Open
Conversation
Author
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description:
This PR introduces a new llm4s-testing module to the llm4s.g8 template, providing a suite of utilities for robust and deterministic testing of LLM-based applications.
Key Features:
MockLLMClient: Allows developers to programmatically define expected inputs and mock responses for unit testing.
RecordingLLMClient: Wraps an existing client to record real LLM interactions to a file, enabling the creation of realistic test data.
PlaybackLLMClient: Replays recorded interactions to ensure tests are deterministic, fast, and cost-free (no API calls).
Scrubber: Automatically sanitizes sensitive information (such as API keys) from recordings before saving them.
Technical Changes:
Added llm4s-testing source and test directories to the template.
Updated build.sbt to configure a multi-module build, correctly separating munit (root) and scalatest (testing) dependencies.
Implemented custom upickle serializers in Interaction.scala to handle llm4s models.
Verified compatibility with llm4s version 0.1.9.