> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Arize Phoenix

> Integrate Arize Phoenix observability with PraisonAI agents

# Arize Phoenix Integration

[Arize Phoenix](https://phoenix.arize.com/) provides LLM observability with OpenInference.

## Setup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install arize-phoenix openinference-instrumentation
export PHOENIX_API_KEY=xxx
export PHOENIX_COLLECTOR_ENDPOINT=https://app.phoenix.arize.com/
```

## Usage

### Auto-Instrumentation (Recommended)

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools.observability import obs
from praisonaiagents import Agent

obs.init(provider="arize_phoenix")

# Everything is auto-traced - no wrappers needed!
agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant.",
    model="gpt-4o-mini",
)

response = agent.chat("Hello!")
print(response)
```

### Explicit Tracing (For Fine Control)

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools.observability import obs

obs.init(provider="arize_phoenix", auto_instrument=False)

with obs.trace("workflow"):
    # Your agent code
    pass
```