feat: add support for input overrides for multimodal evals #1101
+2,639
−3
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
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
github-actions
bot
added
test:uipath-langchain
AAgnihotry
force-pushed
the
feat/multiModalEvals
branch
from
cd8bf89 to
9533f66
Compare
Updated the input override deep merge logic to be truly recursive, handling nested dictionaries at any depth. Previously only merged one level deep. Added 9 new tests covering edge cases including multiple nesting levels, type replacements, empty dicts, lists, None values, and immutability guarantees. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Contributor
|
LGTM, can we add some E2E testcases as well, please ? Here is an example 32cabaf |
mjnovice
approved these changes
Jan 13, 2026
AAgnihotry
force-pushed
the
feat/multiModalEvals
branch
from
4281ea4 to
452d38c
Compare
Fixed two mypy errors: 1. Added type parameters to deep_merge function signature - Changed from `def deep_merge(base: dict, override: dict) -> dict:` - To: `def deep_merge(base: dict[str, Any], override: dict[str, Any]) -> dict[str, Any]:` 2. Added type annotation and import to test file - Added `from typing import Any` import - Added explicit type annotation to original_inputs variable All mypy checks now pass successfully. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
cristipufu
reviewed
Jan 14, 2026
| """ | ||
| self.model_settings_override = settings | ||
|
|
||
| def set_input_overrides(self, overrides: dict[str, Any]) -> None: |
Member
There was a problem hiding this comment.
@Chibionos let's get rid of this configurable factory, as we previously talked
cristipufu
requested changes
Jan 14, 2026
| logger.error(f"Failed to create temporary entrypoint file: {e}") | ||
| return None | ||
|
|
||
| def apply_input_overrides( |
Member
There was a problem hiding this comment.
please don't add this here. it's got nothing to do with a factory. this should just override the inputs from the eval item
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
Summary
_ConfigurableFactoryto handle file path overrides for multimodal inputs (images, audio, video, documents)_Runtimeto resolve and validate file paths during eval executionChanges
src/uipath/_cli/_evals/_configurable_factory.py(+70 lines): Added_resolve_file_path_overridesmethod to handle multimodal input overridessrc/uipath/_cli/_evals/_runtime.py(+19 lines): Integrated file path resolution into the runtime execution flowsrc/uipath/_cli/cli_eval.py(+10 lines): Extended CLI to support input overrides parametertests/cli/eval/test_configurable_factory.py(+157 lines): Unit tests for file path override logictests/cli/eval/test_input_overrides_e2e.py(+310 lines, new): E2E tests covering various override scenariosTest plan
_ConfigurableFactoryoverride resolution🤖 Generated with Claude Code