Revert "add model type to APIs" (#605)

Reverts meta-llama/llama-stack#588

llama_stack/distribution/routers/routers.py

@@ -88,10 +88,9 @@ class InferenceRouter(Inference):
         provider_model_id: Optional[str] = None,
         provider_id: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
-        model_type: Optional[ModelType] = None,
     ) -> None:
         await self.routing_table.register_model(
-            model_id, provider_model_id, provider_id, metadata, model_type
+            model_id, provider_model_id, provider_id, metadata
         )
 
     async def chat_completion(
@@ -106,13 +105,6 @@ class InferenceRouter(Inference):
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
     ) -> AsyncGenerator:
-        model = await self.routing_table.get_model(model_id)
-        if model is None:
-            raise ValueError(f"Model '{model_id}' not found")
-        if model.model_type == ModelType.embedding_model:
-            raise ValueError(
-                f"Model '{model_id}' is an embedding model and does not support chat completions"
-            )
         params = dict(
             model_id=model_id,
             messages=messages,
@@ -139,13 +131,6 @@ class InferenceRouter(Inference):
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
     ) -> AsyncGenerator:
-        model = await self.routing_table.get_model(model_id)
-        if model is None:
-            raise ValueError(f"Model '{model_id}' not found")
-        if model.model_type == ModelType.embedding_model:
-            raise ValueError(
-                f"Model '{model_id}' is an embedding model and does not support chat completions"
-            )
         provider = self.routing_table.get_provider_impl(model_id)
         params = dict(
             model_id=model_id,
@@ -165,13 +150,6 @@ class InferenceRouter(Inference):
         model_id: str,
         contents: List[InterleavedTextMedia],
     ) -> EmbeddingsResponse:
-        model = await self.routing_table.get_model(model_id)
-        if model is None:
-            raise ValueError(f"Model '{model_id}' not found")
-        if model.model_type == ModelType.llm:
-            raise ValueError(
-                f"Model '{model_id}' is an LLM model and does not support embeddings"
-            )
         return await self.routing_table.get_provider_impl(model_id).embeddings(
             model_id=model_id,
             contents=contents,

llama_stack/distribution/routers/routing_tables.py

@@ -209,7 +209,6 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
         provider_model_id: Optional[str] = None,
         provider_id: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
-        model_type: Optional[ModelType] = None,
     ) -> Model:
         if provider_model_id is None:
             provider_model_id = model_id
@@ -223,21 +222,11 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
                 )
         if metadata is None:
             metadata = {}
-        if model_type is None:
-            model_type = ModelType.llm
-        if (
-            "embedding_dimension" not in metadata
-            and model_type == ModelType.embedding_model
-        ):
-            raise ValueError(
-                "Embedding model must have an embedding dimension in its metadata"
-            )
         model = Model(
             identifier=model_id,
             provider_resource_id=provider_model_id,
             provider_id=provider_id,
             metadata=metadata,
-            model_type=model_type,
         )
         registered_model = await self.register_object(model)
         return registered_model
@@ -309,29 +298,16 @@ class MemoryBanksRoutingTable(CommonRoutingTableImpl, MemoryBanks):
                 raise ValueError(
                     "No provider specified and multiple providers available. Please specify a provider_id."
                 )
-        model = await self.get_object_by_identifier("model", params.embedding_model)
-        if model is None:
-            raise ValueError(f"Model {params.embedding_model} not found")
-        if model.model_type != ModelType.embedding_model:
-            raise ValueError(
-                f"Model {params.embedding_model} is not an embedding model"
-            )
-        if "embedding_dimension" not in model.metadata:
-            raise ValueError(
-                f"Model {params.embedding_model} does not have an embedding dimension"
-            )
-        memory_bank_data = {
-            "identifier": memory_bank_id,
-            "type": ResourceType.memory_bank.value,
-            "provider_id": provider_id,
-            "provider_resource_id": provider_memory_bank_id,
-            **params.model_dump(),
-        }
-        if params.memory_bank_type == MemoryBankType.vector.value:
-            memory_bank_data["embedding_dimension"] = model.metadata[
-                "embedding_dimension"
-            ]
-        memory_bank = parse_obj_as(MemoryBank, memory_bank_data)
+        memory_bank = parse_obj_as(
+            MemoryBank,
+            {
+                "identifier": memory_bank_id,
+                "type": ResourceType.memory_bank.value,
+                "provider_id": provider_id,
+                "provider_resource_id": provider_memory_bank_id,
+                **params.model_dump(),
+            },
+        )
         await self.register_object(memory_bank)
         return memory_bank
 

llama_stack/distribution/store/registry.py

@@ -40,7 +40,7 @@ class DistributionRegistry(Protocol):
 
 
 REGISTER_PREFIX = "distributions:registry"
-KEY_VERSION = "v3"
+KEY_VERSION = "v2"
 KEY_FORMAT = f"{REGISTER_PREFIX}:{KEY_VERSION}::" + "{type}:{identifier}"