mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-22 16:23:08 +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: ${env.CHROMADB_URL}
persistence:
backend: kv_default
namespace: vector_io::chroma_remote
```
Once the backends are declared, everything else just points at them, so
rotating credentials or swapping to Postgres happens in one place and
the stack reuses a single connection pool.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
add64e8e2a
commit
2c43285e22
105 changed files with 2290 additions and 1292 deletions
|
|
@ -40,12 +40,20 @@ from llama_stack.core.distribution import get_provider_registry
|
|||
from llama_stack.core.external import load_external_apis
|
||||
from llama_stack.core.resolver import InvalidProviderError
|
||||
from llama_stack.core.stack import replace_env_vars
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
InferenceStoreReference,
|
||||
KVStoreReference,
|
||||
ServerStoresConfig,
|
||||
SqliteKVStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
SqlStoreReference,
|
||||
StorageConfig,
|
||||
)
|
||||
from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR, EXTERNAL_PROVIDERS_DIR
|
||||
from llama_stack.core.utils.dynamic import instantiate_class_type
|
||||
from llama_stack.core.utils.exec import formulate_run_args, run_command
|
||||
from llama_stack.core.utils.image_types import LlamaStackImageType
|
||||
from llama_stack.providers.datatypes import Api
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
|
||||
|
||||
DISTRIBS_PATH = Path(__file__).parent.parent.parent / "distributions"
|
||||
|
||||
|
|
@ -286,21 +294,42 @@ def _generate_run_config(
|
|||
Generate a run.yaml template file for user to edit from a build.yaml file
|
||||
"""
|
||||
apis = list(build_config.distribution_spec.providers.keys())
|
||||
distro_dir = DISTRIBS_BASE_DIR / image_name
|
||||
storage = StorageConfig(
|
||||
backends={
|
||||
"kv_default": SqliteKVStoreConfig(
|
||||
db_path=f"${{env.SQLITE_STORE_DIR:={distro_dir}}}/kvstore.db",
|
||||
),
|
||||
"sql_default": SqliteSqlStoreConfig(
|
||||
db_path=f"${{env.SQLITE_STORE_DIR:={distro_dir}}}/sql_store.db",
|
||||
),
|
||||
},
|
||||
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="openai_conversations",
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
run_config = StackRunConfig(
|
||||
container_image=(image_name if build_config.image_type == LlamaStackImageType.CONTAINER.value else None),
|
||||
image_name=image_name,
|
||||
apis=apis,
|
||||
providers={},
|
||||
storage=storage,
|
||||
external_providers_dir=build_config.external_providers_dir
|
||||
if build_config.external_providers_dir
|
||||
else EXTERNAL_PROVIDERS_DIR,
|
||||
)
|
||||
if not run_config.inference_store:
|
||||
run_config.inference_store = SqliteSqlStoreConfig(
|
||||
**SqliteSqlStoreConfig.sample_run_config(
|
||||
__distro_dir__=(DISTRIBS_BASE_DIR / image_name).as_posix(), db_name="inference_store.db"
|
||||
)
|
||||
)
|
||||
# build providers dict
|
||||
provider_registry = get_provider_registry(build_config)
|
||||
for api in apis:
|
||||
|
|
|
|||
|
|
@ -17,10 +17,19 @@ from llama_stack.core.datatypes import (
|
|||
BuildConfig,
|
||||
Provider,
|
||||
StackRunConfig,
|
||||
StorageConfig,
|
||||
)
|
||||
from llama_stack.core.distribution import get_provider_registry
|
||||
from llama_stack.core.resolver import InvalidProviderError
|
||||
from llama_stack.core.utils.config_dirs import EXTERNAL_PROVIDERS_DIR
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
InferenceStoreReference,
|
||||
KVStoreReference,
|
||||
ServerStoresConfig,
|
||||
SqliteKVStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
SqlStoreReference,
|
||||
)
|
||||
from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR, EXTERNAL_PROVIDERS_DIR
|
||||
from llama_stack.core.utils.dynamic import instantiate_class_type
|
||||
from llama_stack.core.utils.image_types import LlamaStackImageType
|
||||
from llama_stack.providers.datatypes import Api
|
||||
|
|
@ -51,11 +60,23 @@ def generate_run_config(
|
|||
Generate a run.yaml template file for user to edit from a build.yaml file
|
||||
"""
|
||||
apis = list(build_config.distribution_spec.providers.keys())
|
||||
distro_dir = DISTRIBS_BASE_DIR / image_name
|
||||
run_config = StackRunConfig(
|
||||
container_image=(image_name if build_config.image_type == LlamaStackImageType.CONTAINER.value else None),
|
||||
image_name=image_name,
|
||||
apis=apis,
|
||||
providers={},
|
||||
storage=StorageConfig(
|
||||
backends={
|
||||
"kv_default": SqliteKVStoreConfig(db_path=str(distro_dir / "kvstore.db")),
|
||||
"sql_default": SqliteSqlStoreConfig(db_path=str(distro_dir / "sql_store.db")),
|
||||
},
|
||||
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="openai_conversations"),
|
||||
),
|
||||
),
|
||||
external_providers_dir=build_config.external_providers_dir
|
||||
if build_config.external_providers_dir
|
||||
else EXTERNAL_PROVIDERS_DIR,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue