Helicone Community Page

Updated last year

Timeout

Hello,
I've been experiencing timeouts using the free plan of Helicone. I intend to upgrade to premium, but currently I'm building my product.
At some point I got 500 Internal Server error, other times just timeouts.

This is the config I'm using:

Plain Text
  const model = new ChatOpenAI({
    temperature: 0,
    modelName: 'gpt-4',
    verbose: true,
    openAIApiKey: 'sk-xxx',
    configuration: {
      basePath: 'https://oai.hconeai.com/v1',
      baseOptions: {
        headers: {
          'Helicone-Auth': `Bearer sk-XXX`,
          'Helicone-User-Id': XXX,
          'Helicone-Cache-Enabled': true,
          'Cache-Control': 'max-age=86400',
          'Helicone-Retry-Enabled': true,
          'Helicone-Property-XXX': `XXX`,
          'Helicone-Property-XXX': `XXX`
        },
      },
    },
  });


Are there any limitations? My usage is 200 / 100,000

Thanks
C
p
J
4 comments
Hey! There should not be timeout issues on our end. Where are you running this code? Is this happening locally or are you running in a serverless or edge environment?
Hey! Both local and in fly.io
When that happens I just comment out the helicone config and it works
For the moment I haven't implemented an error tracker like Sentry (to have better context), but I'll report back with more info if that happens
Interesting that it is happening locally as well. Let me know what you see from Sentry and if that doesn't help fix it, we can always hop on a call and I can help figure it out!
Additionally - you might have more success with our async logging package
Add a reply
Sign up and join the conversation on Discord