feat(CacheForMocks): folder-based caching for LLM and input mocking in evals #730
Conversation
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
github-actions
bot
added
test:uipath-langchain
bai-uipath
force-pushed
the
bai/caching-for-mocks
branch
from
2d3c169 to
abcebb4
Compare
bai-uipath
force-pushed
the
bai/caching-for-mocks
branch
from
abcebb4 to
2a843b4
Compare
akshaylive
reviewed
Oct 17, 2025
| _CACHE_DIR = Path.cwd() / ".uipath" / "eval_cache" | ||
|
|
||
| @staticmethod | ||
| def _compute_cache_key(cache_key_data: Dict[str, Any]) -> str: |
There was a problem hiding this comment.
Let's make all of these non-static. The instance method should maintain self.cache_dir
| eval_set_id: str, | ||
| eval_item_id: str, | ||
| cache_key: str, | ||
| function_name: Optional[str] = None, |
There was a problem hiding this comment.
I'd suggest making this not optional. In input mocking, we can use function_name="get_mock_input" or something
| ) -> str: | ||
| """Generate the LLM input mocking prompt.""" | ||
| current_datetime = datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S") | ||
| current_date = datetime.utcnow().strftime("%Y-%m-%d") |
There was a problem hiding this comment.
Would suggest avoiding this change. I'd suggest adding
prompt_generation_args = {
"input_schema": json.dumps(input_schema, indent=2),
...
}
prompt = get_input_mocking_prompt(**prompt_generation_args)
cache_key_data = {
"response_format": response_format,
"completion_kwargs": completion_kwargs,
"prompt_generation_args": prompt_generation_args,
}
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This PR adds a file-based caching system for both LLM and input mocker responses used in evals. The hash of the prompt and model parameters are used as the cache key, and the LLM response is the cached value, using a hierarchical folder structure under
.uipath/eval_cache.