phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

adding back relevant vector_db files

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

fix tests

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

updating tests and fixing routing logic for single provider

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

setting default provider to update tests

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

updated provider_id

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

updated VectorStoreConfig to use (provider_id, embedding_model_id) and add defautl vector store provider

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 2025-10-17 16:24:15 -04:00
parent accc4c437e
commit b3addc94d1
23 changed files with 637 additions and 261 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/core/stack.py
View file

@ -135,7 +135,7 @@ async def validate_vector_stores_config(run_config: StackRunConfig, impls: dict[
return
vector_stores_config = run_config.vector_stores
default_model_id = vector_stores_config.default_embedding_model_id
default_model_id = vector_stores_config.embedding_model_id
if Api.models not in impls:
raise ValueError(f"Models API is not available but vector_stores config requires model '{default_model_id}'")