Arize Phoenix

This patch release (1.29.1) focuses on minor bug fixes, including updating documentation snippets and fixing an issue related to project deletion after experiment deletion.

Version 13.3.0 introduces a new conciseness classification evaluator and removes several UI components related to model inferences and embeddings. Bug fixes include improved error handling for JSONDistanceEvaluator.

Release 13.2.0 introduces support for AWS Bedrock cross-region inference preferences and includes several bug fixes, notably reverting a dependency that caused build issues.

Version 13.1.1 primarily addresses a bug fix related to the ModelMenu query fetch policy.

Version 13.1.0 introduces significant enhancements to table functionality, adds new session skills, and merges the phoenix-sdk-python skill into phoenix-evals. This release also includes various bug fixes related to model pricing and UI theming.

Patch release 13.0.3 primarily addresses a bug fix related to the playground interface.

Version 2.10.0 introduces dataset evaluators, full mustache prompt template support in the server, and enhancements to classification evaluators. A bug fix simplified template formatters.

This patch release primarily addresses dependency updates, specifically upgrading the arize-phoenix-client to version 1.29.0.

This release introduces dataset evaluators, enhancing the capabilities for evaluating datasets within the library.

Version 13.0.1 is a patch release primarily focused on fixing an issue related to file inclusion during package building.

Version 13.0.0 introduces extensive enhancements to LLM evaluation capabilities, including new built-in evaluators, improved playground features, and UI updates. This release contains breaking changes related to dataset evaluators.

This release introduces support for the Claude Opus 4.6 model and includes several bug fixes related to data validation, dependency updates, and improved UX for trace management.

Version 1.28.1 primarily addresses a bug by introducing timezone validation for the log_spans_dataframe function.

This release introduces the tool_selection evaluator to the evals library and includes several bug fixes, notably updating built-in model token prices and ensuring correct rendering of message content text.

This release introduces the new FaithfulnessEvaluator, several new evaluation metrics, and improves trace ID handling. A minor bug fix addresses the use of deprecated pandas NA checking.

Patch release 12.33.1 primarily addresses a bug fix related to GraphQL attribute access.

Version 12.33.0 introduces configurable email extraction via EMAIL_ATTRIBUTE_PATH for OAuth2 and resolves an import ordering issue related to namespace package discovery.

This release introduces several new skills, including CI/SKILL, evals, and tracing, alongside a new tool invocation accuracy metric. Bug fixes include updated token prices and improved dataset creation submission.

This patch release focuses on bug fixes, notably enabling multipart GraphQL subscription cancellation and removing the unnecessary pytz dependency.

This patch release updates the internal arize-phoenix-client dependency and fixes a KeyError issue related to pandas 3.0 compatibility in span queries.

This release introduces the new FaithfulnessEvaluator, deprecates HallucinationEvaluator, and adds support for linking dataset examples to traces via span_id_key.

This release introduces a new CLI, adds the FaithfulnessEvaluator, and includes updates to token prices and trace linking capabilities.

This release introduces new UI components for displaying JSON attributes and fixes several bugs related to preserving invocation parameters and response formats during model updates.

This release introduces connection timeout error handling, a correctness evaluator, and updates to span attribute display in the UI. It also includes dependency updates and documentation improvements.

Version 2.8.0 introduces a new correctness evaluator and enhances the LLM constructor by enabling sync/async client kwargs. It also fixes an issue related to newlines in built-in prompts.

Version 1.27.2 primarily addresses a bug related to using the context.span_id column when DataFrames utilize an integer index.

Patch release 12.28.1 primarily addresses a bug related to handling non-array values in NumDocuments to avoid PostgreSQL errors.

Version 12.28.0 introduces JSONL dataset upload support and a new tool selection correctness metric for evals, alongside several UI and layout bug fixes.

Version 12.27.0 introduces several UI/UX enhancements, including analytics, theme selection, and layout consistency, alongside a fix for built-in prompt formatting.

Version 12.26.0 introduces organizational improvements by moving the dataset example to the examples tab and includes several dependency updates and bug fixes, notably updating token prices and ensuring proper database engine disposal.

This patch release primarily addresses a bug fix related to updating the available options for the `reasoning_effort` setting when interacting with OpenAI services.

This patch release focuses on updating internal cost data and refining OpenAI reasoning effort options, alongside general documentation improvements.

Version 12.25.0 introduces lazy loading for embeddings/dimensions, Gemini tool call support, and updates key dependencies. LDAP configuration for email attributes has also been adjusted to use null as a sentinel value.

This patch release (2.7.1) primarily addresses bug fixes related to the rate limiter within the evals functionality.

Version 1.27.0 introduces new tracing capabilities with span notes functionality and adds support for Lightweight Directory Access Protocol (LDAP).

This release introduces optional scarf analytics and readme analytics features, alongside documentation updates to reorganize the sidebar navigation.

This release introduces a feature allowing the email field to be optional for LDAP configurations and includes documentation updates.

This release introduces a new span note function for the Python client and includes documentation updates.

Version 12.21.0 introduces a new endpoint for span notes and updates the built-in model token prices for cost tracking.

Version 12.20.0 introduces support for existing secrets and LDAP, alongside a dependency update for arize-phoenix-evals.

This release introduces support for prompt/template messages within the evals module.

Version 12.19.0 introduces a new feature for splitting on the experiments table and includes bug fixes related to token prices and Bedrock invocation parameters.

Version 12.18.0 introduces support for Claude Opus 4-5, enables split assignment during dataset upload, and includes several dependency updates and bug fixes.

Version 1.26.0 introduces the ability to assign splits directly during dataset uploads.

Version 1.25.0 introduces new evaluation helpers specifically designed to simplify pulling RAG spans.

Version 12.17.0 introduces new features like enabling repetitions in the playground and improving the retention policy UX, alongside several dependency updates and bug fixes across the platform.

Version 2.6.1 primarily addresses a bug related to handling None values for top_p and temperature settings within the AnthropicModel integration.

Version 1.24.0 primarily updates the client license to Apache 2.0.

This release primarily focuses on licensing, switching the client to the Apache 2.0 license.

This release introduces significant feature enhancements, including support for OpenAI 5.1 and expanded reasoning capabilities for Gemini models, while simultaneously dropping support for Python 3.9.

This patch release (12.15.1) focuses on maintenance, including updating built-in model token prices and fixing caching and integer handling issues.

Version 12.15.0 introduces an update to the supported Anthropic model list.

This patch release primarily focuses on dependency updates, specifically bumping the playwright version, and includes a fix related to prompt handling by using loadQuery.

This patch release focuses on improving internal stability by adding type safety to the loader data handling.

This release introduces the React compiler feature, accessible via configuration, enhancing the platform's capabilities.

This patch release fixes an issue where backslashes were not properly escaped during Python string sanitization and updates a key dependency.

Version 2.6.0 introduces new adapters for Anthropic and Google GenAI, adds GPT-5 support for Azure OpenAI, and includes various bug fixes and ergonomic improvements to the evaluation module.

Version 1.23.0 introduces experiment retries to enhance robustness. This release focuses on stability and new feature implementation.

Phoenix v12.13.0 introduces pure functions for rendering and removes reliance on "@arizeai/components", alongside several bug fixes including restored charting colors and updated token prices.

Version 12.12.0 introduces a feature where page titles are derived from navigation data. No breaking changes or bug fixes were noted in this release.

This patch release addresses a specific UI bug related to the timezone selector compatibility across different browsers.

Version 12.11.0 introduces user timezone preference settings and includes several bug fixes related to client versioning, form validation, and metric time ranges.

Version 1.22.0 introduces several new features including binding examples to evaluators, prompt metadata, and resuming experiments. It also includes bug fixes related to error messaging and input softening for dataset creation.

Phoenix version 12.10.0 introduces several new features including ES2022 target support, system themes, and enhanced authentication controls. This release also includes bug fixes related to Helm deployments and playground rendering.

Phoenix version 12.9.0 introduces several new features, including enhanced menu abstractions, AWS IAM auth support, and improvements to experiment comparison, alongside a bug fix for Bedrock model IDs.

Version 12.8.0 introduces several UI and backend enhancements, including a split edit menu and preloading GraphQL queries, alongside an update to built-in model token prices.

This patch release primarily focuses on a bug fix related to fetching user API keys on the profile page.

This release focuses heavily on enhancing dataset and experiment management with new filtering, editing, and comparison features, alongside removing the splits feature flag for simplification. Several bug fixes address cost calculations and UI interactions.

Version 12.6.1 primarily addresses a bug related to session table row clicking functionality.

This release primarily focuses on upgrading the frontend framework by moving to React 19.2 and includes a fix for sorting issues on the experiment compare list page.

Phoenix version 12.5.0 introduces several UI and feature enhancements, including filtering for examples and split management, a new viewer role, and improvements to experiment comparison views. A bug fix addresses incorrect Python code for dataset retrieval.

Version 12.4.0 introduces PKCE support for OAuth 2.0 OIDC and includes several bug fixes related to data ingestion and UI elements.

Version 2.5.0 introduces a new regex evaluator, improves binding ergonomics, and expands LLM provider support.

Phoenix version 12.3.0 introduces several UI enhancements for datasets and experiments, alongside bug fixes related to token prices, query parameters, and OIDC error handling.

Version 12.2.0 introduces several new UI and dataset management features, including prompt version editing and bulk label operations, alongside various bug fixes for stability and performance.

Version 2.4.0 introduces support for asynchronous functions within the evaluator creation utility and includes documentation enhancements for the evals module.

Version 2.3.0 introduces support for dot-delimited fstring keys in evaluation templates and improves key extraction logic within evals.

Phoenix version 12.1.0 introduces support for Claude Sonnet 4.5, adds GraphQL operations for dataset labels, and includes several bug fixes for component switching and playground loading.

Version 1.21.0 introduces new client methods for adding trace and session annotations, along with updated session API documentation.

Version 12.0.0 introduces significant database schema updates, including support for session annotations, dataset splits, and experiment snapshots. This major release includes numerous backend improvements and updates to dependency handling.

This release introduces a new document relevance evaluator and a utility for formatting dataframe evaluations as annotations for logging to Phoenix.

Version 1.20.0 introduces support for tracking repetitions and fixes an issue related to Experiment tracing respecting OITracer configurations.

Version 11.38.0 introduces the ability to configure repetitions in the playground and resolves several minor bugs related to link generation and playground error handling.

Version 11.37.0 introduces new UI features like a checkbox and custom HTTP headers for the playground, alongside several bug fixes related to Helm, pagination, and float formatting.

Version 2.1.0 introduces support for the Azure provider and includes bug fixes related to OpenAI SDK retries and tracer implementation.

This release introduces improvements to experiment comparison visualization and updates the notification system to use react-aria toasts, alongside a minor fix in the TypeScript client snippet.

Version 11.35.0 introduces IPv6 support and image registry configuration for Helm charts, alongside several bug fixes primarily focused on SQLite and dependency updates.

This patch release primarily addresses a bug in the client related to handling printed URLs for proxied connections.

Version 1.19.0 introduces compatibility improvements for the Experiments<->Evals 2.0 feature set.

This patch release primarily addresses a documentation issue by fixing incorrect import paths in the preview documentation.

Version 2.0.0 stabilizes Evals 2.0, introduces asynchronous evaluation capabilities, and adds rate limiting to LLM interactions. This release includes significant updates to the evals module.

Version 11.34.0 introduces new features for experiment comparison and span queue management, alongside a fix to the insertion time histogram buckets.

Version 11.33.0 introduces several enhancements to experiment tracking, including new UI elements and paging, alongside prompt labeling features and updated token prices.

Version 1.18.2 primarily focuses on a bug fix within the experiments module to validate the 'repetitions' parameter.

Version 1.18.1 primarily addresses bug fixes, including improved handling for multi-index dataframes in document annotations and correcting documentation errors.

This patch release focuses primarily on documentation improvements, including adding docs links to readmes, fixing python client documentation, ensuring consistent docstrings, and improving OpenTelemetry documentation.

Version 11.32.1 is a patch release focused on restoring compatibility with older versions of Pydantic (<2.6).

This release focuses on frontend improvements for the experiments list page and introduces pagination when fetching experiment runs inside run_experiment.

Version 1.18.0 introduces pagination support for fetching experiment runs inside the run_experiment function, improving handling of large result sets.

Version 1.17.1 primarily addresses a bug fix related to backward compatibility for the 'example' argument within the experiment task function.