Skip to content

fix: sample long text for ontology generation#584

Open
samrusani wants to merge 1 commit into
666ghj:mainfrom
samrusani:fix-ontology-long-text-chunking
Open

fix: sample long text for ontology generation#584
samrusani wants to merge 1 commit into
666ghj:mainfrom
samrusani:fix-ontology-long-text-chunking

Conversation

@samrusani
Copy link
Copy Markdown

Summary

  • replace first-50k ontology truncation with deterministic chunk sampling across long documents
  • keep short-document behavior unchanged
  • add regression tests for short, long, and very long ontology context building

Fixes #582

Test plan

  • uv run pytest -q

@dosubot dosubot Bot added size:L This PR changes 100-499 lines, ignoring generated files. enhancement New feature or request labels Apr 26, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Feature Request] 支持超长文本的自动分块处理

1 participant