Warning

This integration method is maintained but no longer actively developed. For the best experience and latest features, use our new AI Gateway with unified API access to 100+ models.

Using the Helicone SDK (recommended)#

Walkthrough: logging chat completions#

To get started, install the `@helicone/helpers` package

npm install @helicone/helpers

Setup the logger

  import { HeliconeManualLogger } from "@helicone/helpers";  const logger = new HeliconeManualLogger({    apiKey: process.env.HELICONE_API_KEY  });

Call your LLM and log the request

const reqBody = {  model: "phi3:mini",  messages: [{     role: "user",     content: "Why is the sky blue?"  }],  stream: false}const res = await logger.logRequest(reqBody, async (resultRecorder) => {   const r = await fetch("http://localhost:11434/api/chat", {     method: "POST",     headers: {       "Content-Type": "application/json",     },     body: JSON.stringify(reqBody)   })       const resBody = await r.json();   resultRecorder.appendResult(resBody);   return resBody;})

Go to the Helicone Requests page and see your request!

Example: logging completion request#

The above example uses phi3:mini model and the Chat Completion interface. The same can be done with a regular completion request:

// ...const reqBody = {  model: "llama3.1",  prompt: "Why is the sky blue?",  stream: false,};const res = await logger.logRequest(reqBody, async (resultRecorder) => {  const r = await fetch("http://localhost:11434/api/generate", {    method: "POST",    headers: {      "Content-Type": "application/json",    },    body: JSON.stringify(reqBody)  })     const resBody = await r.json();  resultRecorder.appendResult(resBody);  return resBody;})

Resources#

See Logging Custom Models to learn how to log any model.
Ollama API Reference