fix weaviate, update run.yamls

llama_stack/distribution/templates/docker/llamastack-local-cpu/run.yaml

@@ -40,19 +40,3 @@ providers:
   - provider_id: meta-reference
     provider_type: meta-reference
     config: {}
-models:
-- identifier: Llama3.1-8B-Instruct
-  llama_model: Llama3.1-8B-Instruct
-  provider_id: remote::ollama
-shields:
-- identifier: llama_guard
-  type: llama_guard
-  provider_id: meta-reference
-  params: {}
-memory_banks:
-- identifier: vector
-  provider_id: meta-reference
-  type: vector
-  embedding_model: all-MiniLM-L6-v2
-  chunk_size_in_tokens: 512
-  overlap_size_in_tokens: null

llama_stack/distribution/templates/docker/llamastack-local-gpu/run.yaml

@@ -43,19 +43,3 @@ providers:
   - provider_id: meta-reference
     provider_type: meta-reference
     config: {}
-models:
-- identifier: Llama3.1-8B-Instruct
-  llama_model: Llama3.1-8B-Instruct
-  provider_id: meta-reference
-shields:
-- identifier: llama_guard
-  type: llama_guard
-  provider_id: meta-reference
-  params: {}
-memory_banks:
-- identifier: vector
-  provider_id: meta-reference
-  type: vector
-  embedding_model: all-MiniLM-L6-v2
-  chunk_size_in_tokens: 512
-  overlap_size_in_tokens: null

llama_stack/providers/adapters/memory/weaviate/weaviate.py

@@ -14,6 +14,7 @@ from weaviate.classes.init import Auth
 
 from llama_stack.apis.memory import *  # noqa: F403
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.providers.datatypes import MemoryBanksProtocolPrivate
 from llama_stack.providers.utils.memory.vector_store import (
     BankWithIndex,
     EmbeddingIndex,
@@ -78,7 +79,9 @@ class WeaviateIndex(EmbeddingIndex):
         return QueryDocumentsResponse(chunks=chunks, scores=scores)
 
 
-class WeaviateMemoryAdapter(Memory, NeedsRequestProviderData):
+class WeaviateMemoryAdapter(
+    Memory, NeedsRequestProviderData, MemoryBanksProtocolPrivate
+):
     def __init__(self, config: WeaviateConfig) -> None:
         self.config = config
         self.client_cache = {}
@@ -136,6 +139,9 @@ class WeaviateMemoryAdapter(Memory, NeedsRequestProviderData):
         )
         self.cache[memory_bank.identifier] = index
 
+    async def list_memory_banks(self) -> List[MemoryBankDef]:
+        return [i.bank for i in self.cache.values()]
+
     async def _get_and_cache_bank_index(self, bank_id: str) -> Optional[BankWithIndex]:
         if bank_id in self.cache:
             return self.cache[bank_id]

tests/examples/local-run.yaml

@@ -48,19 +48,3 @@ providers:
   - provider_id: meta-reference
     provider_type: meta-reference
     config: {}
-models:
-- identifier: Llama3.1-8B-Instruct
-  llama_model: Llama3.1-8B-Instruct
-  provider_id: meta-reference
-shields:
-- identifier: llama_guard
-  type: llama_guard
-  provider_id: meta-reference
-  params: {}
-memory_banks:
-- identifier: vector
-  provider_id: meta-reference
-  type: vector
-  embedding_model: all-MiniLM-L6-v2
-  chunk_size_in_tokens: 512
-  overlap_size_in_tokens: null