diff --git a/llama_stack/providers/inline/memory/faiss/config.py b/llama_stack/providers/inline/memory/faiss/config.py index d82104477..00b387607 100644 --- a/llama_stack/providers/inline/memory/faiss/config.py +++ b/llama_stack/providers/inline/memory/faiss/config.py @@ -20,7 +20,7 @@ class FaissImplConfig(BaseModel): kvstore: KVStoreConfig @classmethod - def sample_run_config(cls, __distro_dir__: str) -> Dict[str, Any]: + def sample_run_config(cls, __distro_dir__: str = "runtime") -> Dict[str, Any]: return { "kvstore": SqliteKVStoreConfig.sample_run_config( __distro_dir__=__distro_dir__, diff --git a/llama_stack/templates/together/run.yaml b/llama_stack/templates/together/run.yaml index d151c96c4..07aeb62f3 100644 --- a/llama_stack/templates/together/run.yaml +++ b/llama_stack/templates/together/run.yaml @@ -25,13 +25,7 @@ providers: kvstore: type: sqlite namespace: null - db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/faiss_store.db - - provider_id: chromadb - provider_type: remote::chromadb - config: {} - - provider_id: pgvector - provider_type: remote::pgvector - config: {} + db_path: ${env.SQLITE_STORE_DIR:~/.llama/runtime}/faiss_store.db safety: - provider_id: llama-guard provider_type: inline::llama-guard diff --git a/llama_stack/templates/together/together.py b/llama_stack/templates/together/together.py index c33a5b4e7..0ea9deefe 100644 --- a/llama_stack/templates/together/together.py +++ b/llama_stack/templates/together/together.py @@ -9,6 +9,7 @@ from pathlib import Path from llama_models.sku_list import all_registered_models from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput +from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig from llama_stack.providers.remote.inference.together import TogetherImplConfig from llama_stack.providers.remote.inference.together.together import MODEL_ALIASES @@ -32,6 +33,11 @@ def get_distribution_template() -> DistributionTemplate: provider_type="remote::together", config=TogetherImplConfig.sample_run_config(), ) + memory_provider = Provider( + provider_id="faiss", + provider_type="inline::faiss", + config=FaissImplConfig.sample_run_config(), + ) core_model_to_hf_repo = { m.descriptor(): m.huggingface_repo for m in all_registered_models() @@ -56,6 +62,7 @@ def get_distribution_template() -> DistributionTemplate: "run.yaml": RunConfigSettings( provider_overrides={ "inference": [inference_provider], + "memory": [memory_provider], }, default_models=default_models, default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],