Skip to main content

Helicone (螺旋锥)

This page covers how to use the Helicone (螺旋锥) ecosystem within LangChain.

What is Helicone? (什么是螺旋锥?)​

Helicone is an open source (开源) observability platform that proxies your OpenAI traffic and provides you key insights into your spend, latency and usage.

Helicone

Quick start (快速入门)​

With your LangChain environment you can just add the following parameter.

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

Now head over to helicone.ai to create your account, and add your OpenAI API key within our dashboard to view your logs.

Helicone

How to enable Helicone caching (如何启用螺旋锥缓存)​

from langchain.llms 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(text))

Helicone caching docs (螺旋锥缓存文档)

How to use Helicone custom properties (如何使用螺旋锥自定义属性)​

from langchain.llms 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(text))

Helicone property docs (螺旋锥属性文档)