Skip to content

v0.28.0: Merge pull request #122 from manykarim/feature/add_more_llm_keywords

Choose a tag to compare

View all tags
@manykarim manykarim released this 24 Oct 22:44
· 55 commits to main since this release
v0.28.0
6979def
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Features

  • Added a new optional DocTest.Ai library packed with LLM-powered keywords: Get Text With LLM, Get Text From Area With LLM, Chat With Document, Image Should Contain, and Get Item Count From Image.
  • Built-in prompts, typed outputs, and optional overrides let you wire in OpenAI/Azure-compatible vision models with minimal setup (pip install robotframework-doctestlibrary[ai] + .env).
  • Visual/PDF comparisons can now forward difficult cases to the LLM (Compare Images With LLM, Compare Pdf Documents With LLM) with structured decisions and clear overrides.
  • Groundwork laid for future multimodal enhancements—LLM helpers reuse existing rendering/ocr pipeline for
    consistency.
Assets 4
Loading