install pdfminer.six`"
+            )
+        self.file_path = file_path
+
+    def load(self) -> List[Document]:
+        """Load file."""
+        from pdfminer.high_level import extract_text
+
+        text = extract_text(self.file_path)
+        metadata = {"source": self.file_path}
+        return [Document(page_content=text, metadata=metadata)]