llama-stack 0.0.42__py3-none-any.whl → 0.3.4__py3-none-any.whl

llama_stack/apis/inspect/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .inspect import *  # noqa: F401 F403
+from .inspect import *

llama_stack/apis/inspect/inspect.py

@@ -4,38 +4,91 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Dict, List, Protocol, runtime_checkable
+from typing import Protocol, runtime_checkable
 
-from llama_models.schema_utils import json_schema_type, webmethod
 from pydantic import BaseModel
 
-
-@json_schema_type
-class ProviderInfo(BaseModel):
-    provider_id: str
-    provider_type: str
+from llama_stack.apis.version import LLAMA_STACK_API_V1
+from llama_stack.providers.datatypes import HealthStatus
+from llama_stack.schema_utils import json_schema_type, webmethod
 
 
 @json_schema_type
 class RouteInfo(BaseModel):
+    """Information about an API route including its path, method, and implementing providers.
+
+    :param route: The API endpoint path
+    :param method: HTTP method for the route
+    :param provider_types: List of provider types that implement this route
+    """
+
     route: str
     method: str
-    provider_types: List[str]
+    provider_types: list[str]
 
 
 @json_schema_type
 class HealthInfo(BaseModel):
-    status: str
-    # TODO: add a provider level status
+    """Health status information for the service.
+
+    :param status: Current health status of the service
+    """
+
+    status: HealthStatus
+
+
+@json_schema_type
+class VersionInfo(BaseModel):
+    """Version information for the service.
+
+    :param version: Version number of the service
+    """
+
+    version: str
+
+
+class ListRoutesResponse(BaseModel):
+    """Response containing a list of all available API routes.
+
+    :param data: List of available route information objects
+    """
+
+    data: list[RouteInfo]
 
 
 @runtime_checkable
 class Inspect(Protocol):
-    @webmethod(route="/providers/list", method="GET")
-    async def list_providers(self) -> Dict[str, ProviderInfo]: ...
+    """Inspect
+
+    APIs for inspecting the Llama Stack service, including health status, available API routes with methods and implementing providers.
+    """
+
+    @webmethod(route="/inspect/routes", method="GET", level=LLAMA_STACK_API_V1)
+    async def list_routes(self) -> ListRoutesResponse:
+        """List routes.
+
+        List all available API routes with their methods and implementing providers.
+
+        :returns: Response containing information about all available routes.
+        """
+        ...
+
+    @webmethod(route="/health", method="GET", level=LLAMA_STACK_API_V1, require_authentication=False)
+    async def health(self) -> HealthInfo:
+        """Get health status.
+
+        Get the current health status of the service.
+
+        :returns: Health information indicating if the service is operational.
+        """
+        ...
+
+    @webmethod(route="/version", method="GET", level=LLAMA_STACK_API_V1, require_authentication=False)
+    async def version(self) -> VersionInfo:
+        """Get version.
 
-    @webmethod(route="/routes/list", method="GET")
-    async def list_routes(self) -> Dict[str, List[RouteInfo]]: ...
+        Get the version of the service.
 
-    @webmethod(route="/health", method="GET")
-    async def health(self) -> HealthInfo: ...
+        :returns: Version information containing the service version number.
+        """
+        ...

llama_stack/apis/models/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .models import *  # noqa: F401 F403
+from .models import *

llama_stack/apis/models/models.py

@@ -4,39 +4,166 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Any, Dict, List, Optional, Protocol, runtime_checkable
+from enum import StrEnum
+from typing import Any, Literal, Protocol, runtime_checkable
 
-from llama_models.schema_utils import json_schema_type, webmethod
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field, field_validator
 
+from llama_stack.apis.resource import Resource, ResourceType
+from llama_stack.apis.version import LLAMA_STACK_API_V1
+from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
+from llama_stack.schema_utils import json_schema_type, webmethod
 
-class ModelDef(BaseModel):
-    identifier: str = Field(
-        description="A unique name for the model type",
-    )
-    llama_model: str = Field(
-        description="Pointer to the underlying core Llama family model. Each model served by Llama Stack must have a core Llama model.",
-    )
-    metadata: Dict[str, Any] = Field(
+
+class CommonModelFields(BaseModel):
+    metadata: dict[str, Any] = Field(
         default_factory=dict,
         description="Any additional metadata for this model",
     )
 
 
 @json_schema_type
-class ModelDefWithProvider(ModelDef):
-    provider_id: str = Field(
-        description="The provider ID for this model",
-    )
+class ModelType(StrEnum):
+    """Enumeration of supported model types in Llama Stack.
+    :cvar llm: Large language model for text generation and completion
+    :cvar embedding: Embedding model for converting text to vector representations
+    """
+
+    llm = "llm"
+    embedding = "embedding"
+
+
+@json_schema_type
+class Model(CommonModelFields, Resource):
+    """A model resource representing an AI model registered in Llama Stack.
+
+    :param type: The resource type, always 'model' for model resources
+    :param model_type: The type of model (LLM or embedding model)
+    :param metadata: Any additional metadata for this model
+    :param identifier: Unique identifier for this resource in llama stack
+    :param provider_resource_id: Unique identifier for this resource in the provider
+    :param provider_id: ID of the provider that owns this resource
+    """
+
+    type: Literal[ResourceType.model] = ResourceType.model
+
+    @property
+    def model_id(self) -> str:
+        return self.identifier
+
+    @property
+    def provider_model_id(self) -> str:
+        assert self.provider_resource_id is not None, "Provider resource ID must be set"
+        return self.provider_resource_id
+
+    model_config = ConfigDict(protected_namespaces=())
+
+    model_type: ModelType = Field(default=ModelType.llm)
+
+    @field_validator("provider_resource_id")
+    @classmethod
+    def validate_provider_resource_id(cls, v):
+        if v is None:
+            raise ValueError("provider_resource_id cannot be None")
+        return v
+
+
+class ModelInput(CommonModelFields):
+    model_id: str
+    provider_id: str | None = None
+    provider_model_id: str | None = None
+    model_type: ModelType | None = ModelType.llm
+    model_config = ConfigDict(protected_namespaces=())
+
+
+class ListModelsResponse(BaseModel):
+    data: list[Model]
+
+
+@json_schema_type
+class OpenAIModel(BaseModel):
+    """A model from OpenAI.
+
+    :id: The ID of the model
+    :object: The object type, which will be "model"
+    :created: The Unix timestamp in seconds when the model was created
+    :owned_by: The owner of the model
+    """
+
+    id: str
+    object: Literal["model"] = "model"
+    created: int
+    owned_by: str
+
+
+class OpenAIListModelsResponse(BaseModel):
+    data: list[OpenAIModel]
 
 
 @runtime_checkable
+@trace_protocol
 class Models(Protocol):
-    @webmethod(route="/models/list", method="GET")
-    async def list_models(self) -> List[ModelDefWithProvider]: ...
+    @webmethod(route="/models", method="GET", level=LLAMA_STACK_API_V1)
+    async def list_models(self) -> ListModelsResponse:
+        """List all models.
+
+        :returns: A ListModelsResponse.
+        """
+        ...
+
+    @webmethod(route="/openai/v1/models", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
+    async def openai_list_models(self) -> OpenAIListModelsResponse:
+        """List models using the OpenAI API.
+
+        :returns: A OpenAIListModelsResponse.
+        """
+        ...
+
+    @webmethod(route="/models/{model_id:path}", method="GET", level=LLAMA_STACK_API_V1)
+    async def get_model(
+        self,
+        model_id: str,
+    ) -> Model:
+        """Get model.
+
+        Get a model by its identifier.
+
+        :param model_id: The identifier of the model to get.
+        :returns: A Model.
+        """
+        ...
+
+    @webmethod(route="/models", method="POST", level=LLAMA_STACK_API_V1)
+    async def register_model(
+        self,
+        model_id: str,
+        provider_model_id: str | None = None,
+        provider_id: str | None = None,
+        metadata: dict[str, Any] | None = None,
+        model_type: ModelType | None = None,
+    ) -> Model:
+        """Register model.
+
+        Register a model.
+
+        :param model_id: The identifier of the model to register.
+        :param provider_model_id: The identifier of the model in the provider.
+        :param provider_id: The identifier of the provider.
+        :param metadata: Any additional metadata for this model.
+        :param model_type: The type of model to register.
+        :returns: A Model.
+        """
+        ...
+
+    @webmethod(route="/models/{model_id:path}", method="DELETE", level=LLAMA_STACK_API_V1)
+    async def unregister_model(
+        self,
+        model_id: str,
+    ) -> None:
+        """Unregister model.
 
-    @webmethod(route="/models/get", method="GET")
-    async def get_model(self, identifier: str) -> Optional[ModelDefWithProvider]: ...
+        Unregister a model.
 
-    @webmethod(route="/models/register", method="POST")
-    async def register_model(self, model: ModelDefWithProvider) -> None: ...
+        :param model_id: The identifier of the model to unregister.
+        """
+        ...

llama_stack/apis/post_training/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .post_training import *  # noqa: F401 F403
+from .post_training import *