mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-23 08:33:09 +00:00
feat(stores)!: use backend storage references instead of configs (#3697)
**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.
This commit is contained in:
parent
add64e8e2a
commit
2c43285e22
105 changed files with 2290 additions and 1292 deletions
|
@ -10,13 +10,13 @@ import pytest
|
|||
from llama_stack.apis.inference import Model
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.core.datatypes import VectorDBWithOwner
|
||||
from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
|
||||
from llama_stack.core.store.registry import (
|
||||
KEY_FORMAT,
|
||||
CachedDiskDistributionRegistry,
|
||||
DiskDistributionRegistry,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl, register_kvstore_backends
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
@ -72,7 +72,11 @@ async def test_cached_registry_initialization(sqlite_kvstore, sample_vector_db,
|
|||
|
||||
# Test cached version loads from disk
|
||||
db_path = sqlite_kvstore.db_path
|
||||
cached_registry = CachedDiskDistributionRegistry(await kvstore_impl(SqliteKVStoreConfig(db_path=db_path)))
|
||||
backend_name = "kv_cached_test"
|
||||
register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=db_path)})
|
||||
cached_registry = CachedDiskDistributionRegistry(
|
||||
await kvstore_impl(KVStoreReference(backend=backend_name, namespace="registry"))
|
||||
)
|
||||
await cached_registry.initialize()
|
||||
|
||||
result_vector_db = await cached_registry.get("vector_db", "test_vector_db")
|
||||
|
@ -101,7 +105,11 @@ async def test_cached_registry_updates(cached_disk_dist_registry):
|
|||
|
||||
# Verify persisted to disk
|
||||
db_path = cached_disk_dist_registry.kvstore.db_path
|
||||
new_registry = DiskDistributionRegistry(await kvstore_impl(SqliteKVStoreConfig(db_path=db_path)))
|
||||
backend_name = "kv_cached_new"
|
||||
register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=db_path)})
|
||||
new_registry = DiskDistributionRegistry(
|
||||
await kvstore_impl(KVStoreReference(backend=backend_name, namespace="registry"))
|
||||
)
|
||||
await new_registry.initialize()
|
||||
result_vector_db = await new_registry.get("vector_db", "test_vector_db_2")
|
||||
assert result_vector_db is not None
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue