Zander/online pdf loader (#984)

docs/modules/document_loaders/how_to_guides.rst

@@ -49,6 +49,8 @@ There are a lot of different document loaders that LangChain supports. Below are
 
 `Gutenberg <./examples/gutenberg.html>`_: A walkthrough of how to load data from a Gutenberg ebook text.
 
+`Online PDF <./examples/online_pdf.html>`_: A walkthrough of how to load data from an online PDF.
+
 .. toctree::
    :maxdepth: 1
    :glob:

langchain/document_loaders/__init__.py

@@ -14,6 +14,7 @@ from langchain.document_loaders.html import UnstructuredHTMLLoader
 from langchain.document_loaders.imsdb import IMSDbLoader
 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.powerpoint import UnstructuredPowerPointLoader
@@ -52,4 +53,5 @@ __all__ = [
     "GutenbergLoader",
     "PagedPDFSplitter",
     "EveryNoteLoader",
+    "OnlinePDFLoader",
 ]

langchain/document_loaders/online_pdf.py

@@ -0,0 +1,29 @@
+"""Loader that loads online PDF files."""
+
+import tempfile
+from typing import List
+
+import requests
+
+from langchain.docstore.document import Document
+from langchain.document_loaders.base import BaseLoader
+from langchain.document_loaders.pdf import UnstructuredPDFLoader
+
+
+class OnlinePDFLoader(BaseLoader):
+    """Loader that loads online PDFs."""
+
+    def __init__(self, web_path: str):
+        """Initialize with file path."""
+        self.web_path = web_path
+
+    def load(self) -> List[Document]:
+        """Load documents."""
+        r = requests.get(self.web_path)
+        with tempfile.TemporaryDirectory() as temp_dir:
+            file_path = f"{temp_dir}/online_file.pdf"
+            file = open(file_path, "wb")
+            file.write(r.content)
+            file.close()
+            loader = UnstructuredPDFLoader(file_path)
+            return loader.load()