edsl 0.1.39.dev1__py3-none-any.whl → 0.1.39.dev3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (256) hide show
  1. edsl/Base.py +332 -332
  2. edsl/BaseDiff.py +260 -260
  3. edsl/TemplateLoader.py +24 -24
  4. edsl/__init__.py +49 -49
  5. edsl/__version__.py +1 -1
  6. edsl/agents/Agent.py +867 -867
  7. edsl/agents/AgentList.py +413 -413
  8. edsl/agents/Invigilator.py +233 -233
  9. edsl/agents/InvigilatorBase.py +270 -265
  10. edsl/agents/PromptConstructor.py +354 -354
  11. edsl/agents/__init__.py +3 -3
  12. edsl/agents/descriptors.py +99 -99
  13. edsl/agents/prompt_helpers.py +129 -129
  14. edsl/auto/AutoStudy.py +117 -117
  15. edsl/auto/StageBase.py +230 -230
  16. edsl/auto/StageGenerateSurvey.py +178 -178
  17. edsl/auto/StageLabelQuestions.py +125 -125
  18. edsl/auto/StagePersona.py +61 -61
  19. edsl/auto/StagePersonaDimensionValueRanges.py +88 -88
  20. edsl/auto/StagePersonaDimensionValues.py +74 -74
  21. edsl/auto/StagePersonaDimensions.py +69 -69
  22. edsl/auto/StageQuestions.py +73 -73
  23. edsl/auto/SurveyCreatorPipeline.py +21 -21
  24. edsl/auto/utilities.py +224 -224
  25. edsl/base/Base.py +279 -279
  26. edsl/config.py +157 -157
  27. edsl/conversation/Conversation.py +290 -290
  28. edsl/conversation/car_buying.py +58 -58
  29. edsl/conversation/chips.py +95 -95
  30. edsl/conversation/mug_negotiation.py +81 -81
  31. edsl/conversation/next_speaker_utilities.py +93 -93
  32. edsl/coop/PriceFetcher.py +54 -54
  33. edsl/coop/__init__.py +2 -2
  34. edsl/coop/coop.py +1028 -1028
  35. edsl/coop/utils.py +131 -131
  36. edsl/data/Cache.py +555 -555
  37. edsl/data/CacheEntry.py +233 -233
  38. edsl/data/CacheHandler.py +149 -149
  39. edsl/data/RemoteCacheSync.py +78 -78
  40. edsl/data/SQLiteDict.py +292 -292
  41. edsl/data/__init__.py +4 -4
  42. edsl/data/orm.py +10 -10
  43. edsl/data_transfer_models.py +73 -73
  44. edsl/enums.py +175 -175
  45. edsl/exceptions/BaseException.py +21 -21
  46. edsl/exceptions/__init__.py +54 -54
  47. edsl/exceptions/agents.py +42 -42
  48. edsl/exceptions/cache.py +5 -5
  49. edsl/exceptions/configuration.py +16 -16
  50. edsl/exceptions/coop.py +10 -10
  51. edsl/exceptions/data.py +14 -14
  52. edsl/exceptions/general.py +34 -34
  53. edsl/exceptions/jobs.py +33 -33
  54. edsl/exceptions/language_models.py +63 -63
  55. edsl/exceptions/prompts.py +15 -15
  56. edsl/exceptions/questions.py +91 -91
  57. edsl/exceptions/results.py +29 -29
  58. edsl/exceptions/scenarios.py +22 -22
  59. edsl/exceptions/surveys.py +37 -37
  60. edsl/inference_services/AnthropicService.py +87 -87
  61. edsl/inference_services/AwsBedrock.py +120 -120
  62. edsl/inference_services/AzureAI.py +217 -217
  63. edsl/inference_services/DeepInfraService.py +18 -18
  64. edsl/inference_services/GoogleService.py +148 -148
  65. edsl/inference_services/GroqService.py +20 -20
  66. edsl/inference_services/InferenceServiceABC.py +147 -147
  67. edsl/inference_services/InferenceServicesCollection.py +97 -97
  68. edsl/inference_services/MistralAIService.py +123 -123
  69. edsl/inference_services/OllamaService.py +18 -18
  70. edsl/inference_services/OpenAIService.py +224 -224
  71. edsl/inference_services/PerplexityService.py +163 -163
  72. edsl/inference_services/TestService.py +89 -89
  73. edsl/inference_services/TogetherAIService.py +170 -170
  74. edsl/inference_services/models_available_cache.py +118 -118
  75. edsl/inference_services/rate_limits_cache.py +25 -25
  76. edsl/inference_services/registry.py +41 -41
  77. edsl/inference_services/write_available.py +10 -10
  78. edsl/jobs/Answers.py +56 -56
  79. edsl/jobs/Jobs.py +898 -898
  80. edsl/jobs/JobsChecks.py +147 -147
  81. edsl/jobs/JobsPrompts.py +268 -268
  82. edsl/jobs/JobsRemoteInferenceHandler.py +239 -239
  83. edsl/jobs/__init__.py +1 -1
  84. edsl/jobs/buckets/BucketCollection.py +63 -63
  85. edsl/jobs/buckets/ModelBuckets.py +65 -65
  86. edsl/jobs/buckets/TokenBucket.py +251 -251
  87. edsl/jobs/interviews/Interview.py +661 -661
  88. edsl/jobs/interviews/InterviewExceptionCollection.py +99 -99
  89. edsl/jobs/interviews/InterviewExceptionEntry.py +186 -186
  90. edsl/jobs/interviews/InterviewStatistic.py +63 -63
  91. edsl/jobs/interviews/InterviewStatisticsCollection.py +25 -25
  92. edsl/jobs/interviews/InterviewStatusDictionary.py +78 -78
  93. edsl/jobs/interviews/InterviewStatusLog.py +92 -92
  94. edsl/jobs/interviews/ReportErrors.py +66 -66
  95. edsl/jobs/interviews/interview_status_enum.py +9 -9
  96. edsl/jobs/runners/JobsRunnerAsyncio.py +466 -466
  97. edsl/jobs/runners/JobsRunnerStatus.py +330 -330
  98. edsl/jobs/tasks/QuestionTaskCreator.py +242 -242
  99. edsl/jobs/tasks/TaskCreators.py +64 -64
  100. edsl/jobs/tasks/TaskHistory.py +450 -450
  101. edsl/jobs/tasks/TaskStatusLog.py +23 -23
  102. edsl/jobs/tasks/task_status_enum.py +163 -163
  103. edsl/jobs/tokens/InterviewTokenUsage.py +27 -27
  104. edsl/jobs/tokens/TokenUsage.py +34 -34
  105. edsl/language_models/KeyLookup.py +30 -30
  106. edsl/language_models/LanguageModel.py +668 -668
  107. edsl/language_models/ModelList.py +155 -155
  108. edsl/language_models/RegisterLanguageModelsMeta.py +184 -184
  109. edsl/language_models/__init__.py +3 -3
  110. edsl/language_models/fake_openai_call.py +15 -15
  111. edsl/language_models/fake_openai_service.py +61 -61
  112. edsl/language_models/registry.py +190 -190
  113. edsl/language_models/repair.py +156 -156
  114. edsl/language_models/unused/ReplicateBase.py +83 -83
  115. edsl/language_models/utilities.py +64 -64
  116. edsl/notebooks/Notebook.py +258 -258
  117. edsl/notebooks/__init__.py +1 -1
  118. edsl/prompts/Prompt.py +362 -362
  119. edsl/prompts/__init__.py +2 -2
  120. edsl/questions/AnswerValidatorMixin.py +289 -289
  121. edsl/questions/QuestionBase.py +664 -664
  122. edsl/questions/QuestionBaseGenMixin.py +161 -161
  123. edsl/questions/QuestionBasePromptsMixin.py +217 -217
  124. edsl/questions/QuestionBudget.py +227 -227
  125. edsl/questions/QuestionCheckBox.py +359 -359
  126. edsl/questions/QuestionExtract.py +182 -182
  127. edsl/questions/QuestionFreeText.py +114 -114
  128. edsl/questions/QuestionFunctional.py +166 -166
  129. edsl/questions/QuestionList.py +231 -231
  130. edsl/questions/QuestionMultipleChoice.py +286 -286
  131. edsl/questions/QuestionNumerical.py +153 -153
  132. edsl/questions/QuestionRank.py +324 -324
  133. edsl/questions/Quick.py +41 -41
  134. edsl/questions/RegisterQuestionsMeta.py +71 -71
  135. edsl/questions/ResponseValidatorABC.py +174 -174
  136. edsl/questions/SimpleAskMixin.py +73 -73
  137. edsl/questions/__init__.py +26 -26
  138. edsl/questions/compose_questions.py +98 -98
  139. edsl/questions/decorators.py +21 -21
  140. edsl/questions/derived/QuestionLikertFive.py +76 -76
  141. edsl/questions/derived/QuestionLinearScale.py +87 -87
  142. edsl/questions/derived/QuestionTopK.py +93 -93
  143. edsl/questions/derived/QuestionYesNo.py +82 -82
  144. edsl/questions/descriptors.py +413 -413
  145. edsl/questions/prompt_templates/question_budget.jinja +13 -13
  146. edsl/questions/prompt_templates/question_checkbox.jinja +32 -32
  147. edsl/questions/prompt_templates/question_extract.jinja +11 -11
  148. edsl/questions/prompt_templates/question_free_text.jinja +3 -3
  149. edsl/questions/prompt_templates/question_linear_scale.jinja +11 -11
  150. edsl/questions/prompt_templates/question_list.jinja +17 -17
  151. edsl/questions/prompt_templates/question_multiple_choice.jinja +33 -33
  152. edsl/questions/prompt_templates/question_numerical.jinja +36 -36
  153. edsl/questions/question_registry.py +177 -177
  154. edsl/questions/settings.py +12 -12
  155. edsl/questions/templates/budget/answering_instructions.jinja +7 -7
  156. edsl/questions/templates/budget/question_presentation.jinja +7 -7
  157. edsl/questions/templates/checkbox/answering_instructions.jinja +10 -10
  158. edsl/questions/templates/checkbox/question_presentation.jinja +22 -22
  159. edsl/questions/templates/extract/answering_instructions.jinja +7 -7
  160. edsl/questions/templates/likert_five/answering_instructions.jinja +10 -10
  161. edsl/questions/templates/likert_five/question_presentation.jinja +11 -11
  162. edsl/questions/templates/linear_scale/answering_instructions.jinja +5 -5
  163. edsl/questions/templates/linear_scale/question_presentation.jinja +5 -5
  164. edsl/questions/templates/list/answering_instructions.jinja +3 -3
  165. edsl/questions/templates/list/question_presentation.jinja +5 -5
  166. edsl/questions/templates/multiple_choice/answering_instructions.jinja +9 -9
  167. edsl/questions/templates/multiple_choice/question_presentation.jinja +11 -11
  168. edsl/questions/templates/numerical/answering_instructions.jinja +6 -6
  169. edsl/questions/templates/numerical/question_presentation.jinja +6 -6
  170. edsl/questions/templates/rank/answering_instructions.jinja +11 -11
  171. edsl/questions/templates/rank/question_presentation.jinja +15 -15
  172. edsl/questions/templates/top_k/answering_instructions.jinja +8 -8
  173. edsl/questions/templates/top_k/question_presentation.jinja +22 -22
  174. edsl/questions/templates/yes_no/answering_instructions.jinja +6 -6
  175. edsl/questions/templates/yes_no/question_presentation.jinja +11 -11
  176. edsl/results/CSSParameterizer.py +108 -108
  177. edsl/results/Dataset.py +424 -424
  178. edsl/results/DatasetExportMixin.py +731 -731
  179. edsl/results/DatasetTree.py +275 -275
  180. edsl/results/Result.py +465 -465
  181. edsl/results/Results.py +1165 -1165
  182. edsl/results/ResultsDBMixin.py +238 -238
  183. edsl/results/ResultsExportMixin.py +43 -43
  184. edsl/results/ResultsFetchMixin.py +33 -33
  185. edsl/results/ResultsGGMixin.py +121 -121
  186. edsl/results/ResultsToolsMixin.py +98 -98
  187. edsl/results/Selector.py +135 -135
  188. edsl/results/TableDisplay.py +198 -198
  189. edsl/results/__init__.py +2 -2
  190. edsl/results/table_display.css +77 -77
  191. edsl/results/tree_explore.py +115 -115
  192. edsl/scenarios/FileStore.py +632 -632
  193. edsl/scenarios/Scenario.py +601 -601
  194. edsl/scenarios/ScenarioHtmlMixin.py +64 -64
  195. edsl/scenarios/ScenarioJoin.py +127 -127
  196. edsl/scenarios/ScenarioList.py +1287 -1287
  197. edsl/scenarios/ScenarioListExportMixin.py +52 -52
  198. edsl/scenarios/ScenarioListPdfMixin.py +261 -261
  199. edsl/scenarios/__init__.py +4 -4
  200. edsl/shared.py +1 -1
  201. edsl/study/ObjectEntry.py +173 -173
  202. edsl/study/ProofOfWork.py +113 -113
  203. edsl/study/SnapShot.py +80 -80
  204. edsl/study/Study.py +528 -528
  205. edsl/study/__init__.py +4 -4
  206. edsl/surveys/DAG.py +148 -148
  207. edsl/surveys/Memory.py +31 -31
  208. edsl/surveys/MemoryPlan.py +244 -244
  209. edsl/surveys/Rule.py +326 -326
  210. edsl/surveys/RuleCollection.py +387 -387
  211. edsl/surveys/Survey.py +1801 -1801
  212. edsl/surveys/SurveyCSS.py +261 -261
  213. edsl/surveys/SurveyExportMixin.py +259 -259
  214. edsl/surveys/SurveyFlowVisualizationMixin.py +179 -179
  215. edsl/surveys/SurveyQualtricsImport.py +284 -284
  216. edsl/surveys/__init__.py +3 -3
  217. edsl/surveys/base.py +53 -53
  218. edsl/surveys/descriptors.py +56 -56
  219. edsl/surveys/instructions/ChangeInstruction.py +49 -49
  220. edsl/surveys/instructions/Instruction.py +65 -65
  221. edsl/surveys/instructions/InstructionCollection.py +77 -77
  222. edsl/templates/error_reporting/base.html +23 -23
  223. edsl/templates/error_reporting/exceptions_by_model.html +34 -34
  224. edsl/templates/error_reporting/exceptions_by_question_name.html +16 -16
  225. edsl/templates/error_reporting/exceptions_by_type.html +16 -16
  226. edsl/templates/error_reporting/interview_details.html +115 -115
  227. edsl/templates/error_reporting/interviews.html +19 -19
  228. edsl/templates/error_reporting/overview.html +4 -4
  229. edsl/templates/error_reporting/performance_plot.html +1 -1
  230. edsl/templates/error_reporting/report.css +73 -73
  231. edsl/templates/error_reporting/report.html +117 -117
  232. edsl/templates/error_reporting/report.js +25 -25
  233. edsl/tools/__init__.py +1 -1
  234. edsl/tools/clusters.py +192 -192
  235. edsl/tools/embeddings.py +27 -27
  236. edsl/tools/embeddings_plotting.py +118 -118
  237. edsl/tools/plotting.py +112 -112
  238. edsl/tools/summarize.py +18 -18
  239. edsl/utilities/SystemInfo.py +28 -28
  240. edsl/utilities/__init__.py +22 -22
  241. edsl/utilities/ast_utilities.py +25 -25
  242. edsl/utilities/data/Registry.py +6 -6
  243. edsl/utilities/data/__init__.py +1 -1
  244. edsl/utilities/data/scooter_results.json +1 -1
  245. edsl/utilities/decorators.py +77 -77
  246. edsl/utilities/gcp_bucket/cloud_storage.py +96 -96
  247. edsl/utilities/interface.py +627 -627
  248. edsl/utilities/naming_utilities.py +263 -263
  249. edsl/utilities/repair_functions.py +28 -28
  250. edsl/utilities/restricted_python.py +70 -70
  251. edsl/utilities/utilities.py +424 -424
  252. {edsl-0.1.39.dev1.dist-info → edsl-0.1.39.dev3.dist-info}/LICENSE +21 -21
  253. {edsl-0.1.39.dev1.dist-info → edsl-0.1.39.dev3.dist-info}/METADATA +1 -1
  254. edsl-0.1.39.dev3.dist-info/RECORD +277 -0
  255. edsl-0.1.39.dev1.dist-info/RECORD +0 -277
  256. {edsl-0.1.39.dev1.dist-info → edsl-0.1.39.dev3.dist-info}/WHEEL +0 -0
@@ -1,35 +1,35 @@
1
- <h2>Exceptions by Model</h2>
2
- <table border="1">
3
- <thead>
4
- <tr>
5
- <th>Model</th>
6
- <th>Number</th>
7
- </tr>
8
- </thead>
9
- <tbody>
10
- {% for model, exceptions in exceptions_by_model.items() %}
11
- <tr>
12
- <td>{{ model }}</td>
13
- <td>{{ exceptions }}</td>
14
- </tr>
15
- {% endfor %}
16
- </tbody>
17
- </table>
18
-
19
- <h2>Exceptions by Service</h2>
20
- <table border="1">
21
- <thead>
22
- <tr>
23
- <th>Service</th>
24
- <th>Number</th>
25
- </tr>
26
- </thead>
27
- <tbody>
28
- {% for service, exceptions in exceptions_by_service.items() %}
29
- <tr>
30
- <td>{{ service }}</td>
31
- <td>{{ exceptions }}</td>
32
- </tr>
33
- {% endfor %}
34
- </tbody>
1
+ <h2>Exceptions by Model</h2>
2
+ <table border="1">
3
+ <thead>
4
+ <tr>
5
+ <th>Model</th>
6
+ <th>Number</th>
7
+ </tr>
8
+ </thead>
9
+ <tbody>
10
+ {% for model, exceptions in exceptions_by_model.items() %}
11
+ <tr>
12
+ <td>{{ model }}</td>
13
+ <td>{{ exceptions }}</td>
14
+ </tr>
15
+ {% endfor %}
16
+ </tbody>
17
+ </table>
18
+
19
+ <h2>Exceptions by Service</h2>
20
+ <table border="1">
21
+ <thead>
22
+ <tr>
23
+ <th>Service</th>
24
+ <th>Number</th>
25
+ </tr>
26
+ </thead>
27
+ <tbody>
28
+ {% for service, exceptions in exceptions_by_service.items() %}
29
+ <tr>
30
+ <td>{{ service }}</td>
31
+ <td>{{ exceptions }}</td>
32
+ </tr>
33
+ {% endfor %}
34
+ </tbody>
35
35
  </table>
@@ -1,17 +1,17 @@
1
- <h2>Exceptions by Question Name</h2>
2
- <table border="1">
3
- <thead>
4
- <tr>
5
- <th>Question Name</th>
6
- <th>Number of Exceptions</th>
7
- </tr>
8
- </thead>
9
- <tbody>
10
- {% for question_name, exception_count in exceptions_by_question_name.items() %}
11
- <tr>
12
- <td>{{ question_name }}</td>
13
- <td>{{ exception_count }}</td>
14
- </tr>
15
- {% endfor %}
16
- </tbody>
1
+ <h2>Exceptions by Question Name</h2>
2
+ <table border="1">
3
+ <thead>
4
+ <tr>
5
+ <th>Question Name</th>
6
+ <th>Number of Exceptions</th>
7
+ </tr>
8
+ </thead>
9
+ <tbody>
10
+ {% for question_name, exception_count in exceptions_by_question_name.items() %}
11
+ <tr>
12
+ <td>{{ question_name }}</td>
13
+ <td>{{ exception_count }}</td>
14
+ </tr>
15
+ {% endfor %}
16
+ </tbody>
17
17
  </table>
@@ -1,17 +1,17 @@
1
- <h2>Exceptions by Type</h2>
2
- <table border="1">
3
- <thead>
4
- <tr>
5
- <th>Exception Type</th>
6
- <th>Number</th>
7
- </tr>
8
- </thead>
9
- <tbody>
10
- {% for exception_type, exceptions in exceptions_by_type.items() %}
11
- <tr>
12
- <td>{{ exception_type }}</td>
13
- <td>{{ exceptions }}</td>
14
- </tr>
15
- {% endfor %}
16
- </tbody>
1
+ <h2>Exceptions by Type</h2>
2
+ <table border="1">
3
+ <thead>
4
+ <tr>
5
+ <th>Exception Type</th>
6
+ <th>Number</th>
7
+ </tr>
8
+ </thead>
9
+ <tbody>
10
+ {% for exception_type, exceptions in exceptions_by_type.items() %}
11
+ <tr>
12
+ <td>{{ exception_type }}</td>
13
+ <td>{{ exceptions }}</td>
14
+ </tr>
15
+ {% endfor %}
16
+ </tbody>
17
17
  </table>
@@ -1,116 +1,116 @@
1
- <div class="question">question_name: {{ question }}</div>
2
-
3
-
4
- <h2>Exception details</h2>
5
-
6
- {% for exception_message in exceptions %}
7
- <div class="exception-detail">
8
- <div class="exception-header">
9
- <span class="exception-exception">Exception: {{ exception_message.name }}</span>
10
- <button class="toggle-btn">▼</button>
11
- </div>
12
- <div class="exception-content">
13
- <table border="1">
14
- <tr>
15
- <th>Key</th>
16
- <th>Value</th>
17
- </tr>
18
- <tr>
19
- <td>Interview ID (index in results)</td>
20
- <td>{{ index }}</td>
21
- </tr>
22
- <tr>
23
- <td>Question name (question_name)</td>
24
- <td>{{ question }}</td>
25
- </tr>
26
-
27
- <tr>
28
- <td>Question type (question_type)</td>
29
- <td>{{ exception_message.question_type }}</td>
30
- </tr>
31
-
32
- <tr>
33
- <td>Human-readable question</td>
34
- <td>{{ interview.survey.get_question(question).html(
35
- scenario = interview.scenario,
36
- agent = interview.agent,
37
- answers = exception_message.answers)
38
-
39
- }}</td>
40
- </tr>
41
- <tr>
42
- <td>Scenario</td>
43
- <td>{{ interview.scenario.__repr__() }}</td>
44
- </tr>
45
- <tr>
46
- <td>Agent</td>
47
- <td>{{ interview.agent.__repr__() }}</td>
48
- </tr>
49
- <tr>
50
- <td>Model name</td>
51
- <td>{{ interview.model.model }}</td>
52
- </tr>
53
- <tr>
54
- <td>Inference service</td>
55
- <td>{{ interview.model._inference_service_ }}</td>
56
- </tr>
57
- <tr>
58
- <td>Model parameters</td>
59
- <td>{{ interview.model.__repr__() }}</td>
60
- </tr>
61
- <tr>
62
- <td>User Prompt</td>
63
- <td><pre>{{ exception_message.rendered_prompts['user_prompt'] }}</pre></td>
64
- </tr>
65
- <tr>
66
- <td>System Prompt</td>
67
- <td><pre>{{ exception_message.rendered_prompts['system_prompt'] }}</pre></td>
68
- </tr>
69
- <tr>
70
- <td>Raw model response</td>
71
- <td><pre>{{ exception_message.raw_model_response }}</pre>
72
- </td>
73
- </tr>
74
- <tr>
75
- <td>Generated token string (at {{ exception_message.key_sequence }}) in raw response</td>
76
- <td><pre>{{ exception_message.generated_token_string }}</pre>
77
- </td>
78
- </tr>
79
- <tr>
80
- <td>Code to (likely) reproduce the error</td>
81
- <td>
82
- <textarea id="codeToCopy" rows="10" cols="90">{{ exception_message.code_to_reproduce }}</textarea>
83
- <button onclick="copyCode()">Copy</button>
84
- </td>
85
- </tr>
86
-
87
- </table>
88
-
89
-
90
- {% if exception_message.exception.__class__.__name__ == 'QuestionAnswerValidationError' %}
91
- <h3>Answer validation details</h3>
92
- <table border="1">
93
- <tr>
94
- <th>Field</th>
95
- <th>Value</th>
96
- </tr>
97
- {% for field, (explanation, open_tag, close_tag, value) in exception_message.exception.to_html_dict().items() %}
98
-
99
- <tr>
100
- <td>{{ field }}: ({{ explanation }})</td>
101
- <td><{{open_tag}}> {{ value | escape }} <{{close_tag}}></td>
102
- </tr>
103
- {% endfor %}
104
- </table>
105
- {% endif %}
106
-
107
- <div class="exception-time">Time: {{ exception_message.time }}</div>
108
- <div class="exception-traceback">Traceback:
109
- <text>
110
- <pre>{{ exception_message.traceback }}</pre>
111
- </text>
112
- </div>
113
- </div>
114
- </div>
115
-
1
+ <div class="question">question_name: {{ question }}</div>
2
+
3
+
4
+ <h2>Exception details</h2>
5
+
6
+ {% for exception_message in exceptions %}
7
+ <div class="exception-detail">
8
+ <div class="exception-header">
9
+ <span class="exception-exception">Exception: {{ exception_message.name }}</span>
10
+ <button class="toggle-btn">▼</button>
11
+ </div>
12
+ <div class="exception-content">
13
+ <table border="1">
14
+ <tr>
15
+ <th>Key</th>
16
+ <th>Value</th>
17
+ </tr>
18
+ <tr>
19
+ <td>Interview ID (index in results)</td>
20
+ <td>{{ index }}</td>
21
+ </tr>
22
+ <tr>
23
+ <td>Question name (question_name)</td>
24
+ <td>{{ question }}</td>
25
+ </tr>
26
+
27
+ <tr>
28
+ <td>Question type (question_type)</td>
29
+ <td>{{ exception_message.question_type }}</td>
30
+ </tr>
31
+
32
+ <tr>
33
+ <td>Human-readable question</td>
34
+ <td>{{ interview.survey.get_question(question).html(
35
+ scenario = interview.scenario,
36
+ agent = interview.agent,
37
+ answers = exception_message.answers)
38
+
39
+ }}</td>
40
+ </tr>
41
+ <tr>
42
+ <td>Scenario</td>
43
+ <td>{{ interview.scenario.__repr__() }}</td>
44
+ </tr>
45
+ <tr>
46
+ <td>Agent</td>
47
+ <td>{{ interview.agent.__repr__() }}</td>
48
+ </tr>
49
+ <tr>
50
+ <td>Model name</td>
51
+ <td>{{ interview.model.model }}</td>
52
+ </tr>
53
+ <tr>
54
+ <td>Inference service</td>
55
+ <td>{{ interview.model._inference_service_ }}</td>
56
+ </tr>
57
+ <tr>
58
+ <td>Model parameters</td>
59
+ <td>{{ interview.model.__repr__() }}</td>
60
+ </tr>
61
+ <tr>
62
+ <td>User Prompt</td>
63
+ <td><pre>{{ exception_message.rendered_prompts['user_prompt'] }}</pre></td>
64
+ </tr>
65
+ <tr>
66
+ <td>System Prompt</td>
67
+ <td><pre>{{ exception_message.rendered_prompts['system_prompt'] }}</pre></td>
68
+ </tr>
69
+ <tr>
70
+ <td>Raw model response</td>
71
+ <td><pre>{{ exception_message.raw_model_response }}</pre>
72
+ </td>
73
+ </tr>
74
+ <tr>
75
+ <td>Generated token string (at {{ exception_message.key_sequence }}) in raw response</td>
76
+ <td><pre>{{ exception_message.generated_token_string }}</pre>
77
+ </td>
78
+ </tr>
79
+ <tr>
80
+ <td>Code to (likely) reproduce the error</td>
81
+ <td>
82
+ <textarea id="codeToCopy" rows="10" cols="90">{{ exception_message.code_to_reproduce }}</textarea>
83
+ <button onclick="copyCode()">Copy</button>
84
+ </td>
85
+ </tr>
86
+
87
+ </table>
88
+
89
+
90
+ {% if exception_message.exception.__class__.__name__ == 'QuestionAnswerValidationError' %}
91
+ <h3>Answer validation details</h3>
92
+ <table border="1">
93
+ <tr>
94
+ <th>Field</th>
95
+ <th>Value</th>
96
+ </tr>
97
+ {% for field, (explanation, open_tag, close_tag, value) in exception_message.exception.to_html_dict().items() %}
98
+
99
+ <tr>
100
+ <td>{{ field }}: ({{ explanation }})</td>
101
+ <td><{{open_tag}}> {{ value | escape }} <{{close_tag}}></td>
102
+ </tr>
103
+ {% endfor %}
104
+ </table>
105
+ {% endif %}
106
+
107
+ <div class="exception-time">Time: {{ exception_message.time }}</div>
108
+ <div class="exception-traceback">Traceback:
109
+ <text>
110
+ <pre>{{ exception_message.traceback }}</pre>
111
+ </text>
112
+ </div>
113
+ </div>
114
+ </div>
115
+
116
116
  {% endfor %}
@@ -1,19 +1,19 @@
1
-
2
- {% if interviews|length > max_interviews %}
3
- <h1>Only showing the first {{ max_interviews }} interviews with errors</h1>
4
- {% else %}
5
- <h1>Showing all interviews</h1>
6
- {% endif %}
7
-
8
- {% for index, interview in interviews.items() %}
9
- {% if index < max_interviews %}
10
- {% if interview.exceptions != {} %}
11
- <div class="interview">Interview: {{ index }} </div>
12
- Model: {{ interview.model.model }}
13
- <h1>Failing questions</h1>
14
- {% endif %}
15
- {% for question, exceptions in interview.exceptions.items() %}
16
- {% include 'interview_details.html' %}
17
- {% endfor %}
18
- {% endif %}
19
- {% endfor %}
1
+
2
+ {% if interviews|length > max_interviews %}
3
+ <h1>Only showing the first {{ max_interviews }} interviews with errors</h1>
4
+ {% else %}
5
+ <h1>Showing all interviews</h1>
6
+ {% endif %}
7
+
8
+ {% for index, interview in interviews.items() %}
9
+ {% if index < max_interviews %}
10
+ {% if interview.exceptions != {} %}
11
+ <div class="interview">Interview: {{ index }} </div>
12
+ Model: {{ interview.model.model }}
13
+ <h1>Failing questions</h1>
14
+ {% endif %}
15
+ {% for question, exceptions in interview.exceptions.items() %}
16
+ {% include 'interview_details.html' %}
17
+ {% endfor %}
18
+ {% endif %}
19
+ {% endfor %}
@@ -1,5 +1,5 @@
1
- <h1>Overview</h1>
2
- <p>There were {{ interviews|length }} total interview(s). An 'interview' is the result of one survey, taken by one agent, with one model, with one scenario.</p>
3
- The number of interviews with any exceptions was {{ num_exceptions }}.</p>
4
- <p>For advice on dealing with exceptions on Expected Parrot,
1
+ <h1>Overview</h1>
2
+ <p>There were {{ interviews|length }} total interview(s). An 'interview' is the result of one survey, taken by one agent, with one model, with one scenario.</p>
3
+ The number of interviews with any exceptions was {{ num_exceptions }}.</p>
4
+ <p>For advice on dealing with exceptions on Expected Parrot,
5
5
  see <a href="https://docs.expectedparrot.com/en/latest/exceptions.html">here</a>.</p>
@@ -1,2 +1,2 @@
1
- <h1>Performance Plot</h1>
1
+ <h1>Performance Plot</h1>
2
2
  {{ performance_plot_html }}
@@ -1,74 +1,74 @@
1
- body {
2
- font-family: Arial, sans-serif;
3
- line-height: 1.6;
4
- background-color: #f9f9f9;
5
- color: #333;
6
- margin: 20px;
7
- }
8
-
9
- .interview {
10
- font-size: 1.5em;
11
- margin-bottom: 10px;
12
- padding: 10px;
13
- background-color: #e3f2fd;
14
- border-left: 5px solid #2196f3;
15
- }
16
-
17
- .question {
18
- font-size: 1.2em;
19
- margin-bottom: 10px;
20
- padding: 10px;
21
- background-color: #fff9c4;
22
- border-left: 5px solid #ffeb3b;
23
- }
24
-
25
- .exception-detail {
26
- margin-bottom: 10px;
27
- background-color: #ffebee;
28
- border-left: 5px solid #f44336;
29
- }
30
-
31
- .exception-header {
32
- padding: 10px;
33
- cursor: pointer;
34
- display: flex;
35
- justify-content: space-between;
36
- align-items: center;
37
- }
38
-
39
- .exception-content {
40
- padding: 10px;
41
- display: none;
42
- }
43
-
44
- .exception-content.show {
45
- display: block;
46
- }
47
-
48
- .question-detail {
49
- border: 3px solid black;
50
- padding: 10px;
51
- }
52
-
53
- .exception-exception {
54
- font-weight: bold;
55
- color: #d32f2f;
56
- }
57
-
58
- .exception-time,
59
- .exception-traceback {
60
- font-style: italic;
61
- color: #555;
62
- }
63
-
64
- .toggle-btn {
65
- background: none;
66
- border: none;
67
- font-size: 1.2em;
68
- cursor: pointer;
69
- transition: transform 0.3s;
70
- }
71
-
72
- .toggle-btn.rotated {
73
- transform: rotate(180deg);
1
+ body {
2
+ font-family: Arial, sans-serif;
3
+ line-height: 1.6;
4
+ background-color: #f9f9f9;
5
+ color: #333;
6
+ margin: 20px;
7
+ }
8
+
9
+ .interview {
10
+ font-size: 1.5em;
11
+ margin-bottom: 10px;
12
+ padding: 10px;
13
+ background-color: #e3f2fd;
14
+ border-left: 5px solid #2196f3;
15
+ }
16
+
17
+ .question {
18
+ font-size: 1.2em;
19
+ margin-bottom: 10px;
20
+ padding: 10px;
21
+ background-color: #fff9c4;
22
+ border-left: 5px solid #ffeb3b;
23
+ }
24
+
25
+ .exception-detail {
26
+ margin-bottom: 10px;
27
+ background-color: #ffebee;
28
+ border-left: 5px solid #f44336;
29
+ }
30
+
31
+ .exception-header {
32
+ padding: 10px;
33
+ cursor: pointer;
34
+ display: flex;
35
+ justify-content: space-between;
36
+ align-items: center;
37
+ }
38
+
39
+ .exception-content {
40
+ padding: 10px;
41
+ display: none;
42
+ }
43
+
44
+ .exception-content.show {
45
+ display: block;
46
+ }
47
+
48
+ .question-detail {
49
+ border: 3px solid black;
50
+ padding: 10px;
51
+ }
52
+
53
+ .exception-exception {
54
+ font-weight: bold;
55
+ color: #d32f2f;
56
+ }
57
+
58
+ .exception-time,
59
+ .exception-traceback {
60
+ font-style: italic;
61
+ color: #555;
62
+ }
63
+
64
+ .toggle-btn {
65
+ background: none;
66
+ border: none;
67
+ font-size: 1.2em;
68
+ cursor: pointer;
69
+ transition: transform 0.3s;
70
+ }
71
+
72
+ .toggle-btn.rotated {
73
+ transform: rotate(180deg);
74
74
  }