mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
feat: Implement FastAPI router system
This commit introduces a new FastAPI router-based system for defining API endpoints, enabling a migration path away from the legacy @webmethod decorator system. The implementation includes router infrastructure, migration of the Batches API as the first example, and updates to server, OpenAPI generation, and inspection systems to support both routing approaches. The router infrastructure consists of a router registry system that allows APIs to register FastAPI router factories, which are then automatically discovered and included in the server application. Standard error responses are centralized in router_utils to ensure consistent OpenAPI specification generation with proper $ref references to component responses. The Batches API has been migrated to demonstrate the new pattern. The protocol definition and models remain in llama_stack_api/batches, maintaining clear separation between API contracts and server implementation. The FastAPI router implementation lives in llama_stack/core/server/routers/batches, following the established pattern where API contracts are defined in llama_stack_api and server routing logic lives in llama_stack/core/server. The server now checks for registered routers before falling back to the legacy webmethod-based route discovery, ensuring backward compatibility during the migration period. The OpenAPI generator has been updated to handle both router-based and webmethod-based routes, correctly extracting metadata from FastAPI route decorators and Pydantic Field descriptions. The inspect endpoint now includes routes from both systems, with proper filtering for deprecated routes and API levels. Response descriptions are now explicitly defined in router decorators, ensuring the generated OpenAPI specification matches the previous format. Error responses use $ref references to component responses (BadRequest400, TooManyRequests429, etc.) as required by the specification. This is neat and will allow us to remove a lot of boiler plate code from our generator once the migration is done. This implementation provides a foundation for incrementally migrating other APIs to the router system while maintaining full backward compatibility with existing webmethod-based APIs. Closes: https://github.com/llamastack/llama-stack/issues/4188 Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
parent
5ea1be69fe
commit
eb3cab1eec
16 changed files with 604 additions and 123 deletions
|
|
@ -64,7 +64,8 @@ def _get_protocol_method(api: Api, method_name: str) -> Any | None:
|
|||
def create_llama_stack_app() -> FastAPI:
|
||||
"""
|
||||
Create a FastAPI app that represents the Llama Stack API.
|
||||
This uses the existing route discovery system to automatically find all routes.
|
||||
This uses both router-based routes (for migrated APIs) and the existing
|
||||
route discovery system for legacy webmethod-based routes.
|
||||
"""
|
||||
app = FastAPI(
|
||||
title="Llama Stack API",
|
||||
|
|
@ -75,15 +76,42 @@ def create_llama_stack_app() -> FastAPI:
|
|||
],
|
||||
)
|
||||
|
||||
# Get all API routes
|
||||
# Import batches router to trigger router registration
|
||||
try:
|
||||
from llama_stack.core.server.routers import batches # noqa: F401
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
# Include routers for APIs that have them registered
|
||||
from llama_stack.core.server.router_registry import create_router, has_router
|
||||
|
||||
def dummy_impl_getter(api: Api) -> Any:
|
||||
"""Dummy implementation getter for OpenAPI generation."""
|
||||
return None
|
||||
|
||||
# Get all APIs that might have routers
|
||||
from llama_stack.core.resolver import api_protocol_map
|
||||
|
||||
protocols = api_protocol_map()
|
||||
for api in protocols.keys():
|
||||
if has_router(api):
|
||||
router = create_router(api, dummy_impl_getter)
|
||||
if router:
|
||||
app.include_router(router)
|
||||
|
||||
# Get all API routes (for legacy webmethod-based routes)
|
||||
from llama_stack.core.server.routes import get_all_api_routes
|
||||
|
||||
api_routes = get_all_api_routes()
|
||||
|
||||
# Create FastAPI routes from the discovered routes
|
||||
# Create FastAPI routes from the discovered routes (skip APIs that have routers)
|
||||
from . import endpoints
|
||||
|
||||
for api, routes in api_routes.items():
|
||||
# Skip APIs that have routers - they're already included above
|
||||
if has_router(api):
|
||||
continue
|
||||
|
||||
for route, webmethod in routes:
|
||||
# Convert the route to a FastAPI endpoint
|
||||
endpoints._create_fastapi_endpoint(app, route, webmethod, api)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue