llama-stack-mirror/llama_stack/distribution/routing_tables/models.py
grs 7c1998db25
feat: fine grained access control policy (#2264)
This allows a set of rules to be defined for determining access to
resources. The rules are (loosely) based on the cedar policy format.

A rule defines a list of action either to permit or to forbid. It may
specify a principal or a resource that must match for the rule to take
effect. It may also specify a condition, either a 'when' or an 'unless',
with additional constraints as to where the rule applies.

A list of rules is held for each type to be protected and tried in order
to find a match. If a match is found, the request is permitted or
forbidden depening on the type of rule. If no match is found, the
request is denied. If no rules are specified for a given type, a rule
that allows any action as long as the resource attributes match the user
attributes is added (i.e. the previous behaviour is the default.

Some examples in yaml:

```
    model:
    - permit:
      principal: user-1
      actions: [create, read, delete]
      comment: user-1 has full access to all models
    - permit:
      principal: user-2
      actions: [read]
      resource: model-1
      comment: user-2 has read access to model-1 only
    - permit:
      actions: [read]
      when:
        user_in: resource.namespaces
      comment: any user has read access to models with matching attributes
    vector_db:
    - forbid:
      actions: [create, read, delete]
      unless:
        user_in: role::admin
      comment: only user with admin role can use vector_db resources
```

---------

Signed-off-by: Gordon Sim <gsim@redhat.com>
2025-06-03 14:51:12 -07:00

82 lines
3.1 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import time
from typing import Any
from llama_stack.apis.models import ListModelsResponse, Model, Models, ModelType, OpenAIListModelsResponse, OpenAIModel
from llama_stack.distribution.datatypes import (
ModelWithOwner,
)
from llama_stack.log import get_logger
from .common import CommonRoutingTableImpl
logger = get_logger(name=__name__, category="core")
class ModelsRoutingTable(CommonRoutingTableImpl, Models):
async def list_models(self) -> ListModelsResponse:
return ListModelsResponse(data=await self.get_all_with_type("model"))
async def openai_list_models(self) -> OpenAIListModelsResponse:
models = await self.get_all_with_type("model")
openai_models = [
OpenAIModel(
id=model.identifier,
object="model",
created=int(time.time()),
owned_by="llama_stack",
)
for model in models
]
return OpenAIListModelsResponse(data=openai_models)
async def get_model(self, model_id: str) -> Model:
model = await self.get_object_by_identifier("model", model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
return model
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:
if provider_model_id is None:
provider_model_id = model_id
if provider_id is None:
# If provider_id not specified, use the only provider if it supports this model
if len(self.impls_by_provider_id) == 1:
provider_id = list(self.impls_by_provider_id.keys())[0]
else:
raise ValueError(
f"No provider specified and multiple providers available. Please specify a provider_id. Available providers: {self.impls_by_provider_id.keys()}"
)
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:
raise ValueError("Embedding model must have an embedding dimension in its metadata")
model = ModelWithOwner(
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
async def unregister_model(self, model_id: str) -> None:
existing_model = await self.get_model(model_id)
if existing_model is None:
raise ValueError(f"Model {model_id} not found")
await self.unregister_object(existing_model)