Arize Phoenix Files

Uncover insights, surface problems, monitor, and fine tune your LLM

This is an exact mirror of the Arize Phoenix project, hosted at https://github.com/Arize-ai/phoenix. SourceForge is not affiliated with Arize Phoenix. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
arize-phoenix_ v12.7.0 source code.tar.gz	2025-10-24	310.9 MB	0
arize-phoenix_ v12.7.0 source code.zip	2025-10-24	313.2 MB	2
README.md	2025-10-24	4.7 kB	0
Totals: 3 Items		624.2 MB	2

12.7.0 (2025-10-24)

Features

dataset label cleanup (#9959) (b78072e)
dataset page label (#9903) (4b6098e)
datasets table label filter (#9794) (aca5fe0)
datasets: Remove splits feature flag, simplify menu selection (#9998) (4514a78)
Experiment Compare Page Split Aware (#9951) (19e6909)
ExperimentRuns over Dataset Splits (#9863) (4b556b8)
experiments: add annotation values and sorting to experiment compare slideover (#9872) (068f633)
experiments: experiment compare slideover UI tweaks (#9942) (48e8e3d)
experiments: filter annotations in experiment compare slideover (#9953) (b3ff2fd)
Filter prompts page by label (#9933) (5090026)
individual dataset label edit (#9924) (538fd38)
playground: update slideover in playground dataset examples table (#9928) (dd22536)
query examples by splits (#9762) (e698c9f)
remove dataset-label feature flag (#9934) (2c8a21f)

Bug Fixes

cost: update built-in model token prices (#9886) (42061a1)
cost: update built-in model token prices (#9916) (628228c)
playground: dataset select fixes (#9984) (ca1f7ff)
playground: use more verbose name for save prompt button (#9945) (bfc9e6f)
refresh data in UI after creating a new project or API key (#9958) (c1b2356)
split name as string instead of identifier (#9962) (3eccfce)
version upper bound for wrapt <2.0 (#9915) (bc34268)

Documentation

add phoenix-otel to readmes (#9990) (b5b681a)
sync main to docs (65a68f4)

Source: README.md, updated 2025-10-24

Other Useful Business Software

Gen AI apps are built with MongoDB Atlas Icon

Gen AI apps are built with MongoDB Atlas

Build gen AI apps with an all-in-one modern database: MongoDB Atlas

MongoDB Atlas provides built-in vector search and a flexible document model so developers can build, scale, and run gen AI apps without stitching together multiple databases. From LLM integration to semantic search, Atlas simplifies your AI architecture—and it’s free to get started.

Start Free

Our Free Plans just got better! | Auth0 Icon

Our Free Plans just got better! | Auth0

With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.

Try free now

Recommended Projects

Dagster
Dagster is an orchestration platform for the development, production, and observation of data assets. Dagster as a productivity platform: With Dagster, you can focus on running tasks, or you can identify the key assets you need to create using a declarative approach. Embrace CI/CD best...
OpenLIT
OpenLIT is an OpenTelemetry-native tool designed to help developers gain insights into the performance of their LLM applications in production. It automatically collects LLM input and output metadata and monitors GPU performance for self-hosted LLMs. OpenLIT makes integrating observability into...
Elastic APM Node.js Agent
This is the official Node.js application performance monitoring (APM) agent for the Elastic Observability solution. It is a Node.js package that runs with your Node.js application to automatically capture errors, tracing data, and performance metrics. APM data is sent to your Elastic...
Pandas Profiling
pandas-profiling generates profile reports from a pandas DataFrame. The pandas df.describe() function is handy yet a little basic for exploratory data analysis. pandas-profiling extends pandas DataFrame with df.profile_report(), which automatically generates a standardized univariate and...
Jaeger UI
Visualize distributed tracing with Jaeger. Distributed tracing observability platforms, such as Jaeger, are essential for modern software applications that are architected as microservices. Jaeger maps the flow of requests and data as they traverse a distributed system. These requests may make...