phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 14:58:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: implement provider updating

Browse source 
add `v1/providers/` 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

for the client, `self.impls` is updated to hold the proper methods+configurations

this depends on a client PR, the CI will fail until then but succeeded locally

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-04-04 15:53:21 -04:00
parent d165000bbc
commit 436f8ade9e
8 changed files with 449 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/distribution/server/routes.py
View file

@ -62,6 +62,8 @@ def get_all_api_routes() -> dict[Api, list[Route]]:
http_method = hdrs.METH_GET
elif webmethod.method == hdrs.METH_DELETE:
http_method = hdrs.METH_DELETE
elif webmethod.method == hdrs.METH_PUT:
http_method = hdrs.METH_PUT
else:
http_method = hdrs.METH_POST
routes.append(