feat: implement get chat completions APIs (#2200)

# 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'
```
This commit is contained in:
ehhuang 2025-05-21 22:21:52 -07:00 committed by GitHub
parent 633bb9c5b3
commit 549812f51e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
71 changed files with 1111 additions and 10 deletions

View file

@ -7,8 +7,10 @@
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,
@ -45,7 +47,9 @@ async def get_routing_table_impl(
return impl
async def get_auto_router_impl(api: Api, routing_table: RoutingTable, deps: dict[str, Any]) -> Any:
async def get_auto_router_impl(
api: Api, routing_table: RoutingTable, deps: dict[str, Any], run_config: StackRunConfig
) -> Any:
from .routers import (
DatasetIORouter,
EvalRouter,
@ -76,6 +80,12 @@ async def get_auto_router_impl(api: Api, routing_table: RoutingTable, deps: dict
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