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

peculiar error from ellama-translate #104

Open
oatmealm opened this issue Apr 7, 2024 · 4 comments
Open

peculiar error from ellama-translate #104

oatmealm opened this issue Apr 7, 2024 · 4 comments

Comments

@oatmealm
Copy link

oatmealm commented Apr 7, 2024

I'm seeing this error when trying to translate selection. API calls are proxied via litellm so I can see there was no outgoing call. Seems to be happening when content is parse before the API call.... all other functions work

@s-kostyaev
Copy link
Owner

Show your configuration please (remove keys before sharing).

@oatmealm
Copy link
Author

oatmealm commented Apr 8, 2024

The error echoed to the mini-buffer is "peculiar problem" literary, I forgot to mention that.

  (setopt ellama-provider
          (make-llm-openai-compatible
           :url "http://localhost:4000"
           :key "some=key"  
           :chat-model "some-mode"
           :embedding-model "some-embeding-model"))

Everything works except for ellama-translate and ellama-translate-buffer. There's also not api access, looking at litellm active log. Other commands, such as ellama-define-word or general queries with ellama-chat etc. seem to work fine.

@oatmealm
Copy link
Author

oatmealm commented Apr 10, 2024

Tried directly with olllama using gemma, same error. debug-on-error is set but not catching any errors.

#s(llm-ollama "http" "localhost" 11434 "gemma:latest" "nomic-embed-text:latest")

@s-kostyaev
Copy link
Owner

@oatmealm try to change your config to:

  (setopt ellama-provider
          (make-llm-openai-compatible
           :url "http://localhost:4000/v1/"
           :key "some=key"  
           :chat-model "some-mode"
           :embedding-model "some-embeding-model"))

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

2 participants