Skip to main content

Log10

本页面介绍如何在 LangChain 中使用 Log10。

什么是 Log10？​

Log10 是一个开源的无代理 LLM 数据管理和应用开发平台，可以让您记录、调试和标记您的 Langchain 调用。

快速开始​

  1. 在 log10.io 创建免费帐户。

  2. 从“设置”和“组织”选项卡分别添加您的 LOG10_TOKEN 和 LOG10_ORG_ID 作为环境变量。

  3. 还需将 LOG10_URL=https://log10.io 和您通常的 LLM API 密钥（例如 OPENAI_API_KEY 或 ANTHROPIC_API_KEY）添加到您的环境中。

如何启用 Langchain 的 Log10 数据管理​

与 log10 的集成是一个简单的一行代码 log10_callback 集成，如下所示：

from langchain_openai import ChatOpenAI
from langchain_core.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 + Logs 文档

更多详情 + 截图，包括自行托管日志的说明。

如何在 Log10 中使用标记​

from langchain_openai import OpenAI
from langchain_community.chat_models import ChatAnthropic
from langchain_openai import ChatOpenAI
from langchain_core.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-2", 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)

您还可以混合直接的 OpenAI 调用和 Langchain LLM 调用：

import os
from log10.load import log10, log10_session
import openai
from langchain_openai import OpenAI
log10(openai)
with log10_session(tags=["foo", "bar"]):
    # 记录直接的 OpenAI 调用
    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)
    # 通过 Langchain 记录调用
    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

更多 Langchain 示例

Was this page helpful?


You can leave detailed feedback on GitHub.