Skip to content

SDK update for datalab PR #1088 #79

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
u-ashish wants to merge 2 commits into
base: dev
Choose a base branch
from
Open

SDK update for datalab PR #1088 #79

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
58002b3
Merge pull request #76 from datalab-to/dev
tarun-menta Feb 3, 2026
57e3e94
SDK update for datalab PR #1088
github-actions[bot] Feb 10, 2026
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
9 changes: 9 additions & 0 deletions datalab_sdk/cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,11 @@ def marker_options(func):
default="balanced",
help="OCR mode",
)(func)
func = click.option(
"--token_efficient_markdown",
is_flag=True,
help="Generate token-efficient markdown optimized for LLM consumption",
)(func)
return func


Expand Down Expand Up @@ -263,6 +268,7 @@ def process_documents(
page_schema: Optional[str] = None,
add_block_ids: bool = False,
mode: str = "balanced",
token_efficient_markdown: bool = False,
):
"""Unified document processing function"""
try:
Expand Down Expand Up @@ -304,6 +310,7 @@ def process_documents(
page_schema=page_schema,
add_block_ids=add_block_ids,
mode=mode,
token_efficient_markdown=token_efficient_markdown,
)
else: # method == "ocr"
options = OCROptions(
Expand Down Expand Up @@ -364,6 +371,7 @@ def convert(
page_schema: Optional[str],
add_block_ids: bool,
mode: str,
token_efficient_markdown: bool,
):
"""Convert documents to markdown, HTML, or JSON"""
process_documents(
Expand All @@ -386,6 +394,7 @@ def convert(
page_schema=page_schema,
add_block_ids=add_block_ids,
mode=mode,
token_efficient_markdown=token_efficient_markdown,
)


Expand Down
3 changes: 2 additions & 1 deletion datalab_sdk/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,10 +51,11 @@ class ConvertOptions(ProcessingOptions):
keep_spreadsheet_formatting: bool = False
webhook_url: Optional[str] = None
# Comma-separated list of extra features: 'track_changes', 'chart_understanding',
# 'table_row_bboxes', 'extract_links', 'infographic', 'new_block_types'
# 'table_row_bboxes', 'extract_links', 'infographic', 'new_block_types', 'training_mode'
extras: Optional[str] = None
add_block_ids: bool = False # add block IDs to HTML output
include_markdown_in_chunks: bool = False # include markdown field in chunks/JSON output
token_efficient_markdown: bool = False # generate token-efficient markdown optimized for LLM consumption

def to_form_data(self) -> Dict[str, Any]:
"""Convert to form data format for API requests"""
Expand Down