Skip to main content
Open on GitHub

Helicone

此页面介绍如何在 LangChain 中使用 Helicone 生态系统。

Helicone 是什么？​

Helicone 是一个 开源 可观测性平台，可代理您的 OpenAI 流量，并为您提供有关支出、延迟和使用情况的关键洞察。

Screenshot of the Helicone dashboard showing average requests per day, response time, tokens per response, total cost, and a graph of requests over time.

快速入门​

在您的 LangChain 环境中，您只需添加以下参数即可。

export OPENAI_API_BASE="https://oai.hconeai.com/v1"

现在前往 helicone.ai 创建您的账户，并在我们的仪表板中添加您的 OpenAI API 密钥以查看日志。

Interface for entering and managing OpenAI API keys in the Helicone dashboard.

如何启用 Helicone 缓存​

from langchain_openai import OpenAI
import openai
openai.api_base = "https://oai.hconeai.com/v1"

llm = OpenAI(temperature=0.9, headers={"Helicone-Cache-Enabled": "true"})
text = "What is a helicone?"
print(llm.invoke(text))
API 参考：OpenAI

Helicone 缓存文档

如何使用 Helicone 自定义属性​

from langchain_openai import OpenAI
import openai
openai.api_base = "https://oai.hconeai.com/v1"

llm = OpenAI(temperature=0.9, headers={
        "Helicone-Property-Session": "24",
        "Helicone-Property-Conversation": "support_issue_2",
        "Helicone-Property-App": "mobile",
      })
text = "What is a helicone?"
print(llm.invoke(text))
API 参考：OpenAI

Helicone 属性文档