# LangFuse — Open Source LLM Observability & Tracing

> Trace, evaluate, and monitor LLM applications in production. Open-source alternative to LangSmith with prompt management, cost tracking, and evaluation pipelines.

## Install

Save in your project root:

## Quick Use

```bash
pip install langfuse
```

```python
from langfuse import Langfuse

langfuse = Langfuse(
    public_key="pk-...",
    secret_key="sk-...",
    host="https://cloud.langfuse.com",
)

# Trace a generation
trace = langfuse.trace(name="chat")
generation = trace.generation(
    name="llm-call",
    model="gpt-4o",
    input=[{"role": "user", "content": "Hello"}],
    output="Hi there!",
    usage={"input": 10, "output": 5},
)
langfuse.flush()
```

## What is LangFuse?

LangFuse is an open-source observability platform for LLM applications. It provides tracing, prompt management, evaluation, and cost analytics — helping teams debug, improve, and monitor their AI features in production.

**Answer-Ready**: LangFuse is an open-source LLM observability platform providing tracing, prompt management, evaluation pipelines, and cost analytics for production AI applications.

## Core Features

### 1. Distributed Tracing
Trace complex chains and agent workflows:

```python
from langfuse.decorators import observe

@observe()
def my_agent(query: str):
    context = retrieve_docs(query)
    return generate_response(query, context)

@observe()
def retrieve_docs(query: str):
    # Automatically nested as child span
    return vector_db.search(query)

@observe()
def generate_response(query: str, context: str):
    return openai.chat.completions.create(...)
```

### 2. Framework Integrations

```python
# OpenAI SDK (drop-in)
from langfuse.openai import openai
# All calls automatically traced

# LangChain
from langfuse.callback import CallbackHandler
handler = CallbackHandler()
chain.invoke({"input": "..."}, config={"callbacks": [handler]})

# LlamaIndex
from llama_index.core import Settings
Settings.callback_manager.add_handler(langfuse_handler)
```

### 3. Prompt Management
Version and deploy prompts from the LangFuse UI:

```python
prompt = langfuse.get_prompt("customer-support-v2")
compiled = prompt.compile(customer_name="Alice")
```

### 4. Evaluation Pipelines
Score traces manually or with LLM-as-judge:

```python
langfuse.score(
    trace_id="trace-123",
    name="helpfulness",
    value=0.9,
    comment="Accurate and complete",
)
```

### 5. Cost Dashboard
Automatic cost calculation per model, per user, per feature.

## Self-Hosting

```bash
docker compose up -d  # PostgreSQL + LangFuse server
```

Or use the managed cloud at cloud.langfuse.com.

## FAQ

**Q: How does it compare to LangSmith?**
A: LangFuse is open-source and self-hostable. LangSmith is LangChain-specific and proprietary.

**Q: Does it work without LangChain?**
A: Yes, framework-agnostic. Works with any Python or JS/TS app.

**Q: Production overhead?**
A: Async by default — traces are batched and sent in background with < 1ms overhead.

## Source & Thanks

- GitHub: [langfuse/langfuse](https://github.com/langfuse/langfuse) (10k+ stars)
- Docs: [langfuse.com/docs](https://langfuse.com/docs)

<!-- ZH -->

## 快速使用

```bash
pip install langfuse
```

三行代码开始追踪 LLM 调用，查看延迟、成本和输出质量。

## 什么是 LangFuse？

LangFuse 是开源 LLM 可观测性平台，提供追踪、提示管理、评估和成本分析——帮助团队调试、改进和监控生产环境中的 AI 功能。

**一句话总结**：LangFuse 是开源 LLM 可观测性平台，提供追踪、提示管理、评估管线和成本分析。

## 核心功能

### 1. 分布式追踪
用 `@observe()` 装饰器自动追踪复杂链和代理工作流。

### 2. 框架集成
支持 OpenAI SDK、LangChain、LlamaIndex 等，一行代码接入。

### 3. 提示管理
在 UI 中版本控制和部署提示模板。

### 4. 评估管线
手动评分或用 LLM-as-Judge 自动评估。

### 5. 成本仪表盘
按模型、用户、功能自动计算成本。

## 自托管

```bash
docker compose up -d
```

或使用托管云版本。

## 常见问题

**Q: 和 LangSmith 比较？**
A: LangFuse 开源可自托管，LangSmith 专属 LangChain 且闭源。

**Q: 生产环境开销？**
A: 默认异步，后台批量发送，开销 < 1ms。

## 来源与致谢

- GitHub: [langfuse/langfuse](https://github.com/langfuse/langfuse) (10k+ stars)

---
Source: https://tokrepo.com/en/workflows/763445c0-8c1e-41de-97c8-9685e59521a7
Author: AI Open Source