Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions bigframes/blob/_functions.py
Original file line number Diff line number Diff line change
Expand Up @@ -393,7 +393,7 @@ def pdf_extract_func(src_obj_ref_rt: str) -> str:
return all_text


pdf_extract_def = FunctionDef(pdf_extract_func, ["pypdf", "requests"])
pdf_extract_def = FunctionDef(pdf_extract_func, ["pypdf", "requests", "pypdf[crypto]"])


# Extracts text from a PDF url and chunks it simultaneously
Expand Down Expand Up @@ -438,4 +438,4 @@ def pdf_chunk_func(src_obj_ref_rt: str, chunk_size: int, overlap_size: int) -> s
return all_text_json_string


pdf_chunk_def = FunctionDef(pdf_chunk_func, ["pypdf", "requests"])
pdf_chunk_def = FunctionDef(pdf_chunk_func, ["pypdf", "requests", "pypdf[crypto]"])
3 changes: 1 addition & 2 deletions bigframes/operations/blob.py
Original file line number Diff line number Diff line change
Expand Up @@ -553,8 +553,7 @@ def pdf_extract(
container_cpu: Union[float, int] = 0.33,
container_memory: str = "512Mi",
) -> bigframes.series.Series:
"""Extracts and chunks text from PDF URLs and saves the text as
arrays of string.
"""Extracts text from PDF URLs and saves the text as string.

.. note::
BigFrames Blob is still under experiments. It may not work and
Expand Down