Debian Codegraph @

docs/dyn/ces_v1beta.projects.locations.apps.evaluationDatasets.html

raw
1 <html><body>
2 <style>
3
4 body, h1, h2, h3, div, span, p, pre, a {
5 margin: 0;
6 padding: 0;
7 border: 0;
8 font-weight: inherit;
9 font-style: inherit;
10 font-size: 100%;
11 font-family: inherit;
12 vertical-align: baseline;
13 }
14
15 body {
16 font-size: 13px;
17 padding: 1em;
18 }
19
20 h1 {
21 font-size: 26px;
22 margin-bottom: 1em;
23 }
24
25 h2 {
26 font-size: 24px;
27 margin-bottom: 1em;
28 }
29
30 h3 {
31 font-size: 20px;
32 margin-bottom: 1em;
33 margin-top: 1em;
34 }
35
36 pre, code {
37 line-height: 1.5;
38 font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
39 }
40
41 pre {
42 margin-top: 0.5em;
43 }
44
45 h1, h2, h3, p {
46 font-family: Arial, sans serif;
47 }
48
49 h1, h2, h3 {
50 border-bottom: solid #CCC 1px;
51 }
52
53 .toc_element {
54 margin-top: 0.5em;
55 }
56
57 .firstline {
58 margin-left: 2 em;
59 }
60
61 .method {
62 margin-top: 1em;
63 border: solid 1px #CCC;
64 padding: 1em;
65 background: #EEE;
66 }
67
68 .details {
69 font-weight: bold;
70 font-size: 14px;
71 }
72
73 </style>
74
75 <h1><a href="ces_v1beta.html">Gemini Enterprise for Customer Experience API</a> . <a href="ces_v1beta.projects.html">projects</a> . <a href="ces_v1beta.projects.locations.html">locations</a> . <a href="ces_v1beta.projects.locations.apps.html">apps</a> . <a href="ces_v1beta.projects.locations.apps.evaluationDatasets.html">evaluationDatasets</a></h1>
76 <h2>Instance Methods</h2>
77 <p class="toc_element">
78 <code><a href="#close">close()</a></code></p>
79 <p class="firstline">Close httplib2 connections.</p>
80 <p class="toc_element">
81 <code><a href="#create">create(parent, body=None, evaluationDatasetId=None, x__xgafv=None)</a></code></p>
82 <p class="firstline">Creates an evaluation dataset.</p>
83 <p class="toc_element">
84 <code><a href="#delete">delete(name, etag=None, x__xgafv=None)</a></code></p>
85 <p class="firstline">Deletes an evaluation dataset.</p>
86 <p class="toc_element">
87 <code><a href="#get">get(name, x__xgafv=None)</a></code></p>
88 <p class="firstline">Gets details of the specified evaluation dataset.</p>
89 <p class="toc_element">
90 <code><a href="#list">list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)</a></code></p>
91 <p class="firstline">Lists all evaluation datasets in the given app.</p>
92 <p class="toc_element">
93 <code><a href="#list_next">list_next()</a></code></p>
94 <p class="firstline">Retrieves the next page of results.</p>
95 <p class="toc_element">
96 <code><a href="#patch">patch(name, body=None, updateMask=None, x__xgafv=None)</a></code></p>
97 <p class="firstline">Updates an evaluation dataset.</p>
98 <h3>Method Details</h3>
99 <div class="method">
100 <code class="details" id="close">close()</code>
101 <pre>Close httplib2 connections.</pre>
102 </div>
103
104 <div class="method">
105 <code class="details" id="create">create(parent, body=None, evaluationDatasetId=None, x__xgafv=None)</code>
106 <pre>Creates an evaluation dataset.
107
108 Args:
109 parent: string, Required. The app to create the evaluation for. Format: `projects/{project}/locations/{location}/apps/{app}` (required)
110 body: object, The request body.
111 The object takes the form of:
112
113 { # An evaluation dataset represents a set of evaluations that are grouped together basaed on shared tags.
114 &quot;aggregatedMetrics&quot;: { # Aggregated metrics for an evaluation or evaluation dataset. # Output only. The aggregated metrics for this evaluation dataset across all runs.
115 &quot;metricsByAppVersion&quot;: [ # Output only. Aggregated metrics, grouped by app version ID.
116 { # Metrics aggregated per app version.
117 &quot;appVersionId&quot;: &quot;A String&quot;, # Output only. The app version ID.
118 &quot;failCount&quot;: 42, # Output only. The number of times the evaluation failed.
119 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this app version.
120 { # Metrics for hallucination results.
121 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
122 },
123 ],
124 &quot;metricsByTurn&quot;: [ # Output only. Metrics aggregated per turn within this app version.
125 { # Metrics aggregated per turn.
126 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this turn.
127 { # Metrics for hallucination results.
128 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
129 },
130 ],
131 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this turn.
132 { # Metrics for semantic similarity results.
133 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
134 },
135 ],
136 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this turn.
137 { # Metrics for tool call latency.
138 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
139 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
140 },
141 ],
142 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this turn.
143 { # Metrics for a single tool.
144 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
145 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
146 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
147 },
148 ],
149 &quot;turnIndex&quot;: 42, # Output only. The turn index (0-based).
150 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this turn.
151 { # Metrics for turn latency.
152 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
153 },
154 ],
155 },
156 ],
157 &quot;passCount&quot;: 42, # Output only. The number of times the evaluation passed.
158 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this app version.
159 { # Metrics for semantic similarity results.
160 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
161 },
162 ],
163 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this app version.
164 { # Metrics for tool call latency.
165 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
166 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
167 },
168 ],
169 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this app version.
170 { # Metrics for a single tool.
171 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
172 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
173 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
174 },
175 ],
176 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this app version.
177 { # Metrics for turn latency.
178 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
179 },
180 ],
181 },
182 ],
183 },
184 &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was created.
185 &quot;createdBy&quot;: &quot;A String&quot;, # Output only. The user who created the evaluation dataset.
186 &quot;displayName&quot;: &quot;A String&quot;, # Required. User-defined display name of the evaluation dataset. Unique within an App.
187 &quot;etag&quot;: &quot;A String&quot;, # Output only. Etag used to ensure the object hasn&#x27;t changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
188 &quot;evaluations&quot;: [ # Optional. Evaluations that are included in this dataset.
189 &quot;A String&quot;,
190 ],
191 &quot;lastUpdatedBy&quot;: &quot;A String&quot;, # Output only. The user who last updated the evaluation dataset.
192 &quot;name&quot;: &quot;A String&quot;, # Identifier. The unique identifier of this evaluation dataset. Format: `projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}`
193 &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was last updated.
194 }
195
196 evaluationDatasetId: string, Optional. The ID to use for the evaluation dataset, which will become the final component of the evaluation dataset&#x27;s resource name. If not provided, a unique ID will be automatically assigned for the evaluation.
197 x__xgafv: string, V1 error format.
198 Allowed values
199 1 - v1 error format
200 2 - v2 error format
201
202 Returns:
203 An object of the form:
204
205 { # An evaluation dataset represents a set of evaluations that are grouped together basaed on shared tags.
206 &quot;aggregatedMetrics&quot;: { # Aggregated metrics for an evaluation or evaluation dataset. # Output only. The aggregated metrics for this evaluation dataset across all runs.
207 &quot;metricsByAppVersion&quot;: [ # Output only. Aggregated metrics, grouped by app version ID.
208 { # Metrics aggregated per app version.
209 &quot;appVersionId&quot;: &quot;A String&quot;, # Output only. The app version ID.
210 &quot;failCount&quot;: 42, # Output only. The number of times the evaluation failed.
211 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this app version.
212 { # Metrics for hallucination results.
213 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
214 },
215 ],
216 &quot;metricsByTurn&quot;: [ # Output only. Metrics aggregated per turn within this app version.
217 { # Metrics aggregated per turn.
218 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this turn.
219 { # Metrics for hallucination results.
220 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
221 },
222 ],
223 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this turn.
224 { # Metrics for semantic similarity results.
225 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
226 },
227 ],
228 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this turn.
229 { # Metrics for tool call latency.
230 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
231 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
232 },
233 ],
234 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this turn.
235 { # Metrics for a single tool.
236 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
237 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
238 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
239 },
240 ],
241 &quot;turnIndex&quot;: 42, # Output only. The turn index (0-based).
242 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this turn.
243 { # Metrics for turn latency.
244 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
245 },
246 ],
247 },
248 ],
249 &quot;passCount&quot;: 42, # Output only. The number of times the evaluation passed.
250 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this app version.
251 { # Metrics for semantic similarity results.
252 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
253 },
254 ],
255 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this app version.
256 { # Metrics for tool call latency.
257 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
258 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
259 },
260 ],
261 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this app version.
262 { # Metrics for a single tool.
263 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
264 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
265 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
266 },
267 ],
268 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this app version.
269 { # Metrics for turn latency.
270 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
271 },
272 ],
273 },
274 ],
275 },
276 &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was created.
277 &quot;createdBy&quot;: &quot;A String&quot;, # Output only. The user who created the evaluation dataset.
278 &quot;displayName&quot;: &quot;A String&quot;, # Required. User-defined display name of the evaluation dataset. Unique within an App.
279 &quot;etag&quot;: &quot;A String&quot;, # Output only. Etag used to ensure the object hasn&#x27;t changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
280 &quot;evaluations&quot;: [ # Optional. Evaluations that are included in this dataset.
281 &quot;A String&quot;,
282 ],
283 &quot;lastUpdatedBy&quot;: &quot;A String&quot;, # Output only. The user who last updated the evaluation dataset.
284 &quot;name&quot;: &quot;A String&quot;, # Identifier. The unique identifier of this evaluation dataset. Format: `projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}`
285 &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was last updated.
286 }</pre>
287 </div>
288
289 <div class="method">
290 <code class="details" id="delete">delete(name, etag=None, x__xgafv=None)</code>
291 <pre>Deletes an evaluation dataset.
292
293 Args:
294 name: string, Required. The resource name of the evaluation dataset to delete. (required)
295 etag: string, Optional. The current etag of the evaluation dataset. If an etag is not provided, the deletion will overwrite any concurrent changes. If an etag is provided and does not match the current etag of the evaluation dataset, deletion will be blocked and an ABORTED error will be returned.
296 x__xgafv: string, V1 error format.
297 Allowed values
298 1 - v1 error format
299 2 - v2 error format
300
301 Returns:
302 An object of the form:
303
304 { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
305 }</pre>
306 </div>
307
308 <div class="method">
309 <code class="details" id="get">get(name, x__xgafv=None)</code>
310 <pre>Gets details of the specified evaluation dataset.
311
312 Args:
313 name: string, Required. The resource name of the evaluation dataset to retrieve. (required)
314 x__xgafv: string, V1 error format.
315 Allowed values
316 1 - v1 error format
317 2 - v2 error format
318
319 Returns:
320 An object of the form:
321
322 { # An evaluation dataset represents a set of evaluations that are grouped together basaed on shared tags.
323 &quot;aggregatedMetrics&quot;: { # Aggregated metrics for an evaluation or evaluation dataset. # Output only. The aggregated metrics for this evaluation dataset across all runs.
324 &quot;metricsByAppVersion&quot;: [ # Output only. Aggregated metrics, grouped by app version ID.
325 { # Metrics aggregated per app version.
326 &quot;appVersionId&quot;: &quot;A String&quot;, # Output only. The app version ID.
327 &quot;failCount&quot;: 42, # Output only. The number of times the evaluation failed.
328 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this app version.
329 { # Metrics for hallucination results.
330 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
331 },
332 ],
333 &quot;metricsByTurn&quot;: [ # Output only. Metrics aggregated per turn within this app version.
334 { # Metrics aggregated per turn.
335 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this turn.
336 { # Metrics for hallucination results.
337 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
338 },
339 ],
340 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this turn.
341 { # Metrics for semantic similarity results.
342 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
343 },
344 ],
345 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this turn.
346 { # Metrics for tool call latency.
347 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
348 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
349 },
350 ],
351 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this turn.
352 { # Metrics for a single tool.
353 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
354 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
355 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
356 },
357 ],
358 &quot;turnIndex&quot;: 42, # Output only. The turn index (0-based).
359 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this turn.
360 { # Metrics for turn latency.
361 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
362 },
363 ],
364 },
365 ],
366 &quot;passCount&quot;: 42, # Output only. The number of times the evaluation passed.
367 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this app version.
368 { # Metrics for semantic similarity results.
369 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
370 },
371 ],
372 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this app version.
373 { # Metrics for tool call latency.
374 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
375 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
376 },
377 ],
378 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this app version.
379 { # Metrics for a single tool.
380 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
381 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
382 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
383 },
384 ],
385 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this app version.
386 { # Metrics for turn latency.
387 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
388 },
389 ],
390 },
391 ],
392 },
393 &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was created.
394 &quot;createdBy&quot;: &quot;A String&quot;, # Output only. The user who created the evaluation dataset.
395 &quot;displayName&quot;: &quot;A String&quot;, # Required. User-defined display name of the evaluation dataset. Unique within an App.
396 &quot;etag&quot;: &quot;A String&quot;, # Output only. Etag used to ensure the object hasn&#x27;t changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
397 &quot;evaluations&quot;: [ # Optional. Evaluations that are included in this dataset.
398 &quot;A String&quot;,
399 ],
400 &quot;lastUpdatedBy&quot;: &quot;A String&quot;, # Output only. The user who last updated the evaluation dataset.
401 &quot;name&quot;: &quot;A String&quot;, # Identifier. The unique identifier of this evaluation dataset. Format: `projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}`
402 &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was last updated.
403 }</pre>
404 </div>
405
406 <div class="method">
407 <code class="details" id="list">list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)</code>
408 <pre>Lists all evaluation datasets in the given app.
409
410 Args:
411 parent: string, Required. The resource name of the app to list evaluation datasets from. (required)
412 filter: string, Optional. Filter to be applied when listing the evaluation datasets. See https://google.aip.dev/160 for more details.
413 orderBy: string, Optional. Field to sort by. Only &quot;name&quot; and &quot;create_time&quot;, and &quot;update_time&quot; are supported. Time fields are ordered in descending order, and the name field is ordered in ascending order. If not included, &quot;update_time&quot; will be the default. See https://google.aip.dev/132#ordering for more details.
414 pageSize: integer, Optional. Requested page size. Server may return fewer items than requested. If unspecified, server will pick an appropriate default.
415 pageToken: string, Optional. The next_page_token value returned from a previous list EvaluationService.ListEvaluationDatasets call.
416 x__xgafv: string, V1 error format.
417 Allowed values
418 1 - v1 error format
419 2 - v2 error format
420
421 Returns:
422 An object of the form:
423
424 { # Response message for EvaluationService.ListEvaluationDatasets.
425 &quot;evaluationDatasets&quot;: [ # The list of evaluation datasets.
426 { # An evaluation dataset represents a set of evaluations that are grouped together basaed on shared tags.
427 &quot;aggregatedMetrics&quot;: { # Aggregated metrics for an evaluation or evaluation dataset. # Output only. The aggregated metrics for this evaluation dataset across all runs.
428 &quot;metricsByAppVersion&quot;: [ # Output only. Aggregated metrics, grouped by app version ID.
429 { # Metrics aggregated per app version.
430 &quot;appVersionId&quot;: &quot;A String&quot;, # Output only. The app version ID.
431 &quot;failCount&quot;: 42, # Output only. The number of times the evaluation failed.
432 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this app version.
433 { # Metrics for hallucination results.
434 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
435 },
436 ],
437 &quot;metricsByTurn&quot;: [ # Output only. Metrics aggregated per turn within this app version.
438 { # Metrics aggregated per turn.
439 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this turn.
440 { # Metrics for hallucination results.
441 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
442 },
443 ],
444 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this turn.
445 { # Metrics for semantic similarity results.
446 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
447 },
448 ],
449 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this turn.
450 { # Metrics for tool call latency.
451 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
452 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
453 },
454 ],
455 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this turn.
456 { # Metrics for a single tool.
457 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
458 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
459 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
460 },
461 ],
462 &quot;turnIndex&quot;: 42, # Output only. The turn index (0-based).
463 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this turn.
464 { # Metrics for turn latency.
465 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
466 },
467 ],
468 },
469 ],
470 &quot;passCount&quot;: 42, # Output only. The number of times the evaluation passed.
471 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this app version.
472 { # Metrics for semantic similarity results.
473 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
474 },
475 ],
476 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this app version.
477 { # Metrics for tool call latency.
478 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
479 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
480 },
481 ],
482 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this app version.
483 { # Metrics for a single tool.
484 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
485 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
486 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
487 },
488 ],
489 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this app version.
490 { # Metrics for turn latency.
491 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
492 },
493 ],
494 },
495 ],
496 },
497 &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was created.
498 &quot;createdBy&quot;: &quot;A String&quot;, # Output only. The user who created the evaluation dataset.
499 &quot;displayName&quot;: &quot;A String&quot;, # Required. User-defined display name of the evaluation dataset. Unique within an App.
500 &quot;etag&quot;: &quot;A String&quot;, # Output only. Etag used to ensure the object hasn&#x27;t changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
501 &quot;evaluations&quot;: [ # Optional. Evaluations that are included in this dataset.
502 &quot;A String&quot;,
503 ],
504 &quot;lastUpdatedBy&quot;: &quot;A String&quot;, # Output only. The user who last updated the evaluation dataset.
505 &quot;name&quot;: &quot;A String&quot;, # Identifier. The unique identifier of this evaluation dataset. Format: `projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}`
506 &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was last updated.
507 },
508 ],
509 &quot;nextPageToken&quot;: &quot;A String&quot;, # A token that can be sent as ListEvaluationDatasetsRequest.page_token to retrieve the next page. Absence of this field indicates there are no subsequent pages.
510 }</pre>
511 </div>
512
513 <div class="method">
514 <code class="details" id="list_next">list_next()</code>
515 <pre>Retrieves the next page of results.
516
517 Args:
518 previous_request: The request for the previous page. (required)
519 previous_response: The response from the request for the previous page. (required)
520
521 Returns:
522 A request object that you can call &#x27;execute()&#x27; on to request the next
523 page. Returns None if there are no more items in the collection.
524 </pre>
525 </div>
526
527 <div class="method">
528 <code class="details" id="patch">patch(name, body=None, updateMask=None, x__xgafv=None)</code>
529 <pre>Updates an evaluation dataset.
530
531 Args:
532 name: string, Identifier. The unique identifier of this evaluation dataset. Format: `projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}` (required)
533 body: object, The request body.
534 The object takes the form of:
535
536 { # An evaluation dataset represents a set of evaluations that are grouped together basaed on shared tags.
537 &quot;aggregatedMetrics&quot;: { # Aggregated metrics for an evaluation or evaluation dataset. # Output only. The aggregated metrics for this evaluation dataset across all runs.
538 &quot;metricsByAppVersion&quot;: [ # Output only. Aggregated metrics, grouped by app version ID.
539 { # Metrics aggregated per app version.
540 &quot;appVersionId&quot;: &quot;A String&quot;, # Output only. The app version ID.
541 &quot;failCount&quot;: 42, # Output only. The number of times the evaluation failed.
542 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this app version.
543 { # Metrics for hallucination results.
544 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
545 },
546 ],
547 &quot;metricsByTurn&quot;: [ # Output only. Metrics aggregated per turn within this app version.
548 { # Metrics aggregated per turn.
549 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this turn.
550 { # Metrics for hallucination results.
551 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
552 },
553 ],
554 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this turn.
555 { # Metrics for semantic similarity results.
556 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
557 },
558 ],
559 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this turn.
560 { # Metrics for tool call latency.
561 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
562 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
563 },
564 ],
565 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this turn.
566 { # Metrics for a single tool.
567 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
568 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
569 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
570 },
571 ],
572 &quot;turnIndex&quot;: 42, # Output only. The turn index (0-based).
573 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this turn.
574 { # Metrics for turn latency.
575 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
576 },
577 ],
578 },
579 ],
580 &quot;passCount&quot;: 42, # Output only. The number of times the evaluation passed.
581 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this app version.
582 { # Metrics for semantic similarity results.
583 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
584 },
585 ],
586 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this app version.
587 { # Metrics for tool call latency.
588 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
589 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
590 },
591 ],
592 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this app version.
593 { # Metrics for a single tool.
594 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
595 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
596 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
597 },
598 ],
599 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this app version.
600 { # Metrics for turn latency.
601 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
602 },
603 ],
604 },
605 ],
606 },
607 &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was created.
608 &quot;createdBy&quot;: &quot;A String&quot;, # Output only. The user who created the evaluation dataset.
609 &quot;displayName&quot;: &quot;A String&quot;, # Required. User-defined display name of the evaluation dataset. Unique within an App.
610 &quot;etag&quot;: &quot;A String&quot;, # Output only. Etag used to ensure the object hasn&#x27;t changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
611 &quot;evaluations&quot;: [ # Optional. Evaluations that are included in this dataset.
612 &quot;A String&quot;,
613 ],
614 &quot;lastUpdatedBy&quot;: &quot;A String&quot;, # Output only. The user who last updated the evaluation dataset.
615 &quot;name&quot;: &quot;A String&quot;, # Identifier. The unique identifier of this evaluation dataset. Format: `projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}`
616 &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was last updated.
617 }
618
619 updateMask: string, Optional. Field mask is used to control which fields get updated. If the mask is not present, all fields will be updated.
620 x__xgafv: string, V1 error format.
621 Allowed values
622 1 - v1 error format
623 2 - v2 error format
624
625 Returns:
626 An object of the form:
627
628 { # An evaluation dataset represents a set of evaluations that are grouped together basaed on shared tags.
629 &quot;aggregatedMetrics&quot;: { # Aggregated metrics for an evaluation or evaluation dataset. # Output only. The aggregated metrics for this evaluation dataset across all runs.
630 &quot;metricsByAppVersion&quot;: [ # Output only. Aggregated metrics, grouped by app version ID.
631 { # Metrics aggregated per app version.
632 &quot;appVersionId&quot;: &quot;A String&quot;, # Output only. The app version ID.
633 &quot;failCount&quot;: 42, # Output only. The number of times the evaluation failed.
634 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this app version.
635 { # Metrics for hallucination results.
636 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
637 },
638 ],
639 &quot;metricsByTurn&quot;: [ # Output only. Metrics aggregated per turn within this app version.
640 { # Metrics aggregated per turn.
641 &quot;hallucinationMetrics&quot;: [ # Output only. Metrics for hallucination within this turn.
642 { # Metrics for hallucination results.
643 &quot;score&quot;: 3.14, # Output only. The average hallucination score (0 to 1).
644 },
645 ],
646 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this turn.
647 { # Metrics for semantic similarity results.
648 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
649 },
650 ],
651 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this turn.
652 { # Metrics for tool call latency.
653 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
654 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
655 },
656 ],
657 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this turn.
658 { # Metrics for a single tool.
659 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
660 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
661 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
662 },
663 ],
664 &quot;turnIndex&quot;: 42, # Output only. The turn index (0-based).
665 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this turn.
666 { # Metrics for turn latency.
667 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
668 },
669 ],
670 },
671 ],
672 &quot;passCount&quot;: 42, # Output only. The number of times the evaluation passed.
673 &quot;semanticSimilarityMetrics&quot;: [ # Output only. Metrics for semantic similarity within this app version.
674 { # Metrics for semantic similarity results.
675 &quot;score&quot;: 3.14, # Output only. The average semantic similarity score (0-4).
676 },
677 ],
678 &quot;toolCallLatencyMetrics&quot;: [ # Output only. Metrics for tool call latency within this app version.
679 { # Metrics for tool call latency.
680 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the tool calls.
681 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
682 },
683 ],
684 &quot;toolMetrics&quot;: [ # Output only. Metrics for each tool within this app version.
685 { # Metrics for a single tool.
686 &quot;failCount&quot;: 42, # Output only. The number of times the tool failed.
687 &quot;passCount&quot;: 42, # Output only. The number of times the tool passed.
688 &quot;tool&quot;: &quot;A String&quot;, # Output only. The name of the tool.
689 },
690 ],
691 &quot;turnLatencyMetrics&quot;: [ # Output only. Metrics for turn latency within this app version.
692 { # Metrics for turn latency.
693 &quot;averageLatency&quot;: &quot;A String&quot;, # Output only. The average latency of the turns.
694 },
695 ],
696 },
697 ],
698 },
699 &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was created.
700 &quot;createdBy&quot;: &quot;A String&quot;, # Output only. The user who created the evaluation dataset.
701 &quot;displayName&quot;: &quot;A String&quot;, # Required. User-defined display name of the evaluation dataset. Unique within an App.
702 &quot;etag&quot;: &quot;A String&quot;, # Output only. Etag used to ensure the object hasn&#x27;t changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
703 &quot;evaluations&quot;: [ # Optional. Evaluations that are included in this dataset.
704 &quot;A String&quot;,
705 ],
706 &quot;lastUpdatedBy&quot;: &quot;A String&quot;, # Output only. The user who last updated the evaluation dataset.
707 &quot;name&quot;: &quot;A String&quot;, # Identifier. The unique identifier of this evaluation dataset. Format: `projects/{project}/locations/{location}/apps/{app}/evaluationDatasets/{evaluationDataset}`
708 &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the evaluation dataset was last updated.
709 }</pre>
710 </div>
711
712 </body></html>