Skip to content

feat(docs): add mime_type parameter to AmazonTextractPDFLoader #446

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
alejoar wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(docs): add mime_type parameter to AmazonTextractPDFLoader #446

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 5 additions & 0 deletions libs/community/langchain_community/document_loaders/parsers/pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1542,6 +1542,7 @@ def __init__(
client: Optional[Any] = None,
*,
linearization_config: Optional[TextLinearizationConfig] = None,
mime_type: Optional[str] = None,
) -> None:
"""Initializes the parser.

Expand All @@ -1553,6 +1554,7 @@ def __init__(
linearization_config: Config to be used for linearization of the output
should be an instance of TextLinearizationConfig from
the `textractor` pkg
mime_type: Mime type of the document to be parsed.
"""

try:
Expand All @@ -1561,6 +1563,7 @@ def __init__(

self.tc = tc
self.textractor = textractor
self.mime_type = mime_type

if textract_features is not None:
self.textract_features = [
Expand Down Expand Up @@ -1617,13 +1620,15 @@ def lazy_parse(self, blob: Blob) -> Iterator[Document]:
input_document=str(blob.path),
features=self.textract_features,
boto3_textract_client=self.boto3_textract_client,
mime_type=self.mime_type,
)
else:
textract_response_json = self.tc.call_textract(
input_document=blob.as_bytes(),
features=self.textract_features,
call_mode=self.tc.Textract_Call_Mode.FORCE_SYNC,
boto3_textract_client=self.boto3_textract_client,
mime_type=self.mime_type,
)

document = self.textractor.Document.open(textract_response_json)
Expand Down
4 changes: 3 additions & 1 deletion libs/community/langchain_community/document_loaders/pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1079,6 +1079,7 @@ def __init__(
headers: Optional[dict] = None,
*,
linearization_config: Optional["TextLinearizationConfig"] = None,
mime_type: Optional[str] = None,
) -> None:
"""Initialize the loader.

Expand Down Expand Up @@ -1142,6 +1143,7 @@ def __init__(
textract_features=features,
client=client,
linearization_config=linearization_config,
mime_type=mime_type,
)

def load(self) -> list[Document]:
Expand Down Expand Up @@ -1380,7 +1382,7 @@ def __init__(
Hosted models are passed in format "<provider>/<model>"
Examples: "azure/gpt-4o-mini", "vertex_ai/gemini-1.5-flash-001"
See more details in zerox documentation.
**zerox_kwargs:
**zerox_kwargs:
Arguments specific to the zerox function.
see datailed list of arguments here in zerox repository:
https://github.com/getomni-ai/zerox/blob/main/py_zerox/pyzerox/core/zerox.py#L25
Expand Down