8  PDF Load (Unstructured)

from langchain_community.document_loaders import UnstructuredPDFLoader
loader = UnstructuredPDFLoader(
    file_path="pdf/layout-parser-paper.pdf"
)
docs = []
for doc in loader.lazy_load():
    docs.append(doc)
---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
Cell In[5], line 2
      1 docs = []
----> 2 for doc in loader.lazy_load():
      3     docs.append(doc)

File /opt/miniconda3/envs/llm-env/lib/python3.12/site-packages/langchain_community/document_loaders/unstructured.py:107, in UnstructuredBaseLoader.lazy_load(self)
    105 def lazy_load(self) -> Iterator[Document]:
    106     """Load file."""
--> 107     elements = self._get_elements()
    108     self._post_process_elements(elements)
    109     if self.mode == "elements":

File /opt/miniconda3/envs/llm-env/lib/python3.12/site-packages/langchain_community/document_loaders/pdf.py:92, in UnstructuredPDFLoader._get_elements(self)
     91 def _get_elements(self) -> list:
---> 92     from unstructured.partition.pdf import partition_pdf
     94     return partition_pdf(filename=self.file_path, **self.unstructured_kwargs)

File /opt/miniconda3/envs/llm-env/lib/python3.12/site-packages/unstructured/partition/pdf.py:16
     14 from pdfminer.layout import LTContainer, LTImage, LTItem, LTTextBox
     15 from pdfminer.utils import open_filename
---> 16 from pi_heif import register_heif_opener
     17 from PIL import Image as PILImage
     18 from pypdf import PdfReader

ModuleNotFoundError: No module named 'pi_heif'