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

# Log10 集成

> 使用 LangChain Python 集成 Log10。

> [!WARNING]
>
> `langchain-community`包已不再维护。从`langchain_community`导入的示例可能过时或无法使用。请谨慎使用。

本页面介绍如何在 LangChain 中使用 [Log10](https://log10.io)。

## 什么是 Log10？

Log10 是一个 [开源](https://github.com/log10-io/log10) 无服务 LLM 数据管理和应用开发平台，可帮助您记录、调试和标记 LangChain 调用。

## 快速入门

1. 在 [log10.io](https://log10.io) 创建免费账户
2. 分别从 Settings（设置）和 Organization（组织）标签页添加 `LOG10_TOKEN` 和 `LOG10_ORG_ID` 作为环境变量
3. 同时添加 `LOG10_URL=https://log10.io` 和常规 LLM API 密钥（例如 `OPENAI_API_KEY` 或 `ANTHROPIC_API_KEY`）到环境变量

## 如何为 LangChain 启用 Log10 数据管理

Integration with log10 是一个简单的单行 `log10_callback` 集成，示例如下：

```python theme={null}
from langchain_openai import ChatOpenAI
from langchain.messages import HumanMessage

from log10.langchain import Log10Callback
from log10.llm import Log10Config

log10_callback = Log10Callback(log10_config=Log10Config())

messages = [
    HumanMessage(content="You are a ping pong machine"),
    HumanMessage(content="Ping?"),
]

llm = ChatOpenAI(model="gpt-3.5-turbo", callbacks=[log10_callback])
```

[log10 + LangChain + 日志文档](https://github.com/log10-io/log10/blob/main/logging.md#langchain-logger)

[更多细节 + 屏幕快照](https://log10.io/docs/observability/logs)（包括自托管日志的说明）

## 如何使用 Log10 的标签

> [!WARNING]
>
> `langchain-community`包已不再维护。从`langchain_community`导入的示例可能过时或无法使用。请谨慎使用。

```python theme={null}
from langchain_openai import OpenAI
from langchain_community.chat_models import ChatAnthropic
from langchain_openai import ChatOpenAI
from langchain.messages import HumanMessage

from log10.langchain import Log10Callback
from log10.llm import Log10Config

log10_callback = Log10Callback(log10_config=Log10Config())

messages = [
    HumanMessage(content="You are a ping pong machine"),
    HumanMessage(content="Ping?"),
]

llm = ChatOpenAI(model="gpt-3.5-turbo", callbacks=[log10_callback], temperature=0.5, tags=["test"])
completion = llm.predict_messages(messages, tags=["foobar"])
print(completion)

llm = ChatAnthropic(model="claude-sonnet-4-6", callbacks=[log10_callback], temperature=0.7, tags=["baz"])
llm.predict_messages(messages)
print(completion)

llm = OpenAI(model_name="gpt-3.5-turbo-instruct", callbacks=[log10_callback], temperature=0.5)
completion = llm.predict("You are a ping pong machine.\nPing?\n")
print(completion)
```

您还可以混合直接调用 OpenAI 和 LangChain LLM 的调用：

```python theme={null}
import os
from log10.load import log10, log10_session
import openai
from langchain_openai import OpenAI

log10(openai)

with log10_session(tags=["foo", "bar"]):
    # Log a direct OpenAI call
    response = openai.Completion.create(
        model="text-ada-001",
        prompt="Where is the Eiffel Tower?",
        temperature=0,
        max_tokens=1024,
        top_p=1,
        frequency_penalty=0,
        presence_penalty=0,
    )
    print(response)

    # Log a call via LangChain
    llm = OpenAI(model_name="text-ada-001", temperature=0.5)
    response = llm.predict("You are a ping pong machine.\nPing?\n")
    print(response)
```

## 如何调试 LangChain 调用

[调试示例](https://log10.io/docs/observability/prompt_chain_debugging)

[更多 LangChain 示例](https://github.com/log10-io/log10/tree/main/examples#langchain)

***

> 官方原文：[src/oss/python/integrations/providers/log10.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/providers/log10.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.