build: format codebase imports using ruff linter (#1028)

# What does this PR do?

- Configured ruff linter to automatically fix import sorting issues.
- Set --exit-non-zero-on-fix to ensure non-zero exit code when fixes are
applied.
- Enabled the 'I' selection to focus on import-related linting rules.
- Ran the linter, and formatted all codebase imports accordingly.
- Removed the black dep from the "dev" group since we use ruff

Signed-off-by: Sébastien Han <seb@redhat.com>

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]

[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)

Signed-off-by: Sébastien Han <seb@redhat.com>

llama_stack/providers/remote/agents/sample/sample.py

@@ -5,6 +5,7 @@
 # the root directory of this source tree.
 
 from llama_stack.apis.agents import Agents
+
 from .config import SampleConfig
 
 

llama_stack/providers/remote/datasetio/huggingface/huggingface.py

@@ -9,7 +9,6 @@ import datasets as hf_datasets
 
 from llama_stack.apis.datasetio import DatasetIO, PaginatedRowsResult
 from llama_stack.apis.datasets import Dataset
-
 from llama_stack.providers.datatypes import DatasetsProtocolPrivate
 from llama_stack.providers.utils.datasetio.url_utils import get_dataframe_from_url
 from llama_stack.providers.utils.kvstore import kvstore_impl

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

@@ -31,13 +31,13 @@ from llama_stack.apis.inference import (
 from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
 from llama_stack.providers.utils.bedrock.client import create_bedrock_client
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
-    get_sampling_strategy_options,
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,
+    get_sampling_strategy_options,
     process_chat_completion_response,
     process_chat_completion_stream_response,
 )

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

@@ -29,8 +29,8 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
     get_sampling_options,

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

@@ -26,8 +26,8 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
     get_sampling_options,

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

@@ -31,8 +31,8 @@ from llama_stack.apis.inference import (
 )
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
     convert_message_to_openai_dict,

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

@@ -31,9 +31,9 @@ from llama_stack.apis.inference import (
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.remote.inference.groq.config import GroqConfig
 from llama_stack.providers.utils.inference.model_registry import (
+    ModelRegistryHelper,
     build_model_alias,
     build_model_alias_with_just_provider_model_id,
-    ModelRegistryHelper,
 )
 
 from .groq_utils import (

llama_stack/providers/remote/inference/groq/groq_utils.py

@@ -24,10 +24,8 @@ from groq.types.chat.chat_completion_user_message_param import (
 )
 from groq.types.chat.completion_create_params import CompletionCreateParams
 from groq.types.shared.function_definition import FunctionDefinition
-
 from llama_models.llama3.api.datatypes import ToolParamDefinition
 
-
 from llama_stack.apis.common.content_types import (
     TextDelta,
     ToolCallDelta,
@@ -47,9 +45,9 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
-    get_sampling_strategy_options,
-    convert_tool_call,
     UnparseableToolCall,
+    convert_tool_call,
+    get_sampling_strategy_options,
 )
 
 

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

@@ -29,8 +29,8 @@ from llama_stack.apis.inference import (
     ToolConfig,
 )
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.prompt_adapter import content_has_media
 

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

@@ -22,17 +22,35 @@ from llama_models.llama3.api.datatypes import (
 from openai import AsyncStream
 from openai.types.chat import (
     ChatCompletionAssistantMessageParam as OpenAIChatCompletionAssistantMessage,
+)
+from openai.types.chat import (
     ChatCompletionChunk as OpenAIChatCompletionChunk,
+)
+from openai.types.chat import (
     ChatCompletionContentPartImageParam as OpenAIChatCompletionContentPartImageParam,
+)
+from openai.types.chat import (
     ChatCompletionContentPartParam as OpenAIChatCompletionContentPartParam,
+)
+from openai.types.chat import (
     ChatCompletionMessageParam as OpenAIChatCompletionMessage,
+)
+from openai.types.chat import (
     ChatCompletionMessageToolCallParam as OpenAIChatCompletionMessageToolCall,
+)
+from openai.types.chat import (
     ChatCompletionSystemMessageParam as OpenAIChatCompletionSystemMessage,
+)
+from openai.types.chat import (
     ChatCompletionToolMessageParam as OpenAIChatCompletionToolMessage,
+)
+from openai.types.chat import (
     ChatCompletionUserMessageParam as OpenAIChatCompletionUserMessage,
 )
 from openai.types.chat.chat_completion import (
     Choice as OpenAIChoice,
+)
+from openai.types.chat.chat_completion import (
     ChoiceLogprobs as OpenAIChoiceLogprobs,  # same as chat_completion_chunk ChoiceLogprobs
 )
 from openai.types.chat.chat_completion_content_part_image_param import (
@@ -69,7 +87,6 @@ from llama_stack.apis.inference import (
     ToolResponseMessage,
     UserMessage,
 )
-
 from llama_stack.providers.utils.inference.prompt_adapter import (
     convert_image_content_to_url,
 )

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

@@ -8,7 +8,6 @@ from typing import Any, Dict
 
 from pydantic import BaseModel
 
-
 DEFAULT_OLLAMA_URL = "http://localhost:11434"
 
 

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

@@ -36,14 +36,14 @@ from llama_stack.apis.inference import (
 from llama_stack.apis.models import Model, ModelType
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import (
+    ModelRegistryHelper,
     build_model_alias,
     build_model_alias_with_just_provider_model_id,
-    ModelRegistryHelper,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
-    get_sampling_options,
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,
+    get_sampling_options,
     process_chat_completion_response,
     process_chat_completion_stream_response,
     process_completion_response,

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

@@ -8,14 +8,12 @@ from typing import AsyncGenerator
 from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.datatypes import Message
 from llama_models.llama3.api.tokenizer import Tokenizer
-
 from openai import OpenAI
 
 from llama_stack.apis.inference import *  # noqa: F403
 
 # from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
-
 from llama_stack.providers.utils.inference.openai_compat import (
     get_sampling_options,
     process_chat_completion_response,

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

@@ -24,8 +24,8 @@ from llama_stack.apis.common.content_types import (
 )
 from llama_stack.apis.inference import *  # noqa: F403
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
     process_chat_completion_stream_response,

llama_stack/providers/remote/inference/sample/sample.py

@@ -6,6 +6,7 @@
 
 from llama_stack.apis.inference import Inference
 from llama_stack.apis.models import Model
+
 from .config import SampleConfig
 
 

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

@@ -33,13 +33,13 @@ from llama_stack.apis.inference import (
 from llama_stack.apis.models import Model
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
-    get_sampling_options,
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,
+    get_sampling_options,
     process_chat_completion_response,
     process_chat_completion_stream_response,
     process_completion_response,

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

@@ -30,8 +30,8 @@ from llama_stack.apis.inference import (
 )
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
     convert_message_to_openai_dict,

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

@@ -13,10 +13,14 @@ from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import all_registered_models
 from openai import OpenAI
 
-from llama_stack.apis.common.content_types import InterleavedContent, ToolCallDelta, ToolCallParseStatus, TextDelta
+from llama_stack.apis.common.content_types import InterleavedContent, TextDelta, ToolCallDelta, ToolCallParseStatus
 from llama_stack.apis.inference import (
     ChatCompletionRequest,
     ChatCompletionResponse,
+    ChatCompletionResponseEvent,
+    ChatCompletionResponseEventType,
+    ChatCompletionResponseStreamChunk,
+    CompletionMessage,
     CompletionRequest,
     CompletionResponse,
     CompletionResponseStreamChunk,
@@ -31,26 +35,22 @@ from llama_stack.apis.inference import (
     ToolConfig,
     ToolDefinition,
     ToolPromptFormat,
-    CompletionMessage,
-    ChatCompletionResponseEventType,
-    ChatCompletionResponseStreamChunk,
-    ChatCompletionResponseEvent,
 )
 from llama_stack.apis.models import Model, ModelType
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import (
-    build_model_alias,
     ModelRegistryHelper,
+    build_model_alias,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
-    convert_message_to_openai_dict,
-    get_sampling_options,
-    process_completion_response,
-    process_completion_stream_response,
     OpenAICompatCompletionResponse,
     UnparseableToolCall,
+    convert_message_to_openai_dict,
     convert_tool_call,
+    get_sampling_options,
     process_chat_completion_stream_response,
+    process_completion_response,
+    process_completion_stream_response,
 )
 from llama_stack.providers.utils.inference.prompt_adapter import (
     completion_request_to_prompt,

llama_stack/providers/remote/safety/bedrock/bedrock.py

@@ -6,11 +6,9 @@
 
 import json
 import logging
-
 from typing import Any, Dict, List
 
 from llama_stack.apis.inference import Message
-
 from llama_stack.apis.safety import (
     RunShieldResponse,
     Safety,
@@ -23,7 +21,6 @@ from llama_stack.providers.utils.bedrock.client import create_bedrock_client
 
 from .config import BedrockSafetyConfig
 
-
 logger = logging.getLogger(__name__)
 
 

llama_stack/providers/remote/safety/sample/sample.py

@@ -6,6 +6,7 @@
 
 from llama_stack.apis.safety import Safety
 from llama_stack.apis.shields import Shield
+
 from .config import SampleConfig
 
 

llama_stack/providers/remote/tool_runtime/model_context_protocol/__init__.py

@@ -7,7 +7,6 @@
 from pydantic import BaseModel
 
 from .config import ModelContextProtocolConfig
-
 from .model_context_protocol import ModelContextProtocolToolRuntimeImpl
 
 

llama_stack/providers/remote/vector_io/chroma/chroma.py

@@ -21,6 +21,7 @@ from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
     VectorDBWithIndex,
 )
+
 from .config import ChromaRemoteImplConfig
 
 log = logging.getLogger(__name__)

llama_stack/providers/remote/vector_io/pgvector/pgvector.py

@@ -10,15 +10,13 @@ from typing import Any, Dict, List, Optional, Tuple
 import psycopg2
 from numpy.typing import NDArray
 from psycopg2 import sql
-from psycopg2.extras import execute_values, Json
-
+from psycopg2.extras import Json, execute_values
 from pydantic import BaseModel, TypeAdapter
 
 from llama_stack.apis.inference import InterleavedContent
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
-
 from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
     VectorDBWithIndex,

llama_stack/providers/remote/vector_io/qdrant/qdrant.py

@@ -20,6 +20,7 @@ from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
     VectorDBWithIndex,
 )
+
 from .config import QdrantConfig
 
 log = logging.getLogger(__name__)

llama_stack/providers/remote/vector_io/sample/sample.py

@@ -6,6 +6,7 @@
 
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import VectorIO
+
 from .config import SampleConfig
 
 

llama_stack/providers/remote/vector_io/weaviate/weaviate.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 import json
 import logging
-
 from typing import Any, Dict, List, Optional
 
 import weaviate