Skip to content

chore(eval): resync evaluator type schemas with Python source #1664

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
ajay-kesavan wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

chore(eval): resync evaluator type schemas with Python source #1664

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 31 additions & 1 deletion packages/uipath/src/uipath/eval/evaluators_types/ContainsEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,18 @@
"title": "Target Output Key",
"type": "string"
},
"line_by_line_evaluator": {
"default": false,
"description": "If True, split output by delimiter and evaluate each line separately",
"title": "Line By Line Evaluator",
"type": "boolean"
},
"line_delimiter": {
"default": "\n",
"description": "Delimiter to split output when line_by_line_evaluator is True",
"title": "Line Delimiter",
"type": "string"
},
"case_sensitive": {
"default": false,
"title": "Case Sensitive",
Expand Down Expand Up @@ -75,5 +87,23 @@
"title": "ContainsEvaluationCriteria",
"type": "object"
},
"justificationSchema": {}
"justificationSchema": {
"description": "Base class for all evaluator justifications.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
}
},
"required": [
"expected",
"actual"
],
"title": "BaseEvaluatorJustification",
"type": "object"
}
}
32 changes: 31 additions & 1 deletion packages/uipath/src/uipath/eval/evaluators_types/ExactMatchEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,18 @@
"title": "Target Output Key",
"type": "string"
},
"line_by_line_evaluator": {
"default": false,
"description": "If True, split output by delimiter and evaluate each line separately",
"title": "Line By Line Evaluator",
"type": "boolean"
},
"line_delimiter": {
"default": "\n",
"description": "Delimiter to split output when line_by_line_evaluator is True",
"title": "Line Delimiter",
"type": "string"
},
"case_sensitive": {
"default": false,
"title": "Case Sensitive",
Expand Down Expand Up @@ -91,5 +103,23 @@
"title": "OutputEvaluationCriteria",
"type": "object"
},
"justificationSchema": {}
"justificationSchema": {
"description": "Base class for all evaluator justifications.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
}
},
"required": [
"expected",
"actual"
],
"title": "BaseEvaluatorJustification",
"type": "object"
}
}
40 changes: 39 additions & 1 deletion packages/uipath/src/uipath/eval/evaluators_types/JsonSimilarityEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,18 @@
"description": "Key to extract output from agent execution",
"title": "Target Output Key",
"type": "string"
},
"line_by_line_evaluator": {
"default": false,
"description": "If True, split output by delimiter and evaluate each line separately",
"title": "Line By Line Evaluator",
"type": "boolean"
},
"line_delimiter": {
"default": "\n",
"description": "Delimiter to split output when line_by_line_evaluator is True",
"title": "Line Delimiter",
"type": "string"
}
},
"title": "JsonSimilarityEvaluatorConfig",
Expand Down Expand Up @@ -82,6 +94,32 @@
"type": "object"
},
"justificationSchema": {
"type": "string"
"description": "Justification for the JSON similarity evaluator.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
},
"matched_leaves": {
"title": "Matched Leaves",
"type": "number"
},
"total_leaves": {
"title": "Total Leaves",
"type": "number"
}
},
"required": [
"expected",
"actual",
"matched_leaves",
"total_leaves"
],
"title": "JsonSimilarityJustification",
"type": "object"
}
}
35 changes: 34 additions & 1 deletion packages/uipath/src/uipath/eval/evaluators_types/LLMJudgeOutputEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,18 @@
"description": "Key to extract output from agent execution",
"title": "Target Output Key",
"type": "string"
},
"line_by_line_evaluator": {
"default": false,
"description": "If True, split output by delimiter and evaluate each line separately",
"title": "Line By Line Evaluator",
"type": "boolean"
},
"line_delimiter": {
"default": "\n",
"description": "Delimiter to split output when line_by_line_evaluator is True",
"title": "Line Delimiter",
"type": "string"
}
},
"title": "LLMJudgeOutputEvaluatorConfig",
Expand Down Expand Up @@ -109,6 +121,27 @@
"type": "object"
},
"justificationSchema": {
"type": "string"
"description": "Justification for LLM judge evaluators.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
},
"justification": {
"title": "Justification",
"type": "string"
}
},
"required": [
"expected",
"actual",
"justification"
],
"title": "LLMJudgeJustification",
"type": "object"
}
}
35 changes: 34 additions & 1 deletion .../uipath/src/uipath/eval/evaluators_types/LLMJudgeStrictJSONSimilarityOutputEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,18 @@
"description": "Key to extract output from agent execution",
"title": "Target Output Key",
"type": "string"
},
"line_by_line_evaluator": {
"default": false,
"description": "If True, split output by delimiter and evaluate each line separately",
"title": "Line By Line Evaluator",
"type": "boolean"
},
"line_delimiter": {
"default": "\n",
"description": "Delimiter to split output when line_by_line_evaluator is True",
"title": "Line Delimiter",
"type": "string"
}
},
"title": "LLMJudgeStrictJSONSimilarityOutputEvaluatorConfig",
Expand Down Expand Up @@ -109,6 +121,27 @@
"type": "object"
},
"justificationSchema": {
"type": "string"
"description": "Justification for LLM judge evaluators.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
},
"justification": {
"title": "Justification",
"type": "string"
}
},
"required": [
"expected",
"actual",
"justification"
],
"title": "LLMJudgeJustification",
"type": "object"
}
}
23 changes: 22 additions & 1 deletion packages/uipath/src/uipath/eval/evaluators_types/LLMJudgeTrajectoryEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,6 +87,27 @@
"type": "object"
},
"justificationSchema": {
"type": "string"
"description": "Justification for LLM judge evaluators.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
},
"justification": {
"title": "Justification",
"type": "string"
}
},
"required": [
"expected",
"actual",
"justification"
],
"title": "LLMJudgeJustification",
"type": "object"
}
}
23 changes: 22 additions & 1 deletion packages/uipath/src/uipath/eval/evaluators_types/LLMJudgeTrajectorySimulationEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,6 +87,27 @@
"type": "object"
},
"justificationSchema": {
"type": "string"
"description": "Justification for LLM judge evaluators.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
},
"justification": {
"title": "Justification",
"type": "string"
}
},
"required": [
"expected",
"actual",
"justification"
],
"title": "LLMJudgeJustification",
"type": "object"
}
}
10 changes: 10 additions & 0 deletions packages/uipath/src/uipath/eval/evaluators_types/ToolCallArgsEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,6 +120,14 @@
"justificationSchema": {
"description": "Justification for the tool call args evaluator.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
},
"explained_tool_calls_args": {
"additionalProperties": {
"type": "string"
Expand All @@ -129,6 +137,8 @@
}
},
"required": [
"expected",
"actual",
"explained_tool_calls_args"
],
"title": "ToolCallArgsEvaluatorJustification",
Expand Down
10 changes: 10 additions & 0 deletions packages/uipath/src/uipath/eval/evaluators_types/ToolCallCountEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,6 +93,14 @@
"justificationSchema": {
"description": "Justification for the tool call count evaluator.",
"properties": {
"expected": {
"title": "Expected",
"type": "string"
},
"actual": {
"title": "Actual",
"type": "string"
},
"explained_tool_calls_count": {
"additionalProperties": {
"type": "string"
Expand All @@ -102,6 +110,8 @@
}
},
"required": [
"expected",
"actual",
"explained_tool_calls_count"
],
"title": "ToolCallCountEvaluatorJustification",
Expand Down
22 changes: 8 additions & 14 deletions packages/uipath/src/uipath/eval/evaluators_types/ToolCallOrderEvaluator.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,19 +73,13 @@
"justificationSchema": {
"description": "Justification for the tool call order evaluator.",
"properties": {
"actual_tool_calls_order": {
"items": {
"type": "string"
},
"title": "Actual Tool Calls Order",
"type": "array"
"expected": {
"title": "Expected",
"type": "string"
},
"expected_tool_calls_order": {
"items": {
"type": "string"
},
"title": "Expected Tool Calls Order",
"type": "array"
"actual": {
"title": "Actual",
"type": "string"
},
"lcs": {
"items": {
Expand All @@ -96,8 +90,8 @@
}
},
"required": [
"actual_tool_calls_order",
"expected_tool_calls_order",
"expected",
"actual",
"lcs"
],
"title": "ToolCallOrderEvaluatorJustification",
Expand Down
Loading
Loading