mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-24 00:47:00 +00:00
**This PR changes configurations in a backward incompatible way.**
Run configs today repeat full SQLite/Postgres snippets everywhere a
store is needed, which means duplicated credentials, extra connection
pools, and lots of drift between files. This PR introduces named storage
backends so the stack and providers can share a single catalog and
reference those backends by name.
## Key Changes
- Add `storage.backends` to `StackRunConfig`, register each KV/SQL
backend once at startup, and validate that references point to the right
family.
- Move server stores under `storage.stores` with lightweight references
(backend + namespace/table) instead of full configs.
- Update every provider/config/doc to use the new reference style;
docs/codegen now surface the simplified YAML.
## Migration
Before:
```yaml
metadata_store:
type: sqlite
db_path: ~/.llama/distributions/foo/registry.db
inference_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
conversations_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
```
After:
```yaml
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ~/.llama/distributions/foo/kvstore.db
sql_default:
type: sql_postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
stores:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
max_write_queue_size: 10000
num_writers: 4
conversations:
backend: sql_default
table_name: openai_conversations
```
Provider configs follow the same pattern—for example, a Chroma vector
adapter switches from:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
kvstore:
type: sqlite
db_path: ~/.llama/distributions/foo/chroma.db
```
to:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
persistence:
backend: kv_default
namespace: vector_io::chroma_remote
```
Once the backends are declared, everything else just points at them, so
rotating credentials or swapping to Postgres happens in one place and
the stack reuses a single connection pool.
152 lines
5.1 KiB
Python
152 lines
5.1 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 inspect
|
|
import sys
|
|
from typing import Any, Protocol
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.apis.inference import Inference
|
|
from llama_stack.core.datatypes import Api, Provider, StackRunConfig
|
|
from llama_stack.core.resolver import resolve_impls
|
|
from llama_stack.core.routers.inference import InferenceRouter
|
|
from llama_stack.core.routing_tables.models import ModelsRoutingTable
|
|
from llama_stack.core.storage.datatypes import (
|
|
InferenceStoreReference,
|
|
KVStoreReference,
|
|
ServerStoresConfig,
|
|
SqliteKVStoreConfig,
|
|
SqliteSqlStoreConfig,
|
|
SqlStoreReference,
|
|
StorageConfig,
|
|
)
|
|
from llama_stack.providers.datatypes import InlineProviderSpec, ProviderSpec
|
|
from llama_stack.providers.utils.kvstore import register_kvstore_backends
|
|
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
|
|
|
|
|
def add_protocol_methods(cls: type, protocol: type[Protocol]) -> None:
|
|
"""Dynamically add protocol methods to a class by inspecting the protocol."""
|
|
for name, value in inspect.getmembers(protocol):
|
|
if inspect.isfunction(value) and hasattr(value, "__webmethod__"):
|
|
# Get the signature
|
|
sig = inspect.signature(value)
|
|
|
|
# Create an async function with the same signature that returns a MagicMock
|
|
async def mock_impl(*args, **kwargs):
|
|
return MagicMock()
|
|
|
|
# Set the signature on our mock implementation
|
|
mock_impl.__signature__ = sig
|
|
# Add it to the class
|
|
setattr(cls, name, mock_impl)
|
|
|
|
|
|
class SampleConfig(BaseModel):
|
|
foo: str = Field(
|
|
default="bar",
|
|
description="foo",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
|
|
return {
|
|
"foo": "baz",
|
|
}
|
|
|
|
|
|
class SampleImpl:
|
|
def __init__(self, config: SampleConfig, deps: dict[Api, Any], provider_spec: ProviderSpec = None):
|
|
self.__provider_id__ = "test_provider"
|
|
self.__provider_spec__ = provider_spec
|
|
self.__provider_config__ = config
|
|
self.__deps__ = deps
|
|
self.foo = config.foo
|
|
|
|
async def initialize(self):
|
|
pass
|
|
|
|
|
|
def make_run_config(**overrides) -> StackRunConfig:
|
|
storage = overrides.pop(
|
|
"storage",
|
|
StorageConfig(
|
|
backends={
|
|
"kv_default": SqliteKVStoreConfig(db_path=":memory:"),
|
|
"sql_default": SqliteSqlStoreConfig(db_path=":memory:"),
|
|
},
|
|
stores=ServerStoresConfig(
|
|
metadata=KVStoreReference(backend="kv_default", namespace="registry"),
|
|
inference=InferenceStoreReference(backend="sql_default", table_name="inference_store"),
|
|
conversations=SqlStoreReference(backend="sql_default", table_name="conversations"),
|
|
),
|
|
),
|
|
)
|
|
register_kvstore_backends({name: cfg for name, cfg in storage.backends.items() if cfg.type.value.startswith("kv_")})
|
|
register_sqlstore_backends(
|
|
{name: cfg for name, cfg in storage.backends.items() if cfg.type.value.startswith("sql_")}
|
|
)
|
|
defaults = dict(
|
|
image_name="test_image",
|
|
apis=[],
|
|
providers={},
|
|
storage=storage,
|
|
)
|
|
defaults.update(overrides)
|
|
return StackRunConfig(**defaults)
|
|
|
|
|
|
async def test_resolve_impls_basic():
|
|
# Create a real provider spec
|
|
provider_spec = InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="sample",
|
|
module="test_module",
|
|
config_class="test_resolver.SampleConfig",
|
|
api_dependencies=[],
|
|
)
|
|
|
|
# Create provider registry with our provider
|
|
provider_registry = {Api.inference: {provider_spec.provider_type: provider_spec}}
|
|
|
|
run_config = make_run_config(
|
|
image_name="test_image",
|
|
providers={
|
|
"inference": [
|
|
Provider(
|
|
provider_id="sample_provider",
|
|
provider_type="sample",
|
|
config=SampleConfig.sample_run_config(),
|
|
)
|
|
]
|
|
},
|
|
)
|
|
|
|
dist_registry = MagicMock()
|
|
|
|
mock_module = MagicMock()
|
|
impl = SampleImpl(SampleConfig(foo="baz"), {}, provider_spec)
|
|
add_protocol_methods(SampleImpl, Inference)
|
|
|
|
mock_module.get_provider_impl = AsyncMock(return_value=impl)
|
|
mock_module.get_provider_impl.__text_signature__ = "()"
|
|
sys.modules["test_module"] = mock_module
|
|
|
|
impls = await resolve_impls(run_config, provider_registry, dist_registry, policy={})
|
|
|
|
assert Api.inference in impls
|
|
assert isinstance(impls[Api.inference], InferenceRouter)
|
|
|
|
table = impls[Api.inference].routing_table
|
|
assert isinstance(table, ModelsRoutingTable)
|
|
|
|
impl = table.impls_by_provider_id["sample_provider"]
|
|
assert isinstance(impl, SampleImpl)
|
|
assert impl.foo == "baz"
|
|
assert impl.__provider_id__ == "sample_provider"
|
|
assert impl.__provider_spec__ == provider_spec
|