Class: Google::Cloud::Ces::V1beta::Evaluation
- Inherits:
-
Object
- Object
- Google::Cloud::Ces::V1beta::Evaluation
- Extended by:
- Protobuf::MessageExts::ClassMethods
- Includes:
- Protobuf::MessageExts
- Defined in:
- proto_docs/google/cloud/ces/v1beta/evaluation.rb
Overview
An evaluation represents all of the information needed to simulate and evaluate an agent.
Defined Under Namespace
Classes: Golden, GoldenExpectation, GoldenTurn, Scenario, ScenarioExpectation, Step
Instance Attribute Summary collapse
-
#aggregated_metrics ⇒ ::Google::Cloud::Ces::V1beta::AggregatedMetrics
readonly
Output only.
-
#create_time ⇒ ::Google::Protobuf::Timestamp
readonly
Output only.
-
#created_by ⇒ ::String
readonly
Output only.
-
#description ⇒ ::String
Optional.
-
#display_name ⇒ ::String
Required.
-
#etag ⇒ ::String
readonly
Output only.
-
#evaluation_datasets ⇒ ::Array<::String>
readonly
Output only.
-
#evaluation_runs ⇒ ::Array<::String>
readonly
Output only.
-
#golden ⇒ ::Google::Cloud::Ces::V1beta::Evaluation::Golden
Optional.
-
#invalid ⇒ ::Boolean
readonly
Output only.
-
#last_completed_result ⇒ ::Google::Cloud::Ces::V1beta::EvaluationResult
readonly
Output only.
-
#last_ten_results ⇒ ::Array<::Google::Cloud::Ces::V1beta::EvaluationResult>
readonly
Output only.
-
#last_updated_by ⇒ ::String
readonly
Output only.
-
#name ⇒ ::String
Identifier.
-
#scenario ⇒ ::Google::Cloud::Ces::V1beta::Evaluation::Scenario
Optional.
-
#tags ⇒ ::Array<::String>
Optional.
-
#update_time ⇒ ::Google::Protobuf::Timestamp
readonly
Output only.
Instance Attribute Details
#aggregated_metrics ⇒ ::Google::Cloud::Ces::V1beta::AggregatedMetrics (readonly)
Returns Output only. The aggregated metrics for this evaluation across all runs.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#create_time ⇒ ::Google::Protobuf::Timestamp (readonly)
Returns Output only. Timestamp when the evaluation was created.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#created_by ⇒ ::String (readonly)
Returns Output only. The user who created the evaluation.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#description ⇒ ::String
Returns Optional. User-defined description of the evaluation.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#display_name ⇒ ::String
Returns Required. User-defined display name of the evaluation. Unique within an App.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#etag ⇒ ::String (readonly)
Returns Output only. Etag used to ensure the object hasn't changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#evaluation_datasets ⇒ ::Array<::String> (readonly)
Returns Output only. List of evaluation datasets the evaluation belongs to.
Format:
projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#evaluation_runs ⇒ ::Array<::String> (readonly)
Returns Output only. The EvaluationRuns that this Evaluation is associated with.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#golden ⇒ ::Google::Cloud::Ces::V1beta::Evaluation::Golden
Returns Optional. The golden steps to be evaluated.
Note: The following fields are mutually exclusive: golden, scenario. If a field in that set is populated, all other fields in the set will automatically be cleared.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#invalid ⇒ ::Boolean (readonly)
Returns Output only. Whether the evaluation is invalid. This can happen if an evaluation is referencing a tool, toolset, or agent that has since been deleted.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#last_completed_result ⇒ ::Google::Cloud::Ces::V1beta::EvaluationResult (readonly)
Returns Output only. The latest evaluation result for this evaluation.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#last_ten_results ⇒ ::Array<::Google::Cloud::Ces::V1beta::EvaluationResult> (readonly)
Returns Output only. The last 10 evaluation results for this evaluation. This is only populated if include_last_ten_results is set to true in the ListEvaluationsRequest or GetEvaluationRequest.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#last_updated_by ⇒ ::String (readonly)
Returns Output only. The user who last updated the evaluation.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#name ⇒ ::String
Returns Identifier. The unique identifier of this evaluation.
Format:
projects/{project}/locations/{location}/apps/{app}/evaluations/{evaluation}.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#scenario ⇒ ::Google::Cloud::Ces::V1beta::Evaluation::Scenario
Returns Optional. The config for a scenario.
Note: The following fields are mutually exclusive: scenario, golden. If a field in that set is populated, all other fields in the set will automatically be cleared.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#tags ⇒ ::Array<::String>
Returns Optional. User defined tags to categorize the evaluation.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |
#update_time ⇒ ::Google::Protobuf::Timestamp (readonly)
Returns Output only. Timestamp when the evaluation was last updated.
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# File 'proto_docs/google/cloud/ces/v1beta/evaluation.rb', line 212 class Evaluation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Represents a single, checkable requirement. # @!attribute [rw] tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Optional. Check that a specific tool was called with the parameters. # # Note: The following fields are mutually exclusive: `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. Check that a specific tool had the expected response. # # Note: The following fields are mutually exclusive: `tool_response`, `tool_call`, `agent_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. Check that the agent responded with the correct response. The # role "agent" is implied. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_call`, `tool_response`, `agent_transfer`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Check that the agent transferred the conversation to a # different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `tool_call`, `tool_response`, `agent_response`, `updated_variables`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] updated_variables # @return [::Google::Protobuf::Struct] # Optional. Check that the agent updated the session variables to the # expected values. Used to also capture agent variable updates for golden # evals. # # Note: The following fields are mutually exclusive: `updated_variables`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `mock_tool_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Optional. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # # Note: The following fields are mutually exclusive: `mock_tool_response`, `tool_call`, `tool_response`, `agent_response`, `agent_transfer`, `updated_variables`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] note # @return [::String] # Optional. A note for this requirement, useful in reporting when specific # checks fail. E.g., "Check_Payment_Tool_Called". class GoldenExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A step defines a singular action to happen during the evaluation. # @!attribute [rw] user_input # @return [::Google::Cloud::Ces::V1beta::SessionInput] # Optional. User input for the conversation. # # Note: The following fields are mutually exclusive: `user_input`, `agent_transfer`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_transfer # @return [::Google::Cloud::Ces::V1beta::AgentTransfer] # Optional. Transfer the conversation to a different agent. # # Note: The following fields are mutually exclusive: `agent_transfer`, `user_input`, `expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::GoldenExpectation] # Optional. Executes an expectation on the current turn. # # Note: The following fields are mutually exclusive: `expectation`, `user_input`, `agent_transfer`. If a field in that set is populated, all other fields in the set will automatically be cleared. class Step include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # A golden turn defines a single turn in a golden conversation. # @!attribute [rw] steps # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Step>] # Required. The steps required to replay a golden conversation. # @!attribute [rw] root_span # @return [::Google::Cloud::Ces::V1beta::Span] # Optional. The root span of the golden turn for processing and maintaining # audio information. class GoldenTurn include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The steps required to replay a golden conversation. # @!attribute [rw] turns # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::GoldenTurn>] # Required. The golden turns required to replay a golden conversation. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the replayed # conversation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Golden include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expectation to evaluate the conversation produced by the simulation. # @!attribute [rw] tool_expectation # @return [::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation::ToolExpectation] # Optional. The tool call and response pair to be evaluated. # # Note: The following fields are mutually exclusive: `tool_expectation`, `agent_response`. If a field in that set is populated, all other fields in the set will automatically be cleared. # @!attribute [rw] agent_response # @return [::Google::Cloud::Ces::V1beta::Message] # Optional. The agent response to be evaluated. # # Note: The following fields are mutually exclusive: `agent_response`, `tool_expectation`. If a field in that set is populated, all other fields in the set will automatically be cleared. class ScenarioExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # The tool call and response pair to be evaluated. # @!attribute [rw] expected_tool_call # @return [::Google::Cloud::Ces::V1beta::ToolCall] # Required. The expected tool call, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. # @!attribute [rw] mock_tool_response # @return [::Google::Cloud::Ces::V1beta::ToolResponse] # Required. The tool response to mock, with the parameters of interest # specified. Any parameters not specified will be hallucinated by the # LLM. class ToolExpectation include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end # The config for a scenario # @!attribute [rw] task # @return [::String] # Required. The task to be targeted by the scenario. # @!attribute [rw] user_facts # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserFact>] # Optional. The user facts to be used by the scenario. # @!attribute [rw] max_turns # @return [::Integer] # Optional. The maximum number of turns to simulate. If not specified, the # simulation will continue until the task is complete. # @!attribute [rw] rubrics # @return [::Array<::String>] # Required. The rubrics to score the scenario against. # @!attribute [rw] scenario_expectations # @return [::Array<::Google::Cloud::Ces::V1beta::Evaluation::ScenarioExpectation>] # Required. The ScenarioExpectations to evaluate the conversation produced # by the user simulation. # @!attribute [rw] variable_overrides # @return [::Google::Protobuf::Struct] # Optional. Variables / Session Parameters as context for the session, # keyed by variable names. Members of this struct will override any default # values set by the system. # # Note, these are different from user facts, which are facts known to the # user. Variables are parameters known to the agent: i.e. MDN (phone # number) passed by the telephony system. # @!attribute [rw] task_completion_behavior # @deprecated This field is deprecated and may be removed in the next major version update. # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::TaskCompletionBehavior] # Optional. Deprecated. Use user_goal_behavior instead. # @!attribute [rw] user_goal_behavior # @return [::Google::Cloud::Ces::V1beta::Evaluation::Scenario::UserGoalBehavior] # Optional. The expected behavior of the user goal. # @!attribute [rw] evaluation_expectations # @return [::Array<::String>] # Optional. The evaluation expectations to evaluate the conversation # produced by the simulation against. Format: # `projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}` class Scenario include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Facts about the user as a key value pair. # @!attribute [rw] name # @return [::String] # Required. The name of the user fact. # @!attribute [rw] value # @return [::String] # Required. The value of the user fact. class UserFact include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end # The expected behavior of the user task. This is used to determine whether # the scenario is successful. module TaskCompletionBehavior # Behavior unspecified. Will default to TASK_SATISFIED. TASK_COMPLETION_BEHAVIOR_UNSPECIFIED = 0 # The user task should be completed successfully. TASK_SATISFIED = 1 # The user task should be rejected. TASK_REJECTED = 2 end # The expected behavior of the user goal. This is used to determine whether # the scenario is successful. module UserGoalBehavior # Behavior unspecified. Will default to USER_GOAL_SATISFIED. USER_GOAL_BEHAVIOR_UNSPECIFIED = 0 # The user goal should be completed successfully. USER_GOAL_SATISFIED = 1 # The user goal should be rejected. USER_GOAL_REJECTED = 2 # Ignore the user goal status. USER_GOAL_IGNORED = 3 end end end |