Add version to REST API url (#478)

# What does this PR do? 

Adds a `/alpha/` prefix to all the REST API urls.

Also makes them all use hyphens instead of underscores as is more
standard practice.

(This is based on feedback from our partners.)

## Test Plan 

The Stack itself does not need updating. However, client SDKs and
documentation will need to be updated.

docs/openapi_generator/generate.py

@@ -31,7 +31,12 @@ from .strong_typing.schema import json_schema_type
 
 schema_utils.json_schema_type = json_schema_type
 
-from llama_stack.distribution.stack import LlamaStack
+# this line needs to be here to ensure json_schema_type has been altered before
+# the imports use the annotation
+from llama_stack.distribution.stack import (  # noqa: E402
+    LLAMA_STACK_API_VERSION,
+    LlamaStack,
+)
 
 
 def main(output_dir: str):
@@ -50,7 +55,7 @@ def main(output_dir: str):
             server=Server(url="http://any-hosted-llama-stack.com"),
             info=Info(
                 title="[DRAFT] Llama Stack Specification",
-                version="0.0.1",
+                version=LLAMA_STACK_API_VERSION,
                 description="""This is the specification of the llama stack that provides
                 a set of endpoints and their corresponding interfaces that are tailored to
                 best leverage Llama Models. The specification is still in draft and subject to change.

docs/openapi_generator/pyopenapi/generator.py

@@ -202,7 +202,9 @@ class ContentBuilder:
     ) -> MediaType:
         schema = self.schema_builder.classdef_to_ref(item_type)
         if self.schema_transformer:
-            schema_transformer: Callable[[SchemaOrRef], SchemaOrRef] = self.schema_transformer  # type: ignore
+            schema_transformer: Callable[[SchemaOrRef], SchemaOrRef] = (
+                self.schema_transformer
+            )  # type: ignore
             schema = schema_transformer(schema)
 
         if not examples:
@@ -630,6 +632,7 @@ class Generator:
                 raise NotImplementedError(f"unknown HTTP method: {op.http_method}")
 
             route = op.get_route()
+            print(f"route: {route}")
             if route in paths:
                 paths[route].update(pathItem)
             else:

docs/openapi_generator/pyopenapi/operations.py

@@ -12,6 +12,8 @@ import uuid
 from dataclasses import dataclass
 from typing import Any, Callable, Dict, Iterable, Iterator, List, Optional, Tuple, Union
 
+from llama_stack.distribution.stack import LLAMA_STACK_API_VERSION
+
 from termcolor import colored
 
 from ..strong_typing.inspection import (
@@ -111,9 +113,12 @@ class EndpointOperation:
 
     def get_route(self) -> str:
         if self.route is not None:
-            return self.route
+            assert (
+                "_" not in self.route
+            ), f"route should not contain underscores: {self.route}"
+            return "/".join(["", LLAMA_STACK_API_VERSION, self.route.lstrip("/")])
 
-        route_parts = ["", self.name]
+        route_parts = ["", LLAMA_STACK_API_VERSION, self.name]
         for param_name, _ in self.path_params:
             route_parts.append("{" + param_name + "}")
         return "/".join(route_parts)