Phoenix FAQs

Question 1

What frameworks and LLMs does Phoenix support?

Accepted Answer

Phoenix offers out-of-the-box support for popular frameworks like LlamaIndex, LangChain, Haystack, DSPy, and smolagents, as well as LLM providers like OpenAI, Bedrock, MistralAI, and VertexAI.

Question 2

How can I install Phoenix?

Accepted Answer

Phoenix can be installed using pip or conda with the command `pip install arize-phoenix`. Container images are also available on Docker Hub for deployment using Docker or Kubernetes.

Question 3

What is Phoenix?

Accepted Answer

Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting of Large Language Model (LLM) applications. It helps you understand and improve your LLM-powered products.

Question 4

What are the key features of Phoenix?

Accepted Answer

Key features include tracing of LLM application runtime, benchmarking application performance using response and retrieval evals, creating versioned datasets, tracking prompt and model changes, and optimizing prompts with a playground environment.

Question 5

What are Phoenix's sub-packages?

Accepted Answer

Phoenix offers lightweight Python sub-packages (arize-phoenix-otel, arize-phoenix-client, arize-phoenix-evals) and TypeScript packages (@arizeai/phoenix-client, @arizeai/phoenix-mcp) for specific functionalities, working seamlessly with the Phoenix platform.

Phoenix

Phoenix

Key Features

Use Cases

Key Features

Use Cases