Conversation
github-actions
Bot
added
the
tutorial
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Assignment Proposal
Title
Prompt regression testing for LLM applications (LLMOps)
Names and KTH ID
Deadline
Category
Description
Tutorial: Google Colab
We want to write a Google Colab notebook that shows how to keep an LLM application stable when its prompt or its model changes. The reader writes a promptfoo configuration with test cases and assertions, runs it against a small instruction-tuned model that is loaded locally in the notebook. The reader then breaks the prompt on purpose, watches the assertions fail, and finally wires the evaluation into a pipeline, so that a failed evaluation blocks the change.
Relevance
An LLM application is defined as much by its prompts and its model version as by its code, and both change often. Without evaluation, a reworded prompt or a model upgrade can silently degrade behaviour, which is the LLMOps version of a regression. The tutorial makes that behaviour testable and automated, so that changes to a model-driven system get the same review discipline as changes to code.