Skip to content

[DO NOT MERGE] PDF Parser tool#103

Open
sanzog03 wants to merge 11 commits into
developfrom
feature/pdf-parser-mcp
Open

[DO NOT MERGE] PDF Parser tool#103
sanzog03 wants to merge 11 commits into
developfrom
feature/pdf-parser-mcp

Conversation

@sanzog03
Copy link
Copy Markdown
Collaborator

pr to trigger the fast-mcp-cloud preview deployment.

lpayne-dev and others added 11 commits March 30, 2026 16:01
Switch PDF parser scraper calls from private _arun to public arun and add optional config passthrough for SimplePDFScraper and DoclingScraper paths to align with reviewer guidance.
  PDFParserTool pulls in DoclingScraper via akd.tools.scrapers,
  and akd-core's pypaperbot eagerly imports docling without
  declaring it. Pin docling>=2.93.0 so fresh installs no longer
  fail test collection with ModuleNotFoundError.
  Rename the input field and helper parameters from
  to  to match the underlying AKD scraper schemas and changed defination for mcp
…ibxcb.so.1 / X11 load errors from docling's transitive cv2 import on slim Linux base images like FastMCP Cloud
…to be faster. this change is for mcp preview only, remove it later before merge
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants