mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
549812f51e
# What does this PR do? * Provide sqlite implementation of the APIs introduced in https://github.com/meta-llama/llama-stack/pull/2145. * Introduced a SqlStore API: llama_stack/providers/utils/sqlstore/api.py and the first Sqlite implementation * Pagination support will be added in a future PR. ## Test Plan Unit test on sql store: <img width="1005" alt="image" src="https://github.com/user-attachments/assets/9b8b7ec8-632b-4667-8127-5583426b2e29" /> Integration test: ``` INFERENCE_MODEL="llama3.2:3b-instruct-fp16" llama stack build --template ollama --image-type conda --run ``` ``` LLAMA_STACK_CONFIG=http://localhost:5001 INFERENCE_MODEL="llama3.2:3b-instruct-fp16" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-fp16" -k 'inference_store and openai' ```
91 lines
2.8 KiB
Python
91 lines
2.8 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 typing import Any
|
|
|
|
from llama_stack.distribution.datatypes import RoutedProtocol
|
|
from llama_stack.distribution.stack import StackRunConfig
|
|
from llama_stack.distribution.store import DistributionRegistry
|
|
from llama_stack.providers.datatypes import Api, RoutingTable
|
|
from llama_stack.providers.utils.inference.inference_store import InferenceStore
|
|
|
|
from .routing_tables import (
|
|
BenchmarksRoutingTable,
|
|
DatasetsRoutingTable,
|
|
ModelsRoutingTable,
|
|
ScoringFunctionsRoutingTable,
|
|
ShieldsRoutingTable,
|
|
ToolGroupsRoutingTable,
|
|
VectorDBsRoutingTable,
|
|
)
|
|
|
|
|
|
async def get_routing_table_impl(
|
|
api: Api,
|
|
impls_by_provider_id: dict[str, RoutedProtocol],
|
|
_deps,
|
|
dist_registry: DistributionRegistry,
|
|
) -> Any:
|
|
api_to_tables = {
|
|
"vector_dbs": VectorDBsRoutingTable,
|
|
"models": ModelsRoutingTable,
|
|
"shields": ShieldsRoutingTable,
|
|
"datasets": DatasetsRoutingTable,
|
|
"scoring_functions": ScoringFunctionsRoutingTable,
|
|
"benchmarks": BenchmarksRoutingTable,
|
|
"tool_groups": ToolGroupsRoutingTable,
|
|
}
|
|
|
|
if api.value not in api_to_tables:
|
|
raise ValueError(f"API {api.value} not found in router map")
|
|
|
|
impl = api_to_tables[api.value](impls_by_provider_id, dist_registry)
|
|
await impl.initialize()
|
|
return impl
|
|
|
|
|
|
async def get_auto_router_impl(
|
|
api: Api, routing_table: RoutingTable, deps: dict[str, Any], run_config: StackRunConfig
|
|
) -> Any:
|
|
from .routers import (
|
|
DatasetIORouter,
|
|
EvalRouter,
|
|
InferenceRouter,
|
|
SafetyRouter,
|
|
ScoringRouter,
|
|
ToolRuntimeRouter,
|
|
VectorIORouter,
|
|
)
|
|
|
|
api_to_routers = {
|
|
"vector_io": VectorIORouter,
|
|
"inference": InferenceRouter,
|
|
"safety": SafetyRouter,
|
|
"datasetio": DatasetIORouter,
|
|
"scoring": ScoringRouter,
|
|
"eval": EvalRouter,
|
|
"tool_runtime": ToolRuntimeRouter,
|
|
}
|
|
api_to_deps = {
|
|
"inference": {"telemetry": Api.telemetry},
|
|
}
|
|
if api.value not in api_to_routers:
|
|
raise ValueError(f"API {api.value} not found in router map")
|
|
|
|
api_to_dep_impl = {}
|
|
for dep_name, dep_api in api_to_deps.get(api.value, {}).items():
|
|
if dep_api in deps:
|
|
api_to_dep_impl[dep_name] = deps[dep_api]
|
|
|
|
# TODO: move pass configs to routers instead
|
|
if api == Api.inference and run_config.inference_store:
|
|
inference_store = InferenceStore(run_config.inference_store)
|
|
await inference_store.initialize()
|
|
api_to_dep_impl["store"] = inference_store
|
|
|
|
impl = api_to_routers[api.value](routing_table, **api_to_dep_impl)
|
|
await impl.initialize()
|
|
return impl
|