Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error connecting workflow to prompt - Network error trying to host locally on vultr using the docker template #1846

Open
TheMindExpansionNetwork opened this issue Feb 27, 2025 · 2 comments

Comments

@TheMindExpansionNetwork

Image

Hello you all love this tool trying to get it hosted locally on this machine I got it all situated with the docker compose up -d and it seems to be running working

I put in the IP address of my vultr server then http://0.0.0.0:8080 took away for security but using the local IP address I get to this

Image

Not sure what I am missing

@wintonzheng
Copy link
Contributor

@TheMindExpansionNetwork Could you open the network tab of your browser and share more of what the network error is?

@devtony10
Copy link

devtony10 commented Feb 28, 2025

error snippet from docker logs below:

litellm.exceptions.BadRequestError: litellm.BadRequestError: AzureException BadRequestError - Unrecognized request argument supplied: max_completion_tokens

It's the same problem I have but with azure, this is the API version I'm using:
model name: gpt-4
model version: turbo-2024-04-09

docker-compose.yml:

  • ENABLE_AZURE=true
  • LLM_KEY=AZURE_OPENAI
  • AZURE_DEPLOYMENT=gpt-4
  • AZURE_API_KEY=xxxx
  • AZURE_API_BASE=https://xxxx.openai.azure.com/
  • AZURE_API_VERSION=2024-08-01-preview

Apparently, for older api versions, max_completion_tokens is not recognized. Please can you make a patch

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants