Arize Phoenix

AI Observability and Evaluation

Phoenix is an open-source observability library designed for experimentation, evaluation, and troubleshooting. It allows AI Engineers and Data Scientists to quickly visualize their data, evaluate performance, track down issues, and export data to improve. Phoenix is built by Arize AI, the company behind the industry-leading AI observability platform, and a set of core contributors.

Install Phoenix

pip

In your Python, Jupyter, or Colab environment, run the following command to install.

pip install arize-phoenix

For full details on how to run phoenix in various environments such as Databricks, consult our environments guide.

conda

conda install -c conda-forge arize-phoenix[evals]

Container

Phoenix can also run via a container. The image can be found at:

Docker

Images for phoenix are published to dockerhub

Checkout the environments section and deployment guide for details.

npm

The Phoenix server can be run as a Containerand be interacted with using the phoenix-client and OpenTelelemetry. See Packages below.

Phoenix works with OpenTelemetry and OpenInference instrumentation. If you are looking to deploy phoenix as a service rather than a library, see Self-hosting

What you can do in Phoenix

Prompt Engineering

Phoenix Prompt Playground

Phoenix offers tools to streamline your prompt engineering workflow.

• Prompt Management - Create, store, modify, and deploy prompts for interacting with LLMs

• Prompt Playground - Play with prompts, models, invocation parameters and track your progress via tracing and experiments

• Span Replay - Replay the invocation of an LLM. Whether it's an LLM step in an LLM workflow or a router query, you can step into the LLM invocation and see if any modifications to the invocation would have yielded a better outcome.

• Prompts in Code - Phoenix offers client SDKs to keep your prompts in sync across different applications and environments.

Tracing

Tracing in Phoenix

Tracing is a helpful tool for understanding how your LLM application works. Phoenix's open-source library offers comprehensive tracing capabilities that are not tied to any specific LLM vendor or framework.

Phoenix accepts traces over the OpenTelemetry protocol (OTLP) and supports first-class instrumentation for a variety of frameworks (LlamaIndex, LangChain, DSPy), SDKs (OpenAI, Bedrock, Mistral, Vertex), and Languages. (Python, Javascript, etc.)

Evaluation

Evals in the Phoenix UI

Phoenix is built to help you evaluate your application and understand their true performance. To accomplish this, Phoenix includes:

• A standalone library to run LLM-based evaluations on your own datasets. This can be used either with the Phoenix library, or independently over your own data.

• Direct integration of LLM-based and code-based evaluators into the Phoenix dashboard. Phoenix is built to be agnostic, and so these evals can be generated using Phoenix's library, or an external library like Ragas, Deepeval, or Cleanlab.

• Human annotation capabilities to attach human ground truth labels to your data in Phoenix.

Datasets & Experiments

Experiments in Phoenix

Phoenix Datasets & Experiments let you test different versions of your application, store relevant traces for evaluation and analysis, and build robust evaluations into your development process.

• Run Experiments to test and compare different iterations of your application

• Collect relevant traces into a Dataset, or directly upload Datasets from code / CSV

• Run Datasets through Prompt Playground, export them in fine-tuning format, or attach them to an Experiment.

Quickstarts

Running Phoenix for the first time? Select a quickstart below.

Tracing

Prompt Playground

Datasets and Experiments

Evaluation

Inferences

Packages

The main Phoenix package is arize-phoenix. We offer several packages below for specific use cases.

Python

Package	What It's For	Pypi
arize-phoenix	Running and connecting to the Phoenix client. Used: - Self-hosting Phoenix - Connecting to a Phoenix client (either Phoenix Developer Edition or self-hosted) to query spans, run evaluations, generate datasets, etc. *arize-phoenix automatically includes arize-phoenix-otel and arize-phoenix evals
arize-phoenix-otel	Sending OpenTelemetry traces to a Phoenix instance
arize-phoenix-evals	Running evaluations in your environment
openinference-semantic-conventions	Our semantic layer to add LLM telemetry to OpenTelemetry
openinference-instrumentation-xxxx	Automatically instrumenting popular packages.	See Tracing Integrations (Auto)

TypeScript

Package	What It's For	npm
@arizeai/phoenix-client	Running and connecting to the Phoenix server.	coming soon
@arizeai/openinference-semantic-conventions	Our semantic layer to add LLM telemetry to OpenTelemetry
@aizeai/openinference-instrumentation-xxxx	Automatically instrumenting popular packages.	See Tracing Integrations (Auto)

Next Steps

Try our Tutorials

Check out a comprehensive list of example notebooks for LLM Traces, Evals, RAG Analysis, and more.

Community

Join the Phoenix Slack community to ask questions, share findings, provide feedback, and connect with other developers.