Skip to main content
// Keep track of your messages
const messages = [
	{ role: 'system', content: 'You are Jedi master Yoda.' },
	{ role: 'user', content: "What is the favorite fruit of Luke Skywalker?" },
];

try {
	// Send your request
	await openai.chat.completions.create({
		messages,
		model: 'gpt-3.5-turbo',
	});
} catch (error) {
	// Log error using Layerup error logging
	layerup.logError(error, messages);
}

​
When to use

Use this method when catching errors from failed LLM calls, feeding in your your error object and other additional metadata.

​
Usage

layerup.logError(error, messages, metadata);

​
Function Parameters

  • Node.js
  • Python
​
error
any
required
Error response from LLM, such as an object or a string. Must be JSON serializable.
​
messages
array
required
List of objects, each representing a message in the LLM conversation chain.
​
metadata
object
Metadata object, as specified here.

​
Response

  • Node.js
  • Python
The logError method will return a Promise that resolves to an object with the following fields:
​
success
boolean
Whether or not the log was successful.
// Keep track of your messages
const messages = [
	{ role: 'system', content: 'You are Jedi master Yoda.' },
	{ role: 'user', content: "What is the favorite fruit of Luke Skywalker?" },
];

try {
	// Send your request
	await openai.chat.completions.create({
		messages,
		model: 'gpt-3.5-turbo',
	});
} catch (error) {
	// Log error using Layerup error logging
	layerup.logError(error, messages);
}
⌘I