Merge branch 'main' into add-nvidia-inference-adapter

llama_stack/providers/remote/inference/bedrock/config.py

@@ -4,11 +4,8 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_models.schema_utils import json_schema_type
-
 from llama_stack.providers.utils.bedrock.config import BedrockBaseConfig
 
 
-@json_schema_type
 class BedrockConfig(BedrockBaseConfig):
     pass

llama_stack/providers/remote/inference/tgi/config.py

@@ -37,6 +37,18 @@ class InferenceEndpointImplConfig(BaseModel):
         description="Your Hugging Face user access token (will default to locally saved token if not provided)",
     )
 
+    @classmethod
+    def sample_run_config(
+        cls,
+        endpoint_name: str = "${env.INFERENCE_ENDPOINT_NAME}",
+        api_token: str = "${env.HF_API_TOKEN}",
+        **kwargs,
+    ):
+        return {
+            "endpoint_name": endpoint_name,
+            "api_token": api_token,
+        }
+
 
 @json_schema_type
 class InferenceAPIImplConfig(BaseModel):
@@ -47,3 +59,15 @@ class InferenceAPIImplConfig(BaseModel):
         default=None,
         description="Your Hugging Face user access token (will default to locally saved token if not provided)",
     )
+
+    @classmethod
+    def sample_run_config(
+        cls,
+        repo: str = "${env.INFERENCE_MODEL}",
+        api_token: str = "${env.HF_API_TOKEN}",
+        **kwargs,
+    ):
+        return {
+            "huggingface_repo": repo,
+            "api_token": api_token,
+        }

llama_stack/providers/remote/memory/chroma/chroma.py

@@ -147,9 +147,7 @@ class ChromaMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
         documents: List[MemoryBankDocument],
         ttl_seconds: Optional[int] = None,
     ) -> None:
-        index = self.cache.get(bank_id, None)
-        if not index:
-            raise ValueError(f"Bank {bank_id} not found")
+        index = await self._get_and_cache_bank_index(bank_id)
 
         await index.insert_documents(documents)
 
@@ -159,8 +157,20 @@ class ChromaMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
         query: InterleavedTextMedia,
         params: Optional[Dict[str, Any]] = None,
     ) -> QueryDocumentsResponse:
-        index = self.cache.get(bank_id, None)
-        if not index:
-            raise ValueError(f"Bank {bank_id} not found")
+        index = await self._get_and_cache_bank_index(bank_id)
 
         return await index.query_documents(query, params)
+
+    async def _get_and_cache_bank_index(self, bank_id: str) -> BankWithIndex:
+        if bank_id in self.cache:
+            return self.cache[bank_id]
+
+        bank = await self.memory_bank_store.get_memory_bank(bank_id)
+        if not bank:
+            raise ValueError(f"Bank {bank_id} not found in Llama Stack")
+        collection = await self.client.get_collection(bank_id)
+        if not collection:
+            raise ValueError(f"Bank {bank_id} not found in Chroma")
+        index = BankWithIndex(bank=bank, index=ChromaIndex(self.client, collection))
+        self.cache[bank_id] = index
+        return index

llama_stack/providers/remote/memory/pgvector/pgvector.py

@@ -201,10 +201,7 @@ class PGVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
         documents: List[MemoryBankDocument],
         ttl_seconds: Optional[int] = None,
     ) -> None:
-        index = self.cache.get(bank_id, None)
-        if not index:
-            raise ValueError(f"Bank {bank_id} not found")
-
+        index = await self._get_and_cache_bank_index(bank_id)
         await index.insert_documents(documents)
 
     async def query_documents(
@@ -213,8 +210,17 @@ class PGVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
         query: InterleavedTextMedia,
         params: Optional[Dict[str, Any]] = None,
     ) -> QueryDocumentsResponse:
-        index = self.cache.get(bank_id, None)
-        if not index:
-            raise ValueError(f"Bank {bank_id} not found")
-
+        index = await self._get_and_cache_bank_index(bank_id)
         return await index.query_documents(query, params)
+
+    async def _get_and_cache_bank_index(self, bank_id: str) -> BankWithIndex:
+        if bank_id in self.cache:
+            return self.cache[bank_id]
+
+        bank = await self.memory_bank_store.get_memory_bank(bank_id)
+        index = BankWithIndex(
+            bank=bank,
+            index=PGVectorIndex(bank, ALL_MINILM_L6_V2_DIMENSION, self.cursor),
+        )
+        self.cache[bank_id] = index
+        return index