RAG Quick start Fails

[arunhari82]

I am following the documentation from https://llama-stack.readthedocs.io/en/latest/getting_started/index.html#your-first-rag-agent

Looks like llama-stack-server when run with docker file has issues with latest run.yaml changes.086174

llama_stack_client.BadRequestError: Error code: 400 - {'detail': 'Invalid value: Embeddings are now served via Inference providers. Please upgrade your run.yaml to include inline::sentence-transformer as an additional inference provider. See https://github.com/meta-llama/llama-stack/blob/main/llama_stack/templates/together/run.yaml

any pointers ?

[terrytangyuan]

The error message looks pretty straightforward. Have you tried it?

[arunhari82]

Please let me how to update the run.yaml as it's inside the container image.

[terrytangyuan]

You can rebuild the image or mounting a new one to your container