fix: rename llama_stack_api dir (#4155)

# What does this PR do?

the directory structure was src/llama-stack-api/llama_stack_api

instead it should just be src/llama_stack_api to match the other
packages.

update the structure and pyproject/linting config

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

src/llama_stack/providers/remote/inference/anthropic/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class AnthropicProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/azure/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, HttpUrl, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class AzureProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/bedrock/bedrock.py

@@ -6,6 +6,11 @@
 
 from collections.abc import AsyncIterator, Iterable
 
+from openai import AuthenticationError
+
+from llama_stack.core.telemetry.tracing import get_current_span
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
@@ -15,11 +20,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
-from openai import AuthenticationError
-
-from llama_stack.core.telemetry.tracing import get_current_span
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import BedrockConfig
 

src/llama_stack/providers/remote/inference/cerebras/cerebras.py

@@ -6,13 +6,12 @@
 
 from urllib.parse import urljoin
 
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
 
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from .config import CerebrasImplConfig
 
 

src/llama_stack/providers/remote/inference/cerebras/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 DEFAULT_BASE_URL = "https://api.cerebras.ai"
 

src/llama_stack/providers/remote/inference/databricks/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class DatabricksProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/databricks/databricks.py

@@ -7,10 +7,10 @@
 from collections.abc import Iterable
 
 from databricks.sdk import WorkspaceClient
-from llama_stack_api import OpenAICompletion, OpenAICompletionRequestWithExtraBody
 
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import OpenAICompletion, OpenAICompletionRequestWithExtraBody
 
 from .config import DatabricksImplConfig
 

src/llama_stack/providers/remote/inference/fireworks/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/gemini/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class GeminiProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/gemini/gemini.py

@@ -6,6 +6,7 @@
 
 from typing import Any
 
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIEmbeddingData,
     OpenAIEmbeddingsRequestWithExtraBody,
@@ -13,8 +14,6 @@ from llama_stack_api import (
     OpenAIEmbeddingUsage,
 )
 
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from .config import GeminiConfig
 
 

src/llama_stack/providers/remote/inference/groq/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class GroqProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/llama_openai_compat/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class LlamaProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/llama_openai_compat/llama.py

@@ -4,6 +4,9 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from llama_stack.log import get_logger
+from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAICompletion,
     OpenAICompletionRequestWithExtraBody,
@@ -11,10 +14,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsResponse,
 )
 
-from llama_stack.log import get_logger
-from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 logger = get_logger(name=__name__, category="inference::llama_openai_compat")
 
 

src/llama_stack/providers/remote/inference/nvidia/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class NVIDIAProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -8,6 +8,9 @@
 from collections.abc import Iterable
 
 import aiohttp
+
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     Model,
     ModelType,
@@ -17,9 +20,6 @@ from llama_stack_api import (
     RerankResponse,
 )
 
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from . import NVIDIAConfig
 from .utils import _is_nvidia_hosted
 

src/llama_stack/providers/remote/inference/oci/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class OCIProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/oci/oci.py

@@ -10,11 +10,6 @@ from typing import Any
 
 import httpx
 import oci
-from llama_stack_api import (
-    ModelType,
-    OpenAIEmbeddingsRequestWithExtraBody,
-    OpenAIEmbeddingsResponse,
-)
 from oci.generative_ai.generative_ai_client import GenerativeAiClient
 from oci.generative_ai.models import ModelCollection
 from openai._base_client import DefaultAsyncHttpxClient
@@ -23,6 +18,11 @@ from llama_stack.log import get_logger
 from llama_stack.providers.remote.inference.oci.auth import OciInstancePrincipalAuth, OciUserPrincipalAuth
 from llama_stack.providers.remote.inference.oci.config import OCIConfig
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import (
+    ModelType,
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+)
 
 logger = get_logger(name=__name__, category="inference::oci")
 

src/llama_stack/providers/remote/inference/ollama/ollama.py

@@ -7,17 +7,17 @@
 
 import asyncio
 
+from ollama import AsyncClient as AsyncOllamaClient
+
+from llama_stack.log import get_logger
+from llama_stack.providers.remote.inference.ollama.config import OllamaImplConfig
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     HealthResponse,
     HealthStatus,
     Model,
     UnsupportedModelError,
 )
-from ollama import AsyncClient as AsyncOllamaClient
-
-from llama_stack.log import get_logger
-from llama_stack.providers.remote.inference.ollama.config import OllamaImplConfig
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 logger = get_logger(name=__name__, category="inference::ollama")
 

src/llama_stack/providers/remote/inference/openai/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class OpenAIProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/passthrough/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/passthrough/passthrough.py

@@ -6,6 +6,9 @@
 
 from collections.abc import AsyncIterator
 
+from openai import AsyncOpenAI
+
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack_api import (
     Inference,
     Model,
@@ -17,9 +20,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
-from openai import AsyncOpenAI
-
-from llama_stack.core.request_headers import NeedsRequestProviderData
 
 from .config import PassthroughImplConfig
 

src/llama_stack/providers/remote/inference/runpod/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class RunpodProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/runpod/runpod.py

@@ -6,14 +6,13 @@
 
 from collections.abc import AsyncIterator
 
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
     OpenAIChatCompletionRequestWithExtraBody,
 )
 
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from .config import RunpodImplConfig
 
 

src/llama_stack/providers/remote/inference/sambanova/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class SambaNovaProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/tgi/config.py

@@ -5,10 +5,10 @@
 # the root directory of this source tree.
 
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/tgi/tgi.py

@@ -8,14 +8,14 @@
 from collections.abc import Iterable
 
 from huggingface_hub import AsyncInferenceClient, HfApi
-from llama_stack_api import (
-    OpenAIEmbeddingsRequestWithExtraBody,
-    OpenAIEmbeddingsResponse,
-)
 from pydantic import SecretStr
 
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import (
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+)
 
 from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
 

src/llama_stack/providers/remote/inference/together/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/together/together.py

@@ -8,18 +8,18 @@
 from collections.abc import Iterable
 from typing import Any, cast
 
-from llama_stack_api import (
-    Model,
-    OpenAIEmbeddingsRequestWithExtraBody,
-    OpenAIEmbeddingsResponse,
-    OpenAIEmbeddingUsage,
-)
 from together import AsyncTogether  # type: ignore[import-untyped]
 from together.constants import BASE_URL  # type: ignore[import-untyped]
 
 from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import (
+    Model,
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+    OpenAIEmbeddingUsage,
+)
 
 from .config import TogetherImplConfig
 

src/llama_stack/providers/remote/inference/vertexai/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class VertexAIProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/vllm/config.py

@@ -6,10 +6,10 @@
 
 from pathlib import Path
 
-from llama_stack_api import json_schema_type
 from pydantic import Field, SecretStr, field_validator
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/vllm/vllm.py

@@ -7,6 +7,10 @@ from collections.abc import AsyncIterator
 from urllib.parse import urljoin
 
 import httpx
+from pydantic import ConfigDict
+
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     HealthResponse,
     HealthStatus,
@@ -15,10 +19,6 @@ from llama_stack_api import (
     OpenAIChatCompletionRequestWithExtraBody,
     ToolChoice,
 )
-from pydantic import ConfigDict
-
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import VLLMInferenceAdapterConfig
 

src/llama_stack/providers/remote/inference/watsonx/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class WatsonXProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/watsonx/watsonx.py

@@ -9,6 +9,12 @@ from typing import Any
 
 import litellm
 import requests
+
+from llama_stack.core.telemetry.tracing import get_current_span
+from llama_stack.log import get_logger
+from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig
+from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
+from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
 from llama_stack_api import (
     Model,
     ModelType,
@@ -22,12 +28,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsResponse,
 )
 
-from llama_stack.core.telemetry.tracing import get_current_span
-from llama_stack.log import get_logger
-from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig
-from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
-from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
-
 logger = get_logger(name=__name__, category="providers::remote::watsonx")
 
 
@@ -238,9 +238,8 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
         )
 
         # Convert response to OpenAI format
-        from llama_stack_api import OpenAIEmbeddingUsage
-
         from llama_stack.providers.utils.inference.litellm_openai_mixin import b64_encode_openai_embeddings_response
+        from llama_stack_api import OpenAIEmbeddingUsage
 
         data = b64_encode_openai_embeddings_response(response.data, params.encoding_format)