# Phoenix Tracing Quickstart — OpenInference Tracer Setup

> Phoenix instruments OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI via OpenInference. Local UI or Arize cloud. No per-call code changes.

## Install

Copy the content below into your project:

## Quick Use

1. `pip install arize-phoenix openinference-instrumentation-openai`
2. `phoenix serve` (or use Arize cloud endpoint)
3. `OpenAIInstrumentor().instrument()` — every call now traces

---

## Intro

Phoenix is the open-source observability companion to Arize AX — drop the OpenInference tracer in once and every OpenAI / Anthropic / LangChain / LlamaIndex / CrewAI / DSPy call gets a trace span automatically with prompts, completions, latency, and token cost. View traces in the local Phoenix UI (port 6006) or send them to Arize cloud. Best for: debugging multi-step agents, finding which retrieval step poisoned the answer, comparing prompt versions side-by-side. Works with: any Python LLM stack via OpenInference instrumentation. Setup time: 2 minutes.

---

### Install + start local Phoenix

```bash
pip install arize-phoenix openinference-instrumentation-openai openinference-instrumentation-langchain
phoenix serve  # starts UI on http://localhost:6006
```

### Auto-instrument OpenAI

```python
from phoenix.otel import register
from openinference.instrumentation.openai import OpenAIInstrumentor

tracer_provider = register(project_name="my-rag-app", endpoint="http://localhost:6006/v1/traces")
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)

# That's it. Now every OpenAI call traces automatically:
from openai import OpenAI
client = OpenAI()
client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Explain quantum entanglement"}],
)
# Open localhost:6006 — your trace appears with prompt, completion, latency, cost.
```

### LangChain + LlamaIndex

```python
from openinference.instrumentation.langchain import LangChainInstrumentor
from openinference.instrumentation.llama_index import LlamaIndexInstrumentor

LangChainInstrumentor().instrument(tracer_provider=tracer_provider)
LlamaIndexInstrumentor().instrument(tracer_provider=tracer_provider)
```

### Send to Arize cloud instead

```python
tracer_provider = register(
    project_name="my-rag-app",
    endpoint="https://otlp.arize.com/v1/traces",
    headers={"api_key": ARIZE_API_KEY, "space_id": ARIZE_SPACE_ID},
)
```

### Trace span attributes (OpenInference standard)

| Attribute | Example |
|---|---|
| `llm.model_name` | `gpt-4o` |
| `llm.token_count.prompt` | `847` |
| `llm.token_count.completion` | `213` |
| `llm.input_messages.0.message.content` | full prompt text |
| `output.value` | model output |
| `retrieval.documents.*.document.content` | chunks fetched in RAG |

---

### FAQ

**Q: Phoenix vs Langfuse vs LangSmith?**
A: Phoenix is OpenInference-native — vendor-neutral OTel attributes that any backend can read. Langfuse has stronger prompt management and self-host story. LangSmith is best if you live in LangChain. Phoenix is the choice when you want OTel and may switch backends.

**Q: Does Phoenix need a database?**
A: Local mode uses SQLite under ~/.phoenix. Production self-host swaps to Postgres via PHOENIX_SQL_DATABASE_URL. Arize cloud handles persistence for you. SQLite is fine for solo dev with <10K traces.

**Q: Can I see traces from a notebook?**
A: Yes — `phoenix.launch_app()` opens the UI inline as a Jupyter widget or new tab. Combine with `phoenix.evals` to run LLM-as-judge evals and view them next to traces.

---

## Source & Thanks

> Built by [Arize AI](https://github.com/Arize-ai). Licensed under Apache-2.0.
>
> [Arize-ai/phoenix](https://github.com/Arize-ai/phoenix) — ⭐ 4,500+

---

<!-- ZH -->

## 快速使用

1. `pip install arize-phoenix openinference-instrumentation-openai`
2. `phoenix serve`（或用 Arize 云端 endpoint）
3. `OpenAIInstrumentor().instrument()` —— 之后每次调用自动 trace

---

## 简介

Phoenix 是 Arize AX 的开源观测同伴 —— OpenInference tracer 装一次，OpenAI / Anthropic / LangChain / LlamaIndex / CrewAI / DSPy 每次调用自动产生 trace span，含 prompt、completion、延迟、token 成本。在本地 Phoenix UI（6006 端口）看，或推到 Arize 云端。适合调试多步 agent、找出哪个 retrieval 步骤毒化了答案、并排对比 prompt 版本。兼容任何走 OpenInference 注入的 Python LLM 栈。装机时间 2 分钟。

---

### 安装 + 起本地 Phoenix

```bash
pip install arize-phoenix openinference-instrumentation-openai openinference-instrumentation-langchain
phoenix serve  # UI 起在 http://localhost:6006
```

### 自动注入 OpenAI

```python
from phoenix.otel import register
from openinference.instrumentation.openai import OpenAIInstrumentor

tracer_provider = register(project_name="my-rag-app", endpoint="http://localhost:6006/v1/traces")
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)

# 这就完了。之后每次 OpenAI 调用都自动 trace：
from openai import OpenAI
client = OpenAI()
client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "解释量子纠缠"}],
)
# 打开 localhost:6006 —— trace 出现，含 prompt、completion、延迟、成本。
```

### LangChain + LlamaIndex

```python
from openinference.instrumentation.langchain import LangChainInstrumentor
from openinference.instrumentation.llama_index import LlamaIndexInstrumentor

LangChainInstrumentor().instrument(tracer_provider=tracer_provider)
LlamaIndexInstrumentor().instrument(tracer_provider=tracer_provider)
```

### 改推到 Arize 云端

```python
tracer_provider = register(
    project_name="my-rag-app",
    endpoint="https://otlp.arize.com/v1/traces",
    headers={"api_key": ARIZE_API_KEY, "space_id": ARIZE_SPACE_ID},
)
```

### Trace span 属性（OpenInference 标准）

| 属性 | 例子 |
|---|---|
| `llm.model_name` | `gpt-4o` |
| `llm.token_count.prompt` | `847` |
| `llm.token_count.completion` | `213` |
| `llm.input_messages.0.message.content` | 完整 prompt 文本 |
| `output.value` | 模型输出 |
| `retrieval.documents.*.document.content` | RAG 拉到的 chunk |

---

### FAQ

**Q: Phoenix vs Langfuse vs LangSmith？**
A: Phoenix 原生 OpenInference —— 厂商中立的 OTel 属性，任何后端都能读。Langfuse prompt 管理和自托管更强。LangSmith 在 LangChain 里活的人最适合。要 OTel 又可能切后端就选 Phoenix。

**Q: Phoenix 需要数据库吗？**
A: 本地模式用 ~/.phoenix 下的 SQLite。生产自托管通过 PHOENIX_SQL_DATABASE_URL 切 Postgres。Arize 云端帮你处理持久化。单人开发 <1 万 trace 的话 SQLite 够用。

**Q: 能在 notebook 里看 trace 吗？**
A: 能 —— `phoenix.launch_app()` 内嵌 UI 当 Jupyter widget 或开新标签页。配 `phoenix.evals` 跑 LLM-as-judge 评估，就在 trace 旁边看。

---

## 来源与感谢

> Built by [Arize AI](https://github.com/Arize-ai). Licensed under Apache-2.0.
>
> [Arize-ai/phoenix](https://github.com/Arize-ai/phoenix) — ⭐ 4,500+


---
Source: https://tokrepo.com/en/workflows/phoenix-tracing-quickstart-openinference-tracer-setup
Author: Arize AI