forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
30 lines
983 B
Python
30 lines
983 B
Python
"""Loader that loads PDF files."""
|
|
from typing import List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
|
|
|
|
class UnstructuredPDFLoader(BaseLoader):
|
|
"""Loader that uses unstructured to load PDF files."""
|
|
|
|
def __init__(self, file_path: str):
|
|
"""Initialize with file path."""
|
|
try:
|
|
import unstructured # noqa:F401
|
|
except ImportError:
|
|
raise ValueError(
|
|
"unstructured package not found, please install it with "
|
|
"`pip install unstructured`"
|
|
)
|
|
self.file_path = file_path
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load file."""
|
|
from unstructured.partition.pdf import partition_pdf
|
|
|
|
elements = partition_pdf(filename=self.file_path)
|
|
text = "\n\n".join([str(el) for el in elements])
|
|
metadata = {"source": self.file_path}
|
|
return [Document(page_content=text, metadata=metadata)]
|