-
Notifications
You must be signed in to change notification settings - Fork 15
Fix provider llm sample #382
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
Conversation
samples/managed-llm/compose.yaml
Outdated
environment: | ||
- ENDPOINT_URL=http://llm/api/v1/chat/completions # endpoint to the gateway service | ||
- MODEL=anthropic.claude-3-haiku-20240307-v1:0 # LLM model ID used for the gateway | ||
- MODEL=us.amazon.nova-micro-v1:0 # LLM model ID used for the gateway |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's use a cloud-agnostic model.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
so either a (hidden) default or llama
or mistral
. (Llama is cheaper than Mistral.)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yeah I think ai/llama3.2
is available everywhere
be mindful of changes in #378, where the whole |
Changing the
managed-llm-provider
sample to use the "generated" environment variables,<service>_URL
and<service>_MODEL
.This needs DefangLabs/defang#1194 to work.
Samples Checklist
✅ All good!