arize-phoenix 4.4.4rc3__py3-none-any.whl → 4.4.4rc5__py3-none-any.whl

{arize_phoenix-4.4.4rc3.dist-info → arize_phoenix-4.4.4rc5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: arize-phoenix
-Version: 4.4.4rc3
+Version: 4.4.4rc5
 Summary: AI Observability and Evaluation
 Project-URL: Documentation, https://docs.arize.com/phoenix/
 Project-URL: Issues, https://github.com/Arize-ai/phoenix/issues
@@ -31,7 +31,7 @@ Requires-Dist: openinference-instrumentation
 Requires-Dist: openinference-instrumentation-langchain>=0.1.12
 Requires-Dist: openinference-instrumentation-llama-index>=1.2.0
 Requires-Dist: openinference-instrumentation-openai>=0.1.4
-Requires-Dist: openinference-semantic-conventions>=0.1.5
+Requires-Dist: openinference-semantic-conventions>=0.1.9
 Requires-Dist: opentelemetry-exporter-otlp
 Requires-Dist: opentelemetry-proto>=1.12.0
 Requires-Dist: opentelemetry-sdk

{arize_phoenix-4.4.4rc3.dist-info → arize_phoenix-4.4.4rc5.dist-info}/RECORD

@@ -5,17 +5,20 @@ phoenix/exceptions.py,sha256=n2L2KKuecrdflB9MsCdAYCiSEvGJptIsfRkXMoJle7A,169
 phoenix/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 phoenix/services.py,sha256=aTxhcOA1pZHB6U-B3TEcp6fqDF5oT0xCUvEUNMZVTUQ,5175
 phoenix/settings.py,sha256=cO-qgis_S27nHirTobYI9hHPfZH18R--WMmxNdsVUwc,273
-phoenix/version.py,sha256=vkzG2Z0dkYNWJYkiDnpu7yJxir6A-qjTBfFVeklU7TY,25
+phoenix/version.py,sha256=-Vg_bLotyeJdv0gFqG5-A64nsG-6AR0xZSp3sDDsV_w,25
 phoenix/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/core/embedding_dimension.py,sha256=zKGbcvwOXgLf-yrJBpQyKtd-LEOPRKHnUToyAU8Owis,87
 phoenix/core/model.py,sha256=km_a--PBHOuA337ClRw9xqhOHhrUT6Rl9pz_zV0JYkQ,4843
 phoenix/core/model_schema.py,sha256=F2dbbVnkDLsPYoyZDv1q03uhvP8LcU1wXp0g-exiWs0,50551
 phoenix/core/model_schema_adapter.py,sha256=0Tm_Y_gV-WED8fKBCaFXAEFwE3CTEZS1dowqnTZ7x7g,8426
 phoenix/datasets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-phoenix/datasets/evaluators.py,sha256=_ezCRB6cyhuJsxsQJRFt2CKg3vqV-KgtBi9NNtkdeJQ,10410
-phoenix/datasets/experiments.py,sha256=D1gmdCbOC7tkjrFjyC_WPNFyY41YrqKESsPE0CebTtc,19223
-phoenix/datasets/tracing.py,sha256=Ieb2Uo-9qHpmv65uf1VsFSsWo5Yxj6VHwGS6dxu9NHQ,2248
-phoenix/datasets/types.py,sha256=w0KoSP7AdlcFlV3I6qVtvKOOWoK0yiY6_s4CvH0flcs,5753
+phoenix/datasets/experiments.py,sha256=RzZezHQcTpPcr7gY9rGtoYlfoesFNhNV7EO5f_oHNFk,21198
+phoenix/datasets/tracing.py,sha256=wVpt8Ie9WNPoi1djJdcrkwCokHdTO0bicXViLg3O-1Y,2831
+phoenix/datasets/types.py,sha256=N17mnnVwmu1k3bnmbyROPt_6TxPaZY_QkOZmCOR5_jE,4835
+phoenix/datasets/evaluators/__init__.py,sha256=KSr9fNG4O93swYxNdPj_UihP9Itl_5mj0a492wi_4_0,465
+phoenix/datasets/evaluators/code_evaluators.py,sha256=DdCcAi274t_TLs_aARd-GmWWpJrxVeNEAegMFEAfe0E,3894
+phoenix/datasets/evaluators/llm_evaluators.py,sha256=aVfAHOWhskBiy0IVeq_ACTs7B37uXTTtDoNBS0XenIc,9165
+phoenix/datasets/evaluators/utils.py,sha256=S7OGrb1sBWg5l9K35X29OKJe5wZ3k7xMhxJBclzxta0,10452
 phoenix/db/README.md,sha256=IvKaZyf9ECbGBYYePaRhBveKZwDbxAc-c7BMxJYZh6Q,595
 phoenix/db/__init__.py,sha256=pDjEFXukHmJBM-1D8RjmXkvLsz85YWNxMQczt81ec3A,118
 phoenix/db/alembic.ini,sha256=p8DjVqGUs_tTx8oU56JP7qj-rMUebNFizItUSv_hPhs,3763
@@ -23,9 +26,9 @@ phoenix/db/bulk_inserter.py,sha256=zbZGWZFDybKaGLGzpxgLwxAS5sC0_wXcvM0be4kUhh8,1
 phoenix/db/engines.py,sha256=vLWaZlToMtDI7rJDxSidYkfOoojamxaZxaz8ND3zTus,4770
 phoenix/db/helpers.py,sha256=L2_jP1iIWpUREhKLYYb4_vf_6v_BiU1E73Z2PczGm6s,1589
 phoenix/db/migrate.py,sha256=MuhtNWnR24riROvarvKfbRb4_D5xuQi6P760vBUKl1E,2270
-phoenix/db/models.py,sha256=zzZHXh1NpS3LyOOFp1BS7aVyrU1Qx3gcBY-H8ouoyjg,20282
+phoenix/db/models.py,sha256=lYzI3tCDUl8njXb3Vf3R8e6y56-MErprjjfBE-o9Kao,20419
 phoenix/db/insertion/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-phoenix/db/insertion/dataset.py,sha256=2aBOTgjwRkmJqjE1FEQp7BTu1Jz4-bS1bKyeJgvSxfg,7305
+phoenix/db/insertion/dataset.py,sha256=_vxy5e6W5jEuvO2fMKbbNCn9JvHkwI4LRKk_10eKFVg,7171
 phoenix/db/insertion/evaluation.py,sha256=fAerUy3QGf2wID_tiVmPvzxBDFGiONPl3pmpZDgJDWQ,7183
 phoenix/db/insertion/helpers.py,sha256=7tf6qQyJ05nn3IXaZEpj2b4Jz5boGLWT8tzlMaJ9tQY,2337
 phoenix/db/insertion/span.py,sha256=DNBjSrx5g2W5KuTB1dkHwtkb0SFnMIxN1jB-BAdGKFY,5634
@@ -33,7 +36,7 @@ phoenix/db/migrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
 phoenix/db/migrations/env.py,sha256=QbzB5zrRs6XQQmrYeUpuzeilcMlM-MsbaAgHHYcIHTI,3626
 phoenix/db/migrations/script.py.mako,sha256=MEqL-2qATlST9TAOeYgscMn1uy6HUS9NFvDgl93dMj8,635
 phoenix/db/migrations/types.py,sha256=Frq1AKSyBKQQ0FLzON-EmgTqE4kNkOpHMsbWnI-WgCE,605
-phoenix/db/migrations/versions/10460e46d750_datasets.py,sha256=RapdD9Sud_Gq45Vpz7VnDQB_toG6B6yHlwS93qAh_0c,8133
+phoenix/db/migrations/versions/10460e46d750_datasets.py,sha256=l69yZfScFrjfZZpY0gnqwhsDUEctLeo02qMgA_aOGDg,8155
 phoenix/db/migrations/versions/cf03bd6bae1d_init.py,sha256=CbWT3ZTR0CZqeT3zWLoTWhboFmnOy3Ju1z6Ztpq8WIM,8122
 phoenix/inferences/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/inferences/errors.py,sha256=cGp9vxnw4SewFoWBV3ZGMkhE0Kh73lPIv3Ppz_H_RoA,8261
@@ -55,18 +58,18 @@ phoenix/pointcloud/pointcloud.py,sha256=4zAIkKs2xOUbchpj4XDAV-iPMXrfAJ15TG6rlIYG
 phoenix/pointcloud/projectors.py,sha256=zO_RrtDYSv2rqVOfIP2_9Cv11Dc8EmcZR94xhFcBYPU,1057
 phoenix/pointcloud/umap_parameters.py,sha256=lJsEOrbSuSiqI7g4Yt6xj7kgYxEqoep4ZHWLr6VWBqw,1760
 phoenix/server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-phoenix/server/app.py,sha256=_D2DgupKJHv8DmS6VgWxvygumSM75qdlDg6qSj61PRU,18227
+phoenix/server/app.py,sha256=LQrHWt5HG_pWqnR9Ozb3-vnAGiiRGuZ3uV_9-886Yxw,18340
 phoenix/server/grpc_server.py,sha256=faktLxEtWGlCB1bPR4QwwTsRoQloahKMx0hAWqRGI5s,3379
 phoenix/server/main.py,sha256=mtzH_2Kyvuy3AHiiKfqiCdUQ6SGFzeT4q9fefbV6GLg,11114
 phoenix/server/prometheus.py,sha256=j9DHB2fERuq_ZKmwVaqR-9wx5WcPPuU1Cm5Bhg5241Y,2996
 phoenix/server/telemetry.py,sha256=T_2OKrxNViAeaANlNspEekg_Y5uZIFWvKAnpz8Aoqvk,2762
 phoenix/server/thread_server.py,sha256=dP6cm6Cf08jNhDA1TRlVZpziu1YgtPDmaeIJMm725eI,2154
 phoenix/server/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-phoenix/server/api/context.py,sha256=GfAD9QHg5erKwYGpqDj_8bL2GwmccARDZQc8yO-4Fm0,2669
+phoenix/server/api/context.py,sha256=jb69SVdb5hpVbfM4U0pZi4sGa2a-0VKOJWcBjjS7l4s,2761
 phoenix/server/api/interceptor.py,sha256=ykDnoC_apUd-llVli3m1CW18kNSIgjz2qZ6m5JmPDu8,1294
 phoenix/server/api/queries.py,sha256=wp5BlapuxDIoaQJm7mzG0dURfVxR32vXSJVC0JqG4_Y,19845
 phoenix/server/api/schema.py,sha256=BcxdqO5CSGqpKd-AAJHMjFlzaK9oJA8GJuxmMfcdjn4,434
-phoenix/server/api/dataloaders/__init__.py,sha256=9fFjDNlCtOYTOKJi0uPIRh7xJMpCnrBOhoWGEdv1BrI,4618
+phoenix/server/api/dataloaders/__init__.py,sha256=urbG3M-k2cpj2ymMLYQ28tzIXAG1edECxM-tJ22ylqE,4720
 phoenix/server/api/dataloaders/dataset_example_revisions.py,sha256=Vpr5IEKSR4QnAVxE5NM7u92fPNgeHQV2ieYc6JakCj0,3788
 phoenix/server/api/dataloaders/dataset_example_spans.py,sha256=_jLlo0KdUS65d4PNTtE9aXVyG_NZWgA7VcpNC9udQ8U,1484
 phoenix/server/api/dataloaders/document_evaluation_summaries.py,sha256=dgAAlD0n8X6oAPLaD-czoefNkDqP338MouWsKaW8bOY,5684
@@ -75,6 +78,7 @@ phoenix/server/api/dataloaders/document_retrieval_metrics.py,sha256=8tZYMNLZ7zxU
 phoenix/server/api/dataloaders/evaluation_summaries.py,sha256=z9aal3IQL_t30aNqpAS7x4tjq0xNkuEG8dWW-bhqZmo,5724
 phoenix/server/api/dataloaders/experiment_annotation_summaries.py,sha256=RsQ-o84kWVTYgIlh9VKkyw2kDMWIlHCRpS7RE2aw9vs,2881
 phoenix/server/api/dataloaders/experiment_error_rates.py,sha256=EHlTdZi8F94vo-qJUcnnXFvuSh_d0fTT0Xg4SfW_A70,1397
+phoenix/server/api/dataloaders/experiment_run_counts.py,sha256=wxHv08aZELJ91KTjHdt_x33M3wGDDa9GfbFHeRyOyGk,1343
 phoenix/server/api/dataloaders/experiment_sequence_number.py,sha256=Va1KuoHOd-wzvrlKykoV4kLRFW4JsJvGp_DUI4HYZX4,1631
 phoenix/server/api/dataloaders/latency_ms_quantile.py,sha256=pEc7QjB2iiNOQm_Fmo99F5O_DKOJWgGmcnT0OADJzYE,7423
 phoenix/server/api/dataloaders/min_start_or_max_end_times.py,sha256=IoFX5PtSpvQdMk_7-oB8TpIse3Q4PMxep4qKggkHpzo,2902
@@ -89,9 +93,10 @@ phoenix/server/api/dataloaders/trace_row_ids.py,sha256=yAWuVFWUjDdmmwfXsGs_l6LuG
 phoenix/server/api/dataloaders/cache/__init__.py,sha256=SYoOM9n8FJaMdQarma5d1blu-jIg2GB8Shqg5ezSzZ8,106
 phoenix/server/api/dataloaders/cache/two_tier_cache.py,sha256=I38L1RsOis98OQftE7n1Q9QBZfFJO6OW_qIINkuJllo,2295
 phoenix/server/api/helpers/__init__.py,sha256=_V1eVkchZmTkhOfRC4QqR1sUB2xtIxdsMJkDouZq_IE,251
-phoenix/server/api/helpers/dataset_helpers.py,sha256=kIo_kPrV8O40CUypB57JCB5Ek3GJmZXPlz6NIULIsSM,6875
+phoenix/server/api/helpers/dataset_helpers.py,sha256=A6UzEyAb4gFtyc_AV63_yl9OpN0vn8Vw1BBCTNjg9J0,6875
 phoenix/server/api/input_types/AddExamplesToDatasetInput.py,sha256=ZGXMV0H3DYHi4DdqGhejDzaWdFinyem1Mc8DVA7iCh0,436
 phoenix/server/api/input_types/AddSpansToDatasetInput.py,sha256=C4oZ0WqYqca1kleNOCMIM2_aY6Qnc5n1xXG51_C1V0w,368
+phoenix/server/api/input_types/ClearProjectInput.py,sha256=cpPFRyQ3ffy2dLbCZgYpway-mCzhdm4QqnUg8caOBfQ,382
 phoenix/server/api/input_types/ClusterInput.py,sha256=EL4ftvZxQ8mVdruUPcdhMhByORmSmM8S-X6RPqU6GX0,179
 phoenix/server/api/input_types/Coordinates.py,sha256=meTwbIjwTfqx5DGD2DBlH9wQzdQVNM5a8x9dp1FfIgA,173
 phoenix/server/api/input_types/CreateDatasetInput.py,sha256=Q3MwouIx9jTQBRWDju75iMQXEGJCrL4aD4ESQp771nc,248
@@ -116,7 +121,7 @@ phoenix/server/api/mutations/auth.py,sha256=vPRFoj7J6PV6QeODewG4K0PhoOebS5AfMRpb
 phoenix/server/api/mutations/dataset_mutations.py,sha256=Zp2sFWyGyubILUQboR6bafRWafsfeRO2ffUWnkLlfgI,22532
 phoenix/server/api/mutations/experiment_mutations.py,sha256=Fw_yEdITGJ6A33M5JZ-2YnBTDoBqZUUFON6vy8JoVjE,2569
 phoenix/server/api/mutations/export_events_mutations.py,sha256=t_wYBxaqvBJYRoHslh3Bmoxmwlzoy0u8SsBKWIKN5hE,4028
-phoenix/server/api/mutations/project_mutations.py,sha256=6A7BS3651iaeAwUszKXQB3NK4QJY_tGpALBMNw1bqp8,2021
+phoenix/server/api/mutations/project_mutations.py,sha256=3SVDCZqxB0Iv60cOwBL8c-rY3QUUPs8PXbp-C_K1mWY,2267
 phoenix/server/api/openapi/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/server/api/openapi/main.py,sha256=WY0pj3B7siQyyYqKyhqnzWC7P8MtEtiukOBUjGwLXfw,153
 phoenix/server/api/openapi/schema.py,sha256=uuSYe1Ecu72aXRgTNjyMu-9ZPE13DAHJPKtedS-MsSs,451
@@ -124,10 +129,10 @@ phoenix/server/api/routers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJ
 phoenix/server/api/routers/utils.py,sha256=M41BoH-fl37izhRuN2aX7lWm7jOC20A_3uClv9TVUUY,583
 phoenix/server/api/routers/v1/__init__.py,sha256=B5eSaylPI7MoYia1-VgKrU8rDi-69r_hRwPU5yMLUTE,2808
 phoenix/server/api/routers/v1/dataset_examples.py,sha256=wtplRUv2ee9xGTrcEMgTn-7L4NX_73IcwUXkCMZEFc4,6726
-phoenix/server/api/routers/v1/datasets.py,sha256=2wkBOLqo8ttSN1VNVEcnPcLCitkSLGp62AjWlxJhV4Y,27605
+phoenix/server/api/routers/v1/datasets.py,sha256=ws2Guou9mspwFx3-cBFZoD2VuTwWGoFZmtt2Sr3zg6k,31516
 phoenix/server/api/routers/v1/evaluations.py,sha256=rwSVg-rpujhsMcDVFt-VAr0Ix9TgvLcY_bSxeh8PzJI,9241
-phoenix/server/api/routers/v1/experiment_evaluations.py,sha256=xemnZ10WL5pErndP7jbaDipUj3Tkl813XSIjx7X5MBY,2656
-phoenix/server/api/routers/v1/experiment_runs.py,sha256=o6IvcyFDY-cy3KqeO9FIKy3XAgbIJhx7SFUoxML-MeY,4337
+phoenix/server/api/routers/v1/experiment_evaluations.py,sha256=xhrkPUc_4ncIBm24aUyzu47UU0CN1tGlbisn-oLqt_Y,2702
+phoenix/server/api/routers/v1/experiment_runs.py,sha256=0AUNHA5nvpGDeoJUGK8VxP2TFN3iPwhMW3D9QmHstPk,4399
 phoenix/server/api/routers/v1/experiments.py,sha256=5Rh7q6sHswmk11PZSJ7KMrtqfIE16X_xSKkKSASK9-I,7251
 phoenix/server/api/routers/v1/spans.py,sha256=FEnmlRPBPl71BSGNBuPrz14fk8nmxJQYsKECdDbdUdw,3977
 phoenix/server/api/routers/v1/traces.py,sha256=dYEf5pThenAQCgfQljHdrnwd4tC_tAXm6Kvk6GphPYs,2774
@@ -154,11 +159,11 @@ phoenix/server/api/types/EvaluationSummary.py,sha256=EFucuzAhcxR9sdEn6WNAtmAGJk-
 phoenix/server/api/types/Event.py,sha256=XdYgaIxcVIW-YFViCkxj5l9OaVNepyIrCtm5Iqg2le8,3989
 phoenix/server/api/types/EventMetadata.py,sha256=-J0tYF9eZTHwCjwxQHY7Gckr2_MNW5OoWT1mydweZNM,635
 phoenix/server/api/types/ExampleRevisionInterface.py,sha256=gV3Gt9-3Oi5wjaVtepC6nOt3FzTzZFD1KebNnqiw56E,294
-phoenix/server/api/types/Experiment.py,sha256=Lon2ZNZYdWXQmj3nLr_TXN8CCtZtC-AXYfyJuoqI2DM,4692
+phoenix/server/api/types/Experiment.py,sha256=Cs0EKhVLI5l5LKFI0hQA-ekZuaiJcOHT88JGFBa2deU,4906
 phoenix/server/api/types/ExperimentAnnotationSummary.py,sha256=Uk3JtxIrsMoZT5tqc4nJdUOM3XegVzjUyoV3pkjNotE,256
 phoenix/server/api/types/ExperimentComparison.py,sha256=0sFz6MoBDw39dds0qVyaqhVs9qqO5rkG1FMSjmfBeCc,441
-phoenix/server/api/types/ExperimentRun.py,sha256=uM7HxaC8nEjtO7yLr8WjLEfYRvEvbX6ibR8I0fVzdeU,2976
-phoenix/server/api/types/ExperimentRunAnnotation.py,sha256=GvWY6wukBhSr2Tk9Ef0R5bH5yCMxVakqeypoyYoUb6o,1774
+phoenix/server/api/types/ExperimentRun.py,sha256=8jUIi3ApVCqQHwnYe59CYhrmh5iZ6-QmlH5WpF7UWtM,2990
+phoenix/server/api/types/ExperimentRunAnnotation.py,sha256=zGstMbS5OxNikEhD8VouY7Ls7YbxKm-0EmqvGeY3-DI,1773
 phoenix/server/api/types/ExportedFile.py,sha256=e3GTn7B5LgsTbqiwjhMCQH7VsiqXitrBO4aCMS1lHsg,163
 phoenix/server/api/types/Functionality.py,sha256=tzV9xdhB8zqfsjWxP66NDC7EZsplYkYO7jRbLWJIeeg,382
 phoenix/server/api/types/Inferences.py,sha256=HWuDZZrXPWVoEy_pA3bRsAOUYsCKgAxf9zshasGqu5Y,3403
@@ -173,7 +178,7 @@ phoenix/server/api/types/Retrieval.py,sha256=OhMK2ncjoyp5h1yjKhjlKpoTbQrMHuxmgSF
 phoenix/server/api/types/ScalarDriftMetricEnum.py,sha256=IUAcRPpgL41WdoIgK6cNk2Te38SspXGyEs-S1fY23_A,232
 phoenix/server/api/types/Segments.py,sha256=m2yoegrxA1Tn7ZAy1rMjjD1isc752MaAXMoffkBlvrM,2921
 phoenix/server/api/types/SortDir.py,sha256=OUpXhlCzCxPoXSDkJJygEs9Rw9pMymfaZUG5zPTrw4Y,152
-phoenix/server/api/types/Span.py,sha256=Nk0Of6JyHSI7OqrEodyV3d5UUvzCWnDkNSZUcmCvq-I,13837
+phoenix/server/api/types/Span.py,sha256=W4Rsg85bgqbDhgYwpjgOTrIQKbkwpFQPpL6nqMyzhCs,13865
 phoenix/server/api/types/TimeSeries.py,sha256=wjzuxHFqCey0O7Ys25qiXyuqXK8an-osyNWUE8A_8G4,5227
 phoenix/server/api/types/Trace.py,sha256=ep-mPexub1ijxAnBvc2KrGsNVXO2SfDR1WxqER2wcD8,2376
 phoenix/server/api/types/UMAPPoints.py,sha256=5sOuruzM8saXa8C2XiyUfk2XPrkVGmhqKpclMYRw1dk,1656
@@ -194,12 +199,12 @@ phoenix/server/static/apple-touch-icon-76x76.png,sha256=CT_xT12I0u2i0WU8JzBZBuOQ
 phoenix/server/static/apple-touch-icon.png,sha256=fOfpjqGpWYbJ0eAurKsyoZP1EAs6ZVooBJ_SGk2ZkDs,3801
 phoenix/server/static/favicon.ico,sha256=bY0vvCKRftemZfPShwZtE93DiiQdaYaozkPGwNFr6H8,34494
 phoenix/server/static/index.css,sha256=KKGpx4iwF91VGRm0YN-4cn8oC-oIqC6HecoPf0x3ZM8,1885
-phoenix/server/static/index.js,sha256=88OQ_pBKrFdD5usFU6Frpm1vBzxL19zO4JS9ChoHWEo,3487681
+phoenix/server/static/index.js,sha256=I9Y8svcPruUrXklKcZUxFz5HfLB0vOwczYLSwLAs_04,3500011
 phoenix/server/static/modernizr.js,sha256=mvK-XtkNqjOral-QvzoqsyOMECXIMu5BQwSVN_wcU9c,2564
 phoenix/server/templates/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/server/templates/index.html,sha256=S4z7qSoNSwnKFAH9r96AR-YJEyoKMd-VMWVlJ_IdzME,2039
 phoenix/session/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-phoenix/session/client.py,sha256=tq2qghwYa_mxNYLD41UNfD7n57msB9lYIe5H16lBqoo,20333
+phoenix/session/client.py,sha256=R7dV38yjkIQa522nhG6jhDllWcXft2JJ7RlcPYpqiiQ,24846
 phoenix/session/data_extractor.py,sha256=dwhiDu-ISaXr8UI9I-CszZhB5BlUNmdDopjFZvMIXMw,2101
 phoenix/session/evaluation.py,sha256=aKeV8UVOyq3b7CYOwt3cWuLz0xzvMjX7vlEPILJ_fcs,5311
 phoenix/session/session.py,sha256=rjIuSSK2gAYIUPQTJc4E2ebew5o6I070FWRoFn4W3EI,26620
@@ -211,7 +216,7 @@ phoenix/trace/exporter.py,sha256=eAYemdvDCHMugDJiaR29BFFMTQBdf3oerdkz34Cl3hE,473
 phoenix/trace/fixtures.py,sha256=gBGFG2gkcBsSDzolzzR9AJDrB_fdOQfUaGgHV-EHdco,14204
 phoenix/trace/otel.py,sha256=WA720jvRadiZBAKjsYoPyXzypHwbyEK2OZRVUwtbjB8,9976
 phoenix/trace/projects.py,sha256=2BwlNjFE-uwpqYtCu5YyBiYZk9wRPpM13vh3-Cv7GkA,2157
-phoenix/trace/schemas.py,sha256=JiFKhGD2JF6Eai7UOhPF5urcuKGkpMLHc3Vltbe1msk,5967
+phoenix/trace/schemas.py,sha256=Mjc6fD9OyeMnEk5wPPSbveqnNUYWK3p3BxpOvSGanHU,5950
 phoenix/trace/span_evaluations.py,sha256=GaADtJLi2njra4aYaie0BIwkSgdxPB_SNseglI4ykZA,13104
 phoenix/trace/span_json_decoder.py,sha256=IAFakPRqSMYxTPKYFMiXYxm7U-FipdN8_xbvapDS0Qc,3131
 phoenix/trace/span_json_encoder.py,sha256=tzSCIQJbeFBm33K68G8A5M12n_86tCDyuU0WAobxEz4,2010
@@ -239,8 +244,8 @@ phoenix/utilities/logging.py,sha256=lDXd6EGaamBNcQxL4vP1au9-i_SXe0OraUDiJOcszSw,
 phoenix/utilities/project.py,sha256=qWsvKnG1oKhOFUowXf9qiOL2ia7jaFe_ijFFHEt8GJo,431
 phoenix/utilities/re.py,sha256=PDve_OLjRTM8yQQJHC8-n3HdIONi7aNils3ZKRZ5uBM,2045
 phoenix/utilities/span_store.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize_phoenix-4.4.4rc3.dist-info/METADATA,sha256=VuX8kXsqxcbsdYmi9-jCDMHgMJ182JMbDYCY-3N74jU,11012
-arize_phoenix-4.4.4rc3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-arize_phoenix-4.4.4rc3.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
-arize_phoenix-4.4.4rc3.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
-arize_phoenix-4.4.4rc3.dist-info/RECORD,,
+arize_phoenix-4.4.4rc5.dist-info/METADATA,sha256=yT0gbMlPkiRkZeC8Yj_eLyaufriREVn3jxz5-qTKDjI,11012
+arize_phoenix-4.4.4rc5.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+arize_phoenix-4.4.4rc5.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
+arize_phoenix-4.4.4rc5.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
+arize_phoenix-4.4.4rc5.dist-info/RECORD,,

phoenix/datasets/evaluators/__init__.py

@@ -0,0 +1,18 @@
+from phoenix.datasets.evaluators.code_evaluators import ContainsKeyword, JSONParsable
+from phoenix.datasets.evaluators.llm_evaluators import (
+    CoherenceEvaluator,
+    ConcisenessEvaluator,
+    HelpfulnessEvaluator,
+    LLMCriteriaEvaluator,
+    RelevanceEvaluator,
+)
+
+__all__ = [
+    "ContainsKeyword",
+    "JSONParsable",
+    "CoherenceEvaluator",
+    "ConcisenessEvaluator",
+    "LLMCriteriaEvaluator",
+    "HelpfulnessEvaluator",
+    "RelevanceEvaluator",
+]

phoenix/datasets/evaluators/code_evaluators.py

@@ -0,0 +1,99 @@
+from __future__ import annotations
+
+import json
+import re
+from typing import Any, List, Optional, Union
+
+from phoenix.datasets.evaluators.utils import Evaluator
+from phoenix.datasets.types import EvaluationResult, TaskOutput
+
+
+class JSONParsable(Evaluator):
+    def evaluate(self, *, output: Optional[TaskOutput] = None, **_: Any) -> EvaluationResult:
+        assert isinstance(output, str), "Experiment run output must be a string"
+        try:
+            json.loads(output)
+            json_parsable = True
+        except BaseException:
+            json_parsable = False
+        return EvaluationResult(
+            score=int(json_parsable),
+        )
+
+
+class ContainsKeyword(Evaluator):
+    def __init__(self, keyword: str, name: Optional[str] = None) -> None:
+        self.keyword = keyword
+        self._name = name or f"Contains({repr(keyword)})"
+
+    def evaluate(self, *, output: Optional[TaskOutput] = None, **_: Any) -> EvaluationResult:
+        assert isinstance(output, str), "Experiment run output must be a string"
+        found = self.keyword in output
+        return EvaluationResult(
+            score=float(found),
+            explanation=(
+                f"the string {repr(self.keyword)} was "
+                f"{'found' if found else 'not found'} in the output"
+            ),
+        )
+
+
+class ContainsAnyKeyword(Evaluator):
+    def __init__(self, keywords: List[str], name: Optional[str] = None) -> None:
+        self.keywords = keywords
+        self._name = name or f"ContainsAny({keywords})"
+
+    def evaluate(self, *, output: Optional[TaskOutput] = None, **_: Any) -> EvaluationResult:
+        assert isinstance(output, str), "Experiment run output must be a string"
+        found = [keyword for keyword in self.keywords if keyword in output]
+        if found:
+            explanation = f"the keywords {found} were found in the output"
+        else:
+            explanation = f"none of the keywords {self.keywords} were found in the output"
+        return EvaluationResult(
+            score=float(bool(found)),
+            explanation=explanation,
+        )
+
+
+class ContainsAllKeywords(Evaluator):
+    def __init__(self, keywords: List[str], name: Optional[str] = None) -> None:
+        self.keywords = keywords
+        self._name = name or f"ContainsAll({keywords})"
+
+    def evaluate(self, *, output: Optional[TaskOutput] = None, **_: Any) -> EvaluationResult:
+        assert isinstance(output, str), "Experiment run output must be a string"
+        not_found = [keyword for keyword in self.keywords if keyword not in output]
+        if not_found:
+            contains_all = False
+            explanation = f"the keywords {not_found} were not found in the output"
+        else:
+            contains_all = True
+            explanation = f"all of the keywords {self.keywords} were found in the output"
+        return EvaluationResult(
+            score=float(contains_all),
+            explanation=explanation,
+        )
+
+
+class MatchesRegex(Evaluator):
+    def __init__(self, pattern: Union[str, re.Pattern[str]], name: Optional[str] = None) -> None:
+        if isinstance(pattern, str):
+            pattern = re.compile(pattern)
+        self.pattern = pattern
+        assert isinstance(pattern, re.Pattern)
+        self._name = name or f"matches_({pattern})"
+
+    def evaluate(self, *, output: Optional[TaskOutput] = None, **_: Any) -> EvaluationResult:
+        assert isinstance(output, str), "Experiment run output must be a string"
+        matches = self.pattern.findall(output)
+        if matches:
+            explanation = (
+                f"the substrings {matches} matched the regex pattern {self.pattern.pattern}"
+            )
+        else:
+            explanation = f"no substrings matched the regex pattern {self.pattern.pattern}"
+        return EvaluationResult(
+            score=float(bool(matches)),
+            explanation=explanation,
+        )

phoenix/datasets/{evaluators.py → evaluators/llm_evaluators.py}

@@ -1,72 +1,23 @@
-import json
 import re
-from typing import TYPE_CHECKING, Callable, Optional, Type
+from types import MappingProxyType
+from typing import Any, Callable, Optional, Type
 
+from phoenix.datasets.evaluators.utils import (
+    ExampleInput,
+    ExampleMetadata,
+    ExperimentEvaluator,
+    LLMEvaluator,
+    _unwrap_json,
+)
 from phoenix.datasets.types import (
     EvaluationResult,
-    Example,
-    ExperimentEvaluator,
-    ExperimentRun,
-    JSONSerializable,
+    TaskOutput,
 )
 from phoenix.evals.models.base import BaseModel as LLMBaseModel
 from phoenix.evals.utils import snap_to_rail
 
 
-def _unwrap_json(obj: JSONSerializable) -> JSONSerializable:
-    if isinstance(obj, dict):
-        if len(obj) == 1:
-            key = next(iter(obj.keys()))
-            output = obj[key]
-            assert isinstance(
-                output, (dict, list, str, int, float, bool, type(None))
-            ), "Output must be JSON serializable"
-            return output
-    return obj
-
-
-class JSONParsable:
-    annotator_kind = "CODE"
-    name = "JSONParsable"
-
-    def evaluate(self, example: Example, exp_run: ExperimentRun) -> EvaluationResult:
-        assert exp_run.output is not None
-        output = _unwrap_json(exp_run.output.result)
-        assert isinstance(output, str), "Experiment run output must be a string"
-        try:
-            json.loads(output)
-            json_parsable = True
-        except BaseException:
-            json_parsable = False
-        return EvaluationResult(
-            score=int(json_parsable),
-        )
-
-
-class ContainsKeyword:
-    annotator_kind = "CODE"
-
-    def __init__(self, keyword: str) -> None:
-        super().__init__()
-        self.keyword = keyword
-        self.name = f"ContainsKeyword({keyword})"
-
-    def evaluate(self, example: Example, exp_run: ExperimentRun) -> EvaluationResult:
-        assert exp_run.output is not None
-        result = _unwrap_json(exp_run.output.result)
-        assert isinstance(result, str), "Experiment run output must be a string"
-        found = self.keyword in result
-        return EvaluationResult(
-            score=float(found),
-            explanation=(
-                f"the string {repr(self.keyword)} was "
-                f"{'found' if found else 'not found'} in the output"
-            ),
-        )
-
-
-class LLMCriteriaEvaluator:
-    annotator_kind = "LLM"
+class LLMCriteriaEvaluator(LLMEvaluator):
     _base_template = (
         "Determine if the following text is {criteria}. {description}"
         "First, explain step-by-step why you think the text is or is not {criteria}. Then provide "
@@ -77,7 +28,7 @@ class LLMCriteriaEvaluator:
         "EXPLANATION: *a step by step explanation of your reasoning for whether the text meets "
         "the criteria*\n"
         "LABEL: *true or false*\n\n"
-        "Follow this template for the following text:\n\n"
+        "Follow this template for the following example:\n\n"
         "CRITERIA: the text is '{criteria}'\n"
         "TEXT: {text}\n"
         "EXPLANATION: "
@@ -95,21 +46,23 @@ class LLMCriteriaEvaluator:
         self.criteria = criteria
         self.description = description
         self.template = self._format_base_template(self.criteria, self.description)
-        self.name = name
+        self._name = name
 
-    def evaluate(self, example: Example, exp_run: ExperimentRun) -> EvaluationResult:
-        formatted_template = self._format_eval_template(exp_run)
+    def evaluate(self, *, output: Optional[TaskOutput] = None, **_: Any) -> EvaluationResult:
+        formatted_template = self._format_eval_template(output)
         unparsed_response = self.model._generate(formatted_template)
         return self._parse_eval_output(unparsed_response)
 
-    async def async_evaluate(self, example: Example, exp_run: ExperimentRun) -> EvaluationResult:
-        formatted_template = self._format_eval_template(exp_run)
+    async def async_evaluate(
+        self, *, output: Optional[TaskOutput] = None, **_: Any
+    ) -> EvaluationResult:
+        formatted_template = self._format_eval_template(output)
         unparsed_response = await self.model._async_generate(formatted_template)
         return self._parse_eval_output(unparsed_response)
 
-    def _format_eval_template(self, experiment_run: ExperimentRun) -> str:
-        assert experiment_run.output is not None
-        result = _unwrap_json(experiment_run.output.result)
+    def _format_eval_template(self, output: TaskOutput) -> str:
+        assert output is not None
+        result = _unwrap_json(output)
         return self.template.format(text=str(result))
 
     def _parse_eval_output(self, unparsed_response: str) -> EvaluationResult:
@@ -142,40 +95,43 @@ class LLMCriteriaEvaluator:
 
 
 def criteria_evaluator_factory(
-    class_name: str, criteria: str, description: str
+    class_name: str, criteria: str, description: str, default_name: str
 ) -> Type[ExperimentEvaluator]:
+    def _init(self, model: LLMBaseModel, name: str = default_name) -> None:  # type: ignore
+        LLMCriteriaEvaluator.__init__(self, model, criteria, description, name=name)
+
     return type(
         class_name,
         (LLMCriteriaEvaluator,),
         {
-            "__init__": lambda self, model: LLMCriteriaEvaluator.__init__(
-                self, model, criteria, description, name=class_name
-            ),
+            "__init__": _init,
             "__module__": __name__,
-            "name": class_name,
             "template": LLMCriteriaEvaluator._format_base_template(criteria, description),
         },
     )
 
 
-LLMConcisenessEvaluator = criteria_evaluator_factory(
-    class_name="LLMConcisenessEvaluator",
+ConcisenessEvaluator = criteria_evaluator_factory(
+    class_name="ConcisenessEvaluator",
     criteria="concise",
     description="is just a few sentences and easy to follow",
+    default_name="Conciseness",
 )
 
 
-LLMHelpfulnessEvaluator = criteria_evaluator_factory(
-    class_name="LLMHelpfulnessEvaluator",
+HelpfulnessEvaluator = criteria_evaluator_factory(
+    class_name="HelpfulnessEvaluator",
     criteria="helpful",
     description="provides useful information",
+    default_name="Helpfulness",
 )
 
 
-LLMCoherenceEvaluator = criteria_evaluator_factory(
-    class_name="LLMCoherenceEvaluator",
+CoherenceEvaluator = criteria_evaluator_factory(
+    class_name="CoherenceEvaluator",
     criteria="coherent",
-    description="is coherent, well-structured, and organized",
+    description="is coherent, well-structured, and logically sound",
+    default_name="Coherence",
 )
 
 
@@ -192,8 +148,7 @@ def _parse_label_from_explanation(raw_string: str) -> str:
     return raw_string
 
 
-class RelevanceEvaluator:
-    annotator_kind = "LLM"
+class RelevanceEvaluator(LLMEvaluator):
     template = (
         "Determine if the following response is relevant to the query. In this context, "
         "'relevance' means that the response directly addresses the core question or topic of the "
@@ -217,19 +172,24 @@ class RelevanceEvaluator:
     def __init__(
         self,
         model: LLMBaseModel,
-        get_query: Optional[Callable[[Example, ExperimentRun], str]] = None,
-        get_response: Optional[Callable[[Example, ExperimentRun], str]] = None,
+        get_query: Optional[Callable[[ExampleInput, ExampleMetadata], str]] = None,
+        get_response: Optional[Callable[[Optional[TaskOutput], ExampleMetadata], str]] = None,
         name: str = "RelevanceEvaluator",
     ):
         self.model = model
-        self.name = name
+        self._name = name
         self.get_query = get_query or self._default_get_query
         self.get_response = get_response or self._default_get_response
 
-    def _format_eval_template(self, example: Example, experiment_run: ExperimentRun) -> str:
-        assert experiment_run.output is not None
-        query = self.get_query(example, experiment_run)
-        response = self.get_response(example, experiment_run)
+    def _format_eval_template(
+        self,
+        output: Optional[TaskOutput] = None,
+        input: ExampleInput = MappingProxyType({}),
+        metadata: ExampleMetadata = MappingProxyType({}),
+    ) -> str:
+        assert output is not None
+        query = self.get_query(input, metadata)
+        response = self.get_response(output, metadata)
         return self.template.format(query=query, response=response)
 
     def _parse_eval_output(self, unparsed_response: str) -> EvaluationResult:
@@ -250,26 +210,35 @@ class RelevanceEvaluator:
             metadata={},
         )
 
-    def _default_get_query(self, example: Example, experiment_run: ExperimentRun) -> str:
-        return str(example.input)
+    def _default_get_query(self, input: ExampleInput, *args: Any, **kwargs: Any) -> str:
+        return str(input)
 
-    def _default_get_response(self, example: Example, experiment_run: ExperimentRun) -> str:
-        assert experiment_run.output is not None
-        return str(_unwrap_json(experiment_run.output.result))
+    def _default_get_response(
+        self, output: Optional[TaskOutput] = None, *args: Any, **kwargs: Any
+    ) -> str:
+        assert output is not None
+        return str(_unwrap_json(output))
 
-    def evaluate(self, example: Example, exp_run: ExperimentRun) -> EvaluationResult:
-        formatted_template = self._format_eval_template(example, exp_run)
+    def evaluate(
+        self,
+        *,
+        output: Optional[TaskOutput] = None,
+        metadata: ExampleMetadata = MappingProxyType({}),
+        input: ExampleInput = MappingProxyType({}),
+        **_: Any,
+    ) -> EvaluationResult:
+        formatted_template = self._format_eval_template(output, input, metadata)
         unparsed_response = self.model._generate(formatted_template)
         return self._parse_eval_output(unparsed_response)
 
-    async def async_evaluate(self, example: Example, exp_run: ExperimentRun) -> EvaluationResult:
-        formatted_template = self._format_eval_template(example, exp_run)
+    async def async_evaluate(
+        self,
+        *,
+        output: Optional[TaskOutput] = None,
+        metadata: ExampleMetadata = MappingProxyType({}),
+        input: ExampleInput = MappingProxyType({}),
+        **_: Any,
+    ) -> EvaluationResult:
+        formatted_template = self._format_eval_template(output, input, metadata)
         unparsed_response = await self.model._async_generate(formatted_template)
         return self._parse_eval_output(unparsed_response)
-
-
-# Someday we'll do typing checking in unit tests.
-if TYPE_CHECKING:
-    _: ExperimentEvaluator
-    _ = JSONParsable()
-    _ = ContainsKeyword("test")