phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 20:12:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

simplified some, walked back some decisions

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-17 10:05:07 -07:00
parent af7472cdb0
commit 636764c2a1
90 changed files with 887 additions and 570 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/core/conversations/conversations.py
View file

@ -55,10 +55,10 @@ class ConversationServiceImpl(Conversations):
self.deps = deps
self.policy = config.policy
# Use conversations store reference from storage config
conversations_ref = config.run_config.storage.conversations
# Use conversations store reference from run config
conversations_ref = config.run_config.conversations_store
if not conversations_ref:
raise ValueError("storage.conversations must be configured in run config")
raise ValueError("conversations_store must be configured in run config")
base_sql_store = sqlstore_impl(conversations_ref)
self.sql_store = AuthorizedSqlStore(base_sql_store, self.policy)

66
llama_stack/core/datatypes.py
View file

@ -26,7 +26,13 @@ from llama_stack.apis.tools import ToolGroup, ToolGroupInput, ToolRuntime
from llama_stack.apis.vector_dbs import VectorDB, VectorDBInput
from llama_stack.apis.vector_io import VectorIO
from llama_stack.core.access_control.datatypes import AccessRule
from llama_stack.core.storage.datatypes import KVStoreReference, StorageConfig
from llama_stack.core.storage.datatypes import (
InferenceStoreReference,
KVStoreReference,
SqlStoreReference,
StorageBackendType,
StorageConfig,
)
from llama_stack.providers.datatypes import Api, ProviderSpec
LLAMA_STACK_BUILD_CONFIG_VERSION = 2
@ -464,10 +470,19 @@ can be instantiated multiple times (with different configs) if necessary.
""",
)
storage: StorageConfig = Field(
description="""
Storage backend configurations. Each backend is named, and can be referenced by various components
throughout the Stack (both by its core as well as providers).
""",
description="Catalog of named storage backends available to the stack",
)
metadata_store: KVStoreReference | None = Field(
default=None,
description="Reference to the KV store backend used by the distribution registry (kv_* backend).",
)
inference_store: InferenceStoreReference | None = Field(
default=None,
description="Reference to the SQL store backend used by the inference API (sql_* backend).",
)
conversations_store: SqlStoreReference | None = Field(
default=None,
description="Reference to the SQL store backend used by the conversations API (sql_* backend).",
)
# registry of "resources" in the distribution
@ -507,6 +522,47 @@ throughout the Stack (both by its core as well as providers).
return Path(v)
return v
@model_validator(mode="after")
def validate_storage_references(self) -> "StackRunConfig":
backend_map = self.storage.backends if self.storage else {}
kv_backends = {
name
for name, cfg in backend_map.items()
if cfg.type
in {
StorageBackendType.KV_REDIS,
StorageBackendType.KV_SQLITE,
StorageBackendType.KV_POSTGRES,
StorageBackendType.KV_MONGODB,
}
}
sql_backends = {
name
for name, cfg in backend_map.items()
if cfg.type in {StorageBackendType.SQL_SQLITE, StorageBackendType.SQL_POSTGRES}
}
def _ensure_backend(reference, expected_set, store_name: str) -> None:
if reference is None:
return
backend_name = reference.backend
if backend_name not in backend_map:
raise ValueError(
f"{store_name} references unknown backend '{backend_name}'. "
f"Available backends: {sorted(backend_map)}"
)
if backend_name not in expected_set:
raise ValueError(
f"{store_name} references backend '{backend_name}' of type "
f"'{backend_map[backend_name].type.value}', but a backend of type "
f"{'kv_*' if expected_set is kv_backends else 'sql_*'} is required."
)
_ensure_backend(self.metadata_store, kv_backends, "metadata_store")
_ensure_backend(self.inference_store, sql_backends, "inference_store")
_ensure_backend(self.conversations_store, sql_backends, "conversations_store")
return self
class BuildConfig(BaseModel):
version: int = LLAMA_STACK_BUILD_CONFIG_VERSION

9
llama_stack/core/prompts/prompts.py
View file

@ -41,11 +41,10 @@ class PromptServiceImpl(Prompts):
async def initialize(self) -> None:
# Use metadata store backend with prompts-specific namespace
metadata_ref = self.config.run_config.storage.metadata
prompts_ref = KVStoreReference(
namespace="prompts",
backend=metadata_ref.backend if metadata_ref else None,
)
metadata_ref = self.config.run_config.metadata_store
if not metadata_ref:
raise ValueError("metadata_store must be configured in run config")
prompts_ref = KVStoreReference(namespace="prompts", backend=metadata_ref.backend)
self.kvstore = await kvstore_impl(prompts_ref)
def _get_default_key(self, prompt_id: str) -> str:

4
llama_stack/core/routers/__init__.py
View file

@ -80,9 +80,9 @@ async def get_auto_router_impl(
# TODO: move pass configs to routers instead
if api == Api.inference:
inference_ref = run_config.storage.inference
inference_ref = run_config.inference_store
if not inference_ref:
raise ValueError("storage.inference must be configured in run config")
raise ValueError("inference_store must be configured in run config")
inference_store = InferenceStore(
reference=inference_ref,

18
llama_stack/core/server/quota.py
View file

@ -10,10 +10,10 @@ from datetime import UTC, datetime, timedelta
from starlette.types import ASGIApp, Receive, Scope, Send
from llama_stack.core.storage.datatypes import KVStoreReference, StorageBackendType
from llama_stack.log import get_logger
from llama_stack.providers.utils.kvstore.api import KVStore
from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
from llama_stack.providers.utils.kvstore.kvstore import kvstore_impl
from llama_stack.providers.utils.kvstore.kvstore import _KVSTORE_BACKENDS, kvstore_impl
logger = get_logger(name=__name__, category="core::server")
@ -33,7 +33,7 @@ class QuotaMiddleware:
def __init__(
self,
app: ASGIApp,
kv_config: KVStoreConfig,
kv_config: KVStoreReference,
anonymous_max_requests: int,
authenticated_max_requests: int,
window_seconds: int = 86400,
@ -45,15 +45,15 @@ class QuotaMiddleware:
self.authenticated_max_requests = authenticated_max_requests
self.window_seconds = window_seconds
if isinstance(self.kv_config, SqliteKVStoreConfig):
logger.warning(
"QuotaMiddleware: Using SQLite backend. Expiry/TTL is not enforced; cleanup is manual. "
f"window_seconds={self.window_seconds}"
)
async def _get_kv(self) -> KVStore:
if self.kv is None:
self.kv = await kvstore_impl(self.kv_config)
backend_config = _KVSTORE_BACKENDS.get(self.kv_config.backend)
if backend_config and backend_config.type == StorageBackendType.KV_SQLITE:
logger.warning(
"QuotaMiddleware: Using SQLite backend. Expiry/TTL is not enforced; cleanup is manual. "
f"window_seconds={self.window_seconds}"
)
return self.kv
async def __call__(self, scope: Scope, receive: Receive, send: Send):

4
llama_stack/core/stack.py
View file

@ -368,7 +368,9 @@ class Stack:
logger.info(f"API recording enabled: mode={os.environ.get('LLAMA_STACK_TEST_INFERENCE_MODE')}")
_initialize_storage(self.run_config)
dist_registry, _ = await create_dist_registry(self.run_config.storage, self.run_config.image_name)
if not self.run_config.metadata_store:
raise ValueError("metadata_store must be configured with a kv_* backend")
dist_registry, _ = await create_dist_registry(self.run_config.metadata_store, self.run_config.image_name)
policy = self.run_config.server.auth.access_policy if self.run_config.server.auth else []
internal_impls = {}

41
llama_stack/core/storage/datatypes.py
View file

@ -27,10 +27,6 @@ class CommonConfig(BaseModel):
default=None,
description="All keys will be prefixed with this namespace",
)
default: bool = Field(
default=False,
description="Mark this KV store as the default choice when a reference omits the backend name",
)
class RedisKVStoreConfig(CommonConfig):
@ -143,13 +139,6 @@ class MongoDBKVStoreConfig(CommonConfig):
}
class CommonSqlStoreConfig(BaseModel):
default: bool = Field(
default=False,
description="Mark this SQL store as the default choice when a reference omits the backend name",
)
class SqlAlchemySqlStoreConfig(BaseModel):
@property
@abstractmethod
@ -161,7 +150,7 @@ class SqlAlchemySqlStoreConfig(BaseModel):
return ["sqlalchemy[asyncio]"]
class SqliteSqlStoreConfig(SqlAlchemySqlStoreConfig, CommonSqlStoreConfig):
class SqliteSqlStoreConfig(SqlAlchemySqlStoreConfig):
type: Literal[StorageBackendType.SQL_SQLITE] = StorageBackendType.SQL_SQLITE
db_path: str = Field(
description="Database path, e.g. ~/.llama/distributions/ollama/sqlstore.db",
@ -219,9 +208,8 @@ class SqlStoreReference(BaseModel):
description="Name of the table to use for the SqlStore",
)
backend: str | None = Field(
description="Name of backend from persistence.backends, a default will be used if not specified",
default=None,
backend: str = Field(
description="Name of backend from storage.backends",
)
@ -233,9 +221,8 @@ class KVStoreReference(BaseModel):
description="Key prefix for KVStore backends",
)
backend: str | None = Field(
description="Name of backend from persistence.backends, a default will be used if not specified",
default=None,
backend: str = Field(
description="Name of backend from storage.backends",
)
@ -263,21 +250,11 @@ class InferenceStoreReference(SqlStoreReference):
)
class ResponsesStoreReference(InferenceStoreReference):
"""Responses store configuration with queue tuning."""
class StorageConfig(BaseModel):
backends: dict[str, StorageBackendConfig] = Field(
description="Named backend configurations (e.g., 'default', 'cache')",
)
# these are stores used natively by the Stack
metadata: KVStoreReference | None = Field(
default=None,
description="Metadata store configuration (uses KVStore backend)",
)
inference: InferenceStoreReference | None = Field(
default=None,
description="Inference store configuration (uses SqlStore backend)",
)
conversations: SqlStoreReference | None = Field(
default=None,
description="Conversations store configuration (uses SqlStore backend)",
)

13
llama_stack/core/store/registry.py
View file

@ -11,7 +11,7 @@ from typing import Protocol
import pydantic
from llama_stack.core.datatypes import RoutableObjectWithProvider
from llama_stack.core.storage.datatypes import KVStoreReference, StorageConfig
from llama_stack.core.storage.datatypes import KVStoreReference
from llama_stack.log import get_logger
from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
@ -190,17 +190,10 @@ class CachedDiskDistributionRegistry(DiskDistributionRegistry):
async def create_dist_registry(
storage: StorageConfig,
image_name: str,
metadata_store: KVStoreReference, image_name: str
) -> tuple[CachedDiskDistributionRegistry, KVStore]:
# instantiate kvstore for storing and retrieving distribution metadata
# Use metadata store backend with registry-specific namespace
metadata_ref = storage.metadata
registry_ref = KVStoreReference(
namespace="registry",
backend=metadata_ref.backend if metadata_ref else None,
)
dist_kvstore = await kvstore_impl(registry_ref)
dist_kvstore = await kvstore_impl(metadata_store)
dist_registry = CachedDiskDistributionRegistry(dist_kvstore)
await dist_registry.initialize()
return dist_registry, dist_kvstore