Skip to content

fix: defer llm init in llamaindex scaffold template#354

Merged
radu-mocanu merged 1 commit into
mainfrom
fix/llamaindex-llm-init-scope
Jun 9, 2026
Merged

fix: defer llm init in llamaindex scaffold template#354
radu-mocanu merged 1 commit into
mainfrom
fix/llamaindex-llm-init-scope

Conversation

@radu-mocanu

Copy link
Copy Markdown
Collaborator

Summary

  • scaffolded llamaindex workflows now build the OpenAI llm lazily via a cached_property instead of as a class attribute

Why

uipath init imports the entrypoint module to extract the input/output schema. With the llm as a class attribute it was constructed at import time, before uipath auth had run. Deferring it to first use lets init succeed without auth.

Copilot AI review requested due to automatic review settings June 9, 2026 11:01

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot wasn't able to review any files in this pull request.


💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@radu-mocanu radu-mocanu force-pushed the fix/llamaindex-llm-init-scope branch from 7ee2fe6 to d30c5e6 Compare June 9, 2026 11:15
@radu-mocanu radu-mocanu force-pushed the fix/llamaindex-llm-init-scope branch from d30c5e6 to 23513d5 Compare June 9, 2026 11:18
@sonarqubecloud

sonarqubecloud Bot commented Jun 9, 2026

Copy link
Copy Markdown

@radu-mocanu radu-mocanu merged commit c017a26 into main Jun 9, 2026
70 checks passed
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.

3 participants