Skip to content

Conversation

@cdoern
Copy link
Collaborator

@cdoern cdoern commented Apr 8, 2025

What does this PR do?

add v1/providers/ client handling which uses PUT to allow users to change their provider configuration

this is a follow up to #1429 and related to #1359

a user can call something like:

llama_stack_client.providers.update(api="inference", provider_id="ollama", provider_type="remote::ollama", config={'url': 'http:/localhost:12345'})

or

llama-stack-client providers update inference ollama remote::ollama "{'url': 'http://localhost:12345'}"

this API works by adding a RequestMiddleware to the server which checks requests, and if the user is using PUT /v1/providers, the routes are re-registered with the re-initialized provider configurations/methods

Test Plan

see llamastack/llama-stack#1905

add v1/providers/ client handling which uses PUT to allow users to change their provider configuration

this is a follow up to #1429 and related to #1359

a user can call something like:

llama_stack_client.providers.update(api="inference", provider_id="ollama", provider_type="remote::ollama", config={'url': 'http:/localhost:12345'})

or

llama-stack-client providers update inference ollama remote::ollama "{'url': 'http://localhost:12345'}"

this API works by adding a RequestMiddleware to the server which checks requests, and if the user is using PUT /v1/providers, the routes are re-registered with the re-initialized provider configurations/methods

Signed-off-by: Charlie Doern <cdoern@redhat.com>
@nathan-weinberg
Copy link

@cdoern you're going to want to close this and reopen it in https://github.com/llamastack/llama-stack-client-python

@cdoern cdoern closed this Sep 18, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants