skeleton models api

llama_stack/distribution/datatypes.py

@@ -20,6 +20,7 @@ class Api(Enum):
     agents = "agents"
     memory = "memory"
     telemetry = "telemetry"
+    models = "models"
 
 
 @json_schema_type

llama_stack/distribution/distribution.py

@@ -11,6 +11,7 @@ from typing import Dict, List
 from llama_stack.apis.agents import Agents
 from llama_stack.apis.inference import Inference
 from llama_stack.apis.memory import Memory
+from llama_stack.apis.models import Models
 from llama_stack.apis.safety import Safety
 from llama_stack.apis.telemetry import Telemetry
 
@@ -38,6 +39,7 @@ def api_endpoints() -> Dict[Api, List[ApiEndpoint]]:
         Api.agents: Agents,
         Api.memory: Memory,
         Api.telemetry: Telemetry,
+        Api.models: Models,
     }
 
     for api, protocol in protocols.items():

llama_stack/distribution/server/server.py

@@ -35,9 +35,6 @@ from fastapi import Body, FastAPI, HTTPException, Request, Response
 from fastapi.exceptions import RequestValidationError
 from fastapi.responses import JSONResponse, StreamingResponse
 from fastapi.routing import APIRoute
-from pydantic import BaseModel, ValidationError
-from termcolor import cprint
-from typing_extensions import Annotated
 
 from llama_stack.providers.utils.telemetry.tracing import (
     end_trace,
@@ -45,6 +42,9 @@ from llama_stack.providers.utils.telemetry.tracing import (
     SpanStatus,
     start_trace,
 )
+from pydantic import BaseModel, ValidationError
+from termcolor import cprint
+from typing_extensions import Annotated
 from llama_stack.distribution.datatypes import *  # noqa: F403
 
 from llama_stack.distribution.distribution import api_endpoints, api_providers
@@ -333,7 +333,9 @@ def main(yaml_config: str, port: int = 5000, disable_ipv6: bool = False):
 
     app = FastAPI()
 
+    print(config)
     impls, specs = asyncio.run(resolve_impls(config.provider_map))
+    print(impls)
     if Api.telemetry in impls:
         setup_logger(impls[Api.telemetry])