Further generalize Xi's changes

- introduce a slightly more general notion of an AutoRouted provider
- the AutoRouted provider is associated with a RoutingTable provider
- e.g. inference -> models
- Introduced safety -> shields and memory -> memory_banks
  correspondences

llama_stack/apis/memory_banks/__init__.py

@@ -0,0 +1,7 @@
+# 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.
+
+from .memory_banks import *  # noqa: F401 F403

llama_stack/apis/memory_banks/client.py

@@ -0,0 +1,67 @@
+# 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 asyncio
+
+from typing import List, Optional
+
+import fire
+import httpx
+from termcolor import cprint
+
+from .memory_banks import *  # noqa: F403
+
+
+class MemoryBanksClient(MemoryBanks):
+    def __init__(self, base_url: str):
+        self.base_url = base_url
+
+    async def initialize(self) -> None:
+        pass
+
+    async def shutdown(self) -> None:
+        pass
+
+    async def list_memory_banks(self) -> List[MemoryBankSpec]:
+        async with httpx.AsyncClient() as client:
+            response = await client.get(
+                f"{self.base_url}/memory_banks/list",
+                headers={"Content-Type": "application/json"},
+            )
+            response.raise_for_status()
+            return [MemoryBankSpec(**x) for x in response.json()]
+
+    async def get_memory_bank(
+        self, bank_type: MemoryBankType
+    ) -> Optional[MemoryBankSpec]:
+        async with httpx.AsyncClient() as client:
+            response = await client.get(
+                f"{self.base_url}/memory_banks/get",
+                json={
+                    "bank_type": bank_type,
+                },
+                headers={"Content-Type": "application/json"},
+            )
+            response.raise_for_status()
+            j = response.json()
+            if j is None:
+                return None
+            return MemoryBankSpec(**j)
+
+
+async def run_main(host: str, port: int, stream: bool):
+    client = MemoryBanksClient(f"http://{host}:{port}")
+
+    response = await client.list_memory_banks()
+    cprint(f"list_memory_banks response={response}", "green")
+
+
+def main(host: str, port: int, stream: bool = True):
+    asyncio.run(run_main(host, port, stream))
+
+
+if __name__ == "__main__":
+    fire.Fire(main)

llama_stack/apis/memory_banks/memory_banks.py

@@ -0,0 +1,32 @@
+# 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.
+
+from typing import List, Optional, Protocol
+
+from llama_memory_banks.schema_utils import json_schema_type, webmethod
+from pydantic import BaseModel, Field
+
+from llama_stack.apis.memory import MemoryBankType
+
+from llama_stack.distribution.datatypes import GenericProviderConfig
+
+
+@json_schema_type
+class MemoryBankSpec(BaseModel):
+    bank_type: MemoryBankType
+    provider_config: GenericProviderConfig = Field(
+        description="Provider config for the model, including provider_id, and corresponding config. ",
+    )
+
+
+class MemoryBanks(Protocol):
+    @webmethod(route="/memory_banks/list", method="GET")
+    async def list_memory_banks(self) -> List[MemoryBankSpec]: ...
+
+    @webmethod(route="/memory_banks/get", method="GET")
+    async def get_memory_bank(
+        self, bank_type: MemoryBankType
+    ) -> Optional[MemoryBankSpec]: ...