7.29.1 (2024-11-27)
7.29.0 (2024-11-26)
7.28.0 (2024-11-25)
7.27.2 (2024-11-22)
7.27.1 (2024-11-22)
7.27.0 (2024-11-22)
- new
log_evaluations_syncmethod to public Flight server (#37834) (86a21ab) - return number of records updated to Flight clients (#38428) (b92ee44)
- Dynamic client key verification on method call (86a21ab)
7.26.0 (2024-11-18)
- datasets: default experiment traces for the same dataset are sent to Arize in 1 traces model/project (#38010) (c3face4)
7.25.7 (2024-11-12)
7.25.6 (2024-11-12)
7.25.5 (2024-11-05)
7.25.4 (2024-11-02)
7.25.3 (2024-11-02)
7.25.2 (2024-11-01)
- Add switcher to conf.py in api docs (4f1ae8c)
- Improve docstring format for API docs (#37475) (4f1ae8c)
7.25.1 (2024-11-01)
7.25.0 (2024-11-01)
7.24.3 (2024-11-01)
7.24.2 (2024-11-01)
- Exclude api_reference directory from build (#37457) (3e595c3)
- Move api docs to docs/ directory (#37460) (d7d0c21)
7.24.1 (2024-11-01)
7.24.0 (2024-10-30)
- datasets: support using dataset_name in addition to dataset_id to update/delete/get_versions on a dataset (#37298) (345a18b)
- experiment: support callable functions as experiment evaluators (#37085) (bee9278), closes #35779
- experiment: update parameter mapping in task and evaluate functions (bee9278)
7.23.0 (2024-10-24)
- Adds project_name support to the Tracing SDK, alongside, to replace model_id, which will be deprecated for Tracing (#36962) (be3c129)
- experiments: add exit_on_error flag to run_experiment API (#36595) (fc860cd)
- experiments: improve task summary formatting (fc860cd)
- experiments: replace print with python logging (fc860cd)
7.22.6 (2024-10-09)
7.22.5 (2024-10-08)
- Improve export of arize tracing data to improve ergonomics of working with data after export (#33762) (121678d)
7.22.4 (2024-10-02)
7.22.3 (2024-10-02)
7.22.2 (2024-10-02)
7.22.1 (2024-10-02)
7.22.0 (2024-09-26)
- experiments: configurable concurrency value for task and evaluator runs (7bfe7ab)
- experiments: configurable otlp endpoint for default experiments traces (7bfe7ab)
- experiments: datasets client experiment dry-run mode (#35678) (7bfe7ab)
7.21.0 (2024-09-13)
- async run task and evaluator functions (23f5a21)
- get experiment data back as a dataframe. (23f5a21)
- run experiment with default traces (#34566) (23f5a21)
7.20.1 (2024-08-19)
7.20.0 (2024-08-16)
- Enable delayed tags for stream logging (#34140) (5593127)
- Experiment eval metadata (#34123) (127a9c4)
- ingest data to arize using space_id (#33982) (4f349d4)
7.19.0 (2024-08-07)
- Add client to provide public APIs to perform CRUD operations on datasets (#32096) (512070b)
- Allow dataset client to create experiments on datasets (512070b)
7.18.1 (2024-05-22)
- Correctly insert default prediction id column using
df.insert()(f938d29) - Improve error message for type errors for raw data character count (#31272) (f938d29)
- Include SHAP value invalid rows if full of nulls in error message (#31264) (24f079f)
- Remove f-strings from docstrings and place them above arguments (#31117) (5c812d6)
- Update similarity timestamp validation (#31125) (1c32c37)
7.18.0 (2024-05-15)
7.17.1 (2024-05-10)
- Serialization of nested dictionaries (#30931) (ece89dc)
- Avoid side effects in dictionary fields (ece89dc)
- Value validation should require dictionaries, not JSON (ece89dc)
7.17.0 (2024-05-07)
- Add session and user ids to spans batch logging (#30588) (90a0416)
- Send arize schema as part of the request body (#30841) (b2f8e67)
- improve evaluation column naming error message (267d23d)
- relax opentelemetry-semantic-conventions dependency (#30840) (267d23d)
- update URL to model page in logger (#30591) (5f0ee5a)
7.16.1 (2024-04-29)
7.16.0 (2024-04-24)
- Add
log_evaluationsmethod for delayed evaluation logging (#30179) (0f52763) - Fileimporter evaluations updates records (#30301) (7e1cbf6)
7.15.0 (2024-04-17)
7.14.1 (2024-04-03)
7.14.0 (2024-03-29)
- Support export of spans from Arize platform (#29350) (e248248)
- Increase span field validation string length limits (#29501)(c32f464)
7.13.0 (2024-03-28)
7.12.1 (2024-03-26)
7.12.0 (2024-03-23)
- evals: Add evals log spans sdk
- Add certificate file reading to sdk client
- Avoid side-effects and correct null validation
- tracing: Improve log spans from phoenix
- tracing: correct missing value check for explanations
- tracing: Import tracing modules dynamically
- Avoid tracing tests for old python
- Add tracing dependencies to release workflow
7.11.1 (2024-03-05)
- Fix
ImportErrorwhen importing Client from arize.api
7.11.0 (2024-02-23)
- Add optional extra dependencies if the Arize package is installed as
pip install arize[NLP_Metrics]:nltk>=3.0.0, <4sacrebleu>=2.3.1, <3rouge-score>=0.1.2, <1evaluate>=0.3, <1
- Add optional strict typing in pandas logger Schema
- Add 0ptional strict typing in record-at-a-time logger
7.10.2 (2024-02-14)
- Address backward compatibility issue for batch logging via Pandas for on-prem customers
- Validate that space and API keys are of string type
7.10.1 (2024-02-6)
- Add
deprecatedto ourTracingextra requirements. Thedeprecateddependency comes fromopentelemetry-semantic-conventions, which absence produced anImportError
7.10.0 (2024-02-1)
- Relax
MimicExplainerextra requirements: require onlyinterpret-community[mimic]>=0.22.0,<1
- Add batch ingestion via Pandas DataFrames for
MULTICLASSmodel type - New
TRACINGenvironment. You can now log spans & traces for your LLM applications into Arize using batch ingestion via Pandas DataFrames - Removed size limitation on the
Schema. You can now log wider models (more columns in your DataFrame) - Prediction ID and Ranking Group ID have an increased character limit from 128 to 512
7.9.0 (2023-12-28)
- New
MULTICLASSmodel type available for record-at-a-time ingestion
7.8.1 (2023-12-18)
- Fix missing columns validation feedback to have repeated columns in the message
- Fix
KeyErrorwhen llm_params is not found in the dataframe. Improved feedback to the user was included.
7.8.0 (2023-12-13)
- Updated
pandasrequirement. We now accept pandas2.x
- Enable latent actuals for
GENERATIVE_LLMmodels - Enable feedback when files are too large for better user experience and troubleshooting
7.7.2 (2023-11-09)
- Default prediction sent as string for
GENERATIVE_LLMsingle-record-logger (before it was incorrectly set as an integer, resulting in it being categorized as prediction score instead of prediction label)
7.7.1 (2023-11-08)
- Only check the value of
prompt/responseif notNone
7.7.0 (2023-11-02)
- Add
CORPUSsupport - Accept strings for prompt and response
- Make prompt and response optional
- Add support for a list of strings features in single-record-logger
- Avoid creating a view of a Pandas dataframe
7.6.1 (2023-10-24)
- Add validation on embedding raw data for batch and record-at-a-time loggers
- Raise validation string limits for string fields
- Add truncation warnings for long string fields
7.6.0 (2023-10-12)
- Add ability to send features with type list[str]
- Add new fields available to send token usage to Arize, both using our pandas batch logger and the single record logger
7.5.1 (2023-10-05)
- Require
python>=3.6(as opposed topython>=3.8) for our core SDK. Our extras still requirepython>=3.8. - Require
pyarrow>=0.15.0(as opposed topyarrow>=5.0.0)
- Increase time interval validation from 2 years to 5 years
7.5.0 (2023-09-02)
- Add prompt templates and LLM config fields to the single log and pandas batch ingestion. These fields are used in the Arize Prompt Template Playground
- Add a validation check that fails if there are more than 30 embedding features sent
7.4.0 (2023-08-15)
- Add filtering via the keyword where to the Exporter client
7.3.0 (2023-08-01)
AutoEmbeddingssupport for any model in the HuggingFace Hub, public or private.- Add
AutoEmbeddingsUseCase for Object Detection - Add
EmbeddingGenerator.list_default_models()method
- Computer Vision
AutoEmbeddingsswitched from usingFeatureExtractor(deprecated from HuggingFace) toImageProcessorclass
7.2.0 (2023-07-22)
- Authenticating Arize Client using environment variables
- Fix permission errors for pandas logging on Windows machines
- Fix enforcement of tags into being strings
7.1.0 (2023-06-26)
- Add
Generative_LLMmodel-type support for single-record logging
7.0.6 (2023-06-24)
- Removed dependency on interpret for the MimicExplainer
7.0.5 (2023-06-23)
- Add missing dependency for Exporter: tqdm>=4.60.0,<5
- Update reserved headers
- exporter: Fix progress bar in the Exporter client
- exporter: Sort exported dataframe by time
- exporter: Add validation check to Exporter client that will fail if start_time > end_time
- exporter: Return empty response when an export query returns no data instead of an error.
- exporter: Fix the Exporter client returning empty columns in the dataframe if there was no data in them
- Fix incorrect parsing of
GENERATIVE_LLMmodel prompt & response fields
7.0.4 (2023-06-13)
- Relax protobuf requirements from
protobuf~=3.12toprotobuf>=3.12, <5
7.0.3 (2023-06-02)
- Add new
ExportClient, you can now export data from Arize using the Python SDK
- Allow
REGRESSIONmodels to use theMimicExplainer - Remove null value validation for
prediction_labelandactual_labelfrom single-record logging - Add model mapping rules validation for
OBJECT_DETECTIONmodels
7.0.2 (2023-05-12)
- Change optional dependency for
MimicExplainer, raise the version ceiling oflightgbmfrom3.3.4to4
- Improve error messages around prediction ID, prediction labels, and tags
- Fix predictions sent as scores instead of labels for
NUMERICmodel types - Add a validation check that will fail if the character limit on tags (1000 max) is exceeded
- Add a validation check that will fail if actuals are sent without prediction ID information (for single-record logging). This would result in a delayed record being sent without a prediction ID, which is necessary for the latent join
- Add a validation check that will fail if the Schema, without prediction columns, does not contain a prediction ID column (for pandas logging). This would result in a delayed record being sent without a prediction ID, which is necessary for the latent join
- Add a validation check that will fail if the Schema points to an empty string as a column name
- Add check for invalid index in AutoEmbeddings: DataFrames must have a sorted, continuous index starting at 0
- Remove label requirements & accept null values on SCORE_CATEGORICAL, NUMERIC, and RANKING models
- Allow feature and tag columns to contain null values for pandas logging
- Allow to send delayed actuals for RANKING models, it is no longer enforced the presence of rank and prediction_group_id columns in the Schema. However, if the columns are sent, they must not have nulls, since we cannot construct predictions with either value null
7.0.1 (2023-04-25)
- Fix
GENERATIVE_LLMmodels being sent asSCORE_CATEGORICALmodels
7.0.0 (2023-04-13)
- Require
Python >= 3.8for all extra functionality - Remove
numeric_sequencesupport
-
Add optional extra dependencies if the Arize package is installed as pip install arize[LLM_Evaluation]:
- nltk>=3.0.0, <4
- sacrebleu>=2.3.1, <3
- rouge-score>=0.1.2, <1
- evaluate>=0.3, <1
- Add Object Detection model-type support
- Add Generative LLM model-type support for pandas logging
- Add evaluation metrics generation for Generative LLM models
- Make prediction IDs optional
- Add summarization UseCase to AutoEmbeddings
- Add optional, additional custom headers to Client instantiation
- Add a warning message when only actuals are sent
- Add a descriptive error message when embedding features are sent without a vector
- Add warning when prediction label or prediction ID will be defaulted
- A bug causing skipped validation checks when the new REGRESSION and CATEGORICAL model types are selected
- Add a validation check that will fail if the character limit on prediction ID (128 max) is exceeded
- Add a validation check that will fail if there are duplicated columns in the dataframe
- Changed time range requirements to -2/+1 (two years in the past, and 1 future year)