phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 23:52:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update resolver to only pass vector_stores section of run config

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

Using Router only from VectorDBs

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

removing model_api from vector store providers

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

fix test

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

updating integration tests

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

special handling for replay mode for available providers

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-10-16 10:59:01 -04:00
parent 24a1430c8b
commit accc4c437e
46 changed files with 397 additions and 702 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/core/resolver.py
View file

@ -409,10 +409,6 @@ async def instantiate_provider(
if "telemetry_enabled" in inspect.signature(getattr(module, method)).parameters and run_config.telemetry:
args.append(run_config.telemetry.enabled)
# vector_io providers need access to run_config.vector_stores
if provider_spec.api == Api.vector_io and "run_config" in inspect.signature(getattr(module, method)).parameters:
args.append(run_config)
fn = getattr(module, method)
impl = await fn(*args)
impl.__provider_id__ = provider.provider_id