mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-13 21:52:56 +00:00
feat(stores)!: use backend storage references instead of configs
This commit is contained in:
parent
b3099d40e2
commit
ea9664874d
47 changed files with 893 additions and 696 deletions
|
|
@ -15,12 +15,13 @@ from llama_stack.apis.inference import (
|
|||
OpenAIMessageParam,
|
||||
Order,
|
||||
)
|
||||
from llama_stack.core.datatypes import AccessRule, InferenceStoreConfig
|
||||
from llama_stack.core.datatypes import AccessRule
|
||||
from llama_stack.core.storage.datatypes import InferenceStoreReference, StorageBackendType
|
||||
from llama_stack.log import get_logger
|
||||
|
||||
from ..sqlstore.api import ColumnDefinition, ColumnType
|
||||
from ..sqlstore.authorized_sqlstore import AuthorizedSqlStore
|
||||
from ..sqlstore.sqlstore import SqlStoreConfig, SqlStoreType, sqlstore_impl
|
||||
from ..sqlstore.sqlstore import _SQLSTORE_BACKENDS, sqlstore_impl
|
||||
|
||||
logger = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
|
@ -28,33 +29,31 @@ logger = get_logger(name=__name__, category="inference")
|
|||
class InferenceStore:
|
||||
def __init__(
|
||||
self,
|
||||
config: InferenceStoreConfig | SqlStoreConfig,
|
||||
reference: InferenceStoreReference,
|
||||
policy: list[AccessRule],
|
||||
):
|
||||
# Handle backward compatibility
|
||||
if not isinstance(config, InferenceStoreConfig):
|
||||
# Legacy: SqlStoreConfig passed directly as config
|
||||
config = InferenceStoreConfig(
|
||||
sql_store_config=config,
|
||||
)
|
||||
|
||||
self.config = config
|
||||
self.sql_store_config = config.sql_store_config
|
||||
self.reference = reference
|
||||
self.sql_store = None
|
||||
self.policy = policy
|
||||
|
||||
# Disable write queue for SQLite to avoid concurrency issues
|
||||
self.enable_write_queue = self.sql_store_config.type != SqlStoreType.sqlite
|
||||
|
||||
# Async write queue and worker control
|
||||
self._queue: asyncio.Queue[tuple[OpenAIChatCompletion, list[OpenAIMessageParam]]] | None = None
|
||||
self._worker_tasks: list[asyncio.Task[Any]] = []
|
||||
self._max_write_queue_size: int = config.max_write_queue_size
|
||||
self._num_writers: int = max(1, config.num_writers)
|
||||
self._max_write_queue_size: int = reference.max_write_queue_size
|
||||
self._num_writers: int = max(1, reference.num_writers)
|
||||
|
||||
async def initialize(self):
|
||||
"""Create the necessary tables if they don't exist."""
|
||||
self.sql_store = AuthorizedSqlStore(sqlstore_impl(self.sql_store_config), self.policy)
|
||||
base_store = sqlstore_impl(self.reference)
|
||||
self.sql_store = AuthorizedSqlStore(base_store, self.policy)
|
||||
|
||||
# Disable write queue for SQLite to avoid concurrency issues
|
||||
backend_name = self.reference.backend or list(_SQLSTORE_BACKENDS.keys())[0] if _SQLSTORE_BACKENDS else None
|
||||
if backend_name:
|
||||
backend_config = _SQLSTORE_BACKENDS.get(backend_name)
|
||||
self.enable_write_queue = backend_config.type != StorageBackendType.SQL_SQLITE
|
||||
else:
|
||||
self.enable_write_queue = True
|
||||
await self.sql_store.create_table(
|
||||
"chat_completions",
|
||||
{
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue