Skip to content

docs: clarify Markdown summary threshold - #408

Draft
yaodong-shen wants to merge 1 commit into
VectifyAI:mainfrom
yaodong-shen:docs/355-document-markdown-summary-threshold
Draft

docs: clarify Markdown summary threshold#408
yaodong-shen wants to merge 1 commit into
VectifyAI:mainfrom
yaodong-shen:docs/355-document-markdown-summary-threshold

Conversation

@yaodong-shen

Copy link
Copy Markdown

Summary

  • document the Markdown-only --summary-token-threshold behavior in the README
  • clarify in --help that nodes below the threshold reuse their text without an LLM call
  • add regression coverage for both the below-threshold path and the equality boundary

The change preserves the existing runtime behavior. Setting the threshold to 0 continues to make every node use LLM summary generation.

Fixes #355

Validation

  • .venv/bin/python -m unittest discover -s tests -p 'test_page_index_md.py' -v
  • .venv/bin/python run_pageindex.py --help

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.

Markdown path: below --summary-token-threshold, node text is copied verbatim into summary (undocumented; diverges from PDF path)

1 participant