mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-22 16:23:08 +00:00
ea233c2134
BREAKING CHANGE: Provider config field names changed for semantic clarity
- Rename kvstore → persistence for all providers
- Simple providers: flat persistence with backend reference
- Complex providers (agents): nested persistence.agent_state + persistence.responses
- Files provider: metadata_store → persistence
- Provider configs now clearly express 'how do I persist?' not 'what type of store?'
Example:
# Before
config:
kvstore:
backend: kvstore
namespace: faiss
# After
config:
persistence:
backend: kvstore
namespace: faiss
# Agents (nested)
config:
persistence:
agent_state:
backend: kvstore
namespace: agents
responses:
backend: sqlstore
namespace: responses
40 lines
1.2 KiB
Python
40 lines
1.2 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.
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
|
|
|
|
|
|
class ReferenceBatchesImplConfig(BaseModel):
|
|
"""Configuration for the Reference Batches implementation."""
|
|
|
|
persistence: KVStoreConfig = Field(
|
|
description="Configuration for the key-value store backend.",
|
|
)
|
|
|
|
max_concurrent_batches: int = Field(
|
|
default=1,
|
|
description="Maximum number of concurrent batches to process simultaneously.",
|
|
ge=1,
|
|
)
|
|
|
|
max_concurrent_requests_per_batch: int = Field(
|
|
default=10,
|
|
description="Maximum number of concurrent requests to process per batch.",
|
|
ge=1,
|
|
)
|
|
|
|
# TODO: add a max requests per second rate limiter
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, __distro_dir__: str) -> dict:
|
|
return {
|
|
"persistence": SqliteKVStoreConfig.sample_run_config(
|
|
__distro_dir__=__distro_dir__,
|
|
db_name="batches.db",
|
|
),
|
|
}
|