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/inline/agents/meta_reference/agent_instance.py

@@ -42,10 +42,10 @@ from llama_stack.apis.agents import (
     Turn,
 )
 from llama_stack.apis.common.content_types import (
+    URL,
     TextContentItem,
     ToolCallDelta,
     ToolCallParseStatus,
-    URL,
 )
 from llama_stack.apis.inference import (
     ChatCompletionResponseEventType,

llama_stack/providers/inline/agents/meta_reference/safety.py

@@ -6,11 +6,9 @@
 
 import asyncio
 import logging
-
 from typing import List
 
 from llama_stack.apis.inference import Message
-
 from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel
 
 log = logging.getLogger(__name__)

llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py

@@ -41,7 +41,6 @@ from llama_stack.apis.tools import (
     ToolInvocationResult,
 )
 from llama_stack.apis.vector_io import QueryChunksResponse
-
 from llama_stack.providers.inline.agents.meta_reference.agent_instance import (
     MEMORY_QUERY_TOOL,
 )

llama_stack/providers/inline/datasetio/localfs/datasetio.py

@@ -15,14 +15,12 @@ import pandas
 from llama_stack.apis.common.content_types import URL
 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
 
 from .config import LocalFSDatasetIOConfig
 
-
 DATASETS_PREFIX = "localfs_datasets:"
 
 

llama_stack/providers/inline/eval/meta_reference/eval.py

@@ -15,7 +15,6 @@ from llama_stack.apis.inference import Inference, UserMessage
 from llama_stack.apis.scoring import Scoring
 from llama_stack.distribution.datatypes import Api
 from llama_stack.providers.datatypes import EvalTasksProtocolPrivate
-
 from llama_stack.providers.inline.agents.meta_reference.agent_instance import (
     MEMORY_QUERY_TOOL,
 )
@@ -28,7 +27,6 @@ from llama_stack.providers.utils.kvstore import kvstore_impl
 
 from .....apis.common.job_types import Job
 from .....apis.eval.eval import Eval, EvalTaskConfig, EvaluateResponse, JobStatus
-
 from .config import MetaReferenceEvalConfig
 
 EVAL_TASKS_PREFIX = "eval_tasks:"

llama_stack/providers/inline/inference/meta_reference/config.py

@@ -9,7 +9,6 @@ from typing import Any, Dict, Optional
 from pydantic import BaseModel, field_validator
 
 from llama_stack.apis.inference import QuantizationConfig
-
 from llama_stack.providers.utils.inference import supported_inference_models
 
 

llama_stack/providers/inline/inference/meta_reference/generation.py

@@ -37,7 +37,6 @@ from llama_models.llama3.reference_impl.multimodal.model import (
     CrossAttentionTransformer,
 )
 from llama_models.sku_list import resolve_model
-
 from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
 from pydantic import BaseModel
 
@@ -47,7 +46,6 @@ from llama_stack.apis.inference import (
     ResponseFormat,
     ResponseFormatType,
 )
-
 from llama_stack.distribution.utils.model_utils import model_local_dir
 from llama_stack.providers.utils.inference.prompt_adapter import (
     ChatCompletionRequestWithRawContent,

llama_stack/providers/inline/inference/meta_reference/inference.py

@@ -46,8 +46,8 @@ from llama_stack.providers.utils.inference.embedding_mixin import (
     SentenceTransformerEmbeddingMixin,
 )
 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 (
     augment_content_with_response_format_prompt,

llama_stack/providers/inline/inference/meta_reference/parallel_utils.py

@@ -22,16 +22,13 @@ from typing import Callable, Generator, Literal, Optional, Union
 
 import torch
 import zmq
-
 from fairscale.nn.model_parallel.initialize import (
     get_model_parallel_group,
     get_model_parallel_rank,
     get_model_parallel_src_rank,
 )
-
 from pydantic import BaseModel, Field
-
-from torch.distributed.launcher.api import elastic_launch, LaunchConfig
+from torch.distributed.launcher.api import LaunchConfig, elastic_launch
 from typing_extensions import Annotated
 
 from llama_stack.providers.utils.inference.prompt_adapter import (

llama_stack/providers/inline/inference/meta_reference/quantization/fp8_impls.py

@@ -8,7 +8,6 @@
 # This software may be used and distributed in accordance with the terms of the Llama 3 Community License Agreement.
 
 import collections
-
 import logging
 from typing import Optional, Type
 
@@ -23,7 +22,7 @@ except ImportError:
     raise
 
 import torch
-from torch import nn, Tensor
+from torch import Tensor, nn
 
 
 class Fp8ScaledWeights:

llama_stack/providers/inline/inference/meta_reference/quantization/fp8_txest_disabled.py

@@ -10,9 +10,9 @@
 import unittest
 
 import torch
-
-from fp8_impls import ffn_swiglu_fp8_dynamic, FfnQuantizeMode, quantize_fp8
-from hypothesis import given, settings, strategies as st
+from fp8_impls import FfnQuantizeMode, ffn_swiglu_fp8_dynamic, quantize_fp8
+from hypothesis import given, settings
+from hypothesis import strategies as st
 from torch import Tensor
 
 

llama_stack/providers/inline/inference/meta_reference/quantization/loader.py

@@ -12,18 +12,13 @@ import os
 from typing import Any, Dict, List, Optional
 
 import torch
-
 from fairscale.nn.model_parallel.layers import ColumnParallelLinear, RowParallelLinear
 from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
-
 from llama_models.datatypes import CheckpointQuantizationFormat
-
 from llama_models.llama3.api.args import ModelArgs
 from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
 from llama_models.sku_list import resolve_model
-
-from torch import nn, Tensor
-
+from torch import Tensor, nn
 from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
 
 from llama_stack.apis.inference import QuantizationType

llama_stack/providers/inline/inference/meta_reference/quantization/scripts/quantize_checkpoint.py

@@ -16,14 +16,12 @@ from pathlib import Path
 from typing import Optional
 
 import fire
-
 import torch
 from fairscale.nn.model_parallel.initialize import (
     get_model_parallel_rank,
     initialize_model_parallel,
     model_parallel_is_initialized,
 )
-
 from llama_models.llama3.api.args import ModelArgs
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock

llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py

@@ -15,9 +15,9 @@ from llama_stack.apis.inference import (
     ResponseFormat,
     SamplingParams,
     ToolChoice,
+    ToolConfig,
     ToolDefinition,
     ToolPromptFormat,
-    ToolConfig,
 )
 from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.embedding_mixin import (

llama_stack/providers/inline/inference/vllm/vllm.py

@@ -37,9 +37,9 @@ 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.openai_compat import (
-    get_sampling_options,
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,
+    get_sampling_options,
     process_chat_completion_response,
     process_chat_completion_stream_response,
 )

llama_stack/providers/inline/post_training/torchtune/common/utils.py

@@ -15,10 +15,8 @@ from typing import Any, Callable, Dict
 import torch
 from llama_models.datatypes import Model
 from llama_models.sku_list import resolve_model
-
 from pydantic import BaseModel
 from torchtune.data._messages import InputOutputToMessages, ShareGPTToMessages
-
 from torchtune.models.llama3 import llama3_tokenizer
 from torchtune.models.llama3._tokenizer import Llama3Tokenizer
 from torchtune.models.llama3_1 import lora_llama3_1_8b

llama_stack/providers/inline/post_training/torchtune/datasets/sft.py

@@ -13,7 +13,6 @@
 from typing import Any, Dict, List, Mapping
 
 import numpy as np
-
 from torch.utils.data import Dataset
 from torchtune.data._common import CROSS_ENTROPY_IGNORE_IDX
 from torchtune.data._messages import validate_messages

llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py

@@ -18,9 +18,9 @@ from llama_models.sku_list import resolve_model
 from torch import nn
 from torch.optim import Optimizer
 from torch.utils.data import DataLoader, DistributedSampler
-from torchtune import modules, training, utils as torchtune_utils
+from torchtune import modules, training
+from torchtune import utils as torchtune_utils
 from torchtune.data import padded_collate_sft
-
 from torchtune.modules.loss import CEWithChunkedOutputLoss
 from torchtune.modules.peft import (
     get_adapter_params,
@@ -44,14 +44,11 @@ from llama_stack.apis.post_training import (
     OptimizerConfig,
     TrainingConfig,
 )
-
 from llama_stack.distribution.utils.config_dirs import DEFAULT_CHECKPOINT_DIR
-
 from llama_stack.distribution.utils.model_utils import model_local_dir
 from llama_stack.providers.inline.post_training.common.validator import (
     validate_input_dataset_schema,
 )
-
 from llama_stack.providers.inline.post_training.torchtune.common import utils
 from llama_stack.providers.inline.post_training.torchtune.common.checkpointer import (
     TorchtuneCheckpointer,

llama_stack/providers/inline/safety/code_scanner/code_scanner.py

@@ -21,7 +21,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import CodeScannerConfig
 
-
 log = logging.getLogger(__name__)
 
 ALLOWED_CODE_SCANNER_MODEL_IDS = [

llama_stack/providers/inline/safety/llama_guard/llama_guard.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import re
-
 from string import Template
 from typing import Any, Dict, List, Optional
 
@@ -25,10 +24,8 @@ from llama_stack.apis.safety import (
     SafetyViolation,
     ViolationLevel,
 )
-
 from llama_stack.apis.shields import Shield
 from llama_stack.distribution.datatypes import Api
-
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
@@ -36,7 +33,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import LlamaGuardConfig
 
-
 CANNED_RESPONSE_TEXT = "I can't answer that. Can I help with something else?"
 
 SAFE_RESPONSE = "safe"

llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py

@@ -8,7 +8,6 @@ import logging
 from typing import Any, Dict, List
 
 import torch
-
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
 from llama_stack.apis.inference import Message
@@ -19,7 +18,6 @@ from llama_stack.apis.safety import (
     ViolationLevel,
 )
 from llama_stack.apis.shields import Shield
-
 from llama_stack.distribution.utils.model_utils import model_local_dir
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.inference.prompt_adapter import (

llama_stack/providers/inline/scoring/basic/scoring.py

@@ -14,13 +14,13 @@ from llama_stack.apis.scoring import (
     ScoringResult,
 )
 from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
-
 from llama_stack.distribution.datatypes import Api
 from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
 from llama_stack.providers.utils.common.data_schema_validator import (
     get_valid_schemas,
     validate_dataset_schema,
 )
+
 from .config import BasicScoringConfig
 from .scoring_fn.equality_scoring_fn import EqualityScoringFn
 from .scoring_fn.regex_parser_scoring_fn import RegexParserScoringFn

llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py

@@ -7,7 +7,6 @@
 from typing import Any, Dict, Optional
 
 from llama_stack.apis.scoring import ScoringResultRow
-
 from llama_stack.apis.scoring_functions import ScoringFnParams
 from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn
 

llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py

@@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import (
     ScoringFn,
 )
 
-
 equality = ScoringFn(
     identifier="basic::equality",
     description="Returns 1.0 if the input is equal to the target, 0.0 otherwise.",

llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py

@@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import (
     ScoringFn,
 )
 
-
 subset_of = ScoringFn(
     identifier="basic::subset_of",
     description="Returns 1.0 if the expected is included in generated, 0.0 otherwise.",

llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 import re
-
 from typing import Any, Dict, Optional
 
 from llama_stack.apis.scoring import ScoringResultRow

llama_stack/providers/inline/scoring/braintrust/braintrust.py

@@ -29,9 +29,7 @@ from llama_stack.apis.scoring import (
     ScoringResultRow,
 )
 from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
-
 from llama_stack.distribution.datatypes import Api
-
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
 from llama_stack.providers.utils.common.data_schema_validator import (
@@ -39,8 +37,8 @@ from llama_stack.providers.utils.common.data_schema_validator import (
     validate_dataset_schema,
     validate_row_schema,
 )
-
 from llama_stack.providers.utils.scoring.aggregation_utils import aggregate_metrics
+
 from .config import BraintrustScoringConfig
 from .scoring_fn.fn_defs.answer_correctness import answer_correctness_fn_def
 from .scoring_fn.fn_defs.answer_relevancy import answer_relevancy_fn_def

llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py

@@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import (
     ScoringFn,
 )
 
-
 answer_correctness_fn_def = ScoringFn(
     identifier="braintrust::answer-correctness",
     description=(

llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py

@@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import (
     ScoringFn,
 )
 
-
 factuality_fn_def = ScoringFn(
     identifier="braintrust::factuality",
     description=(

llama_stack/providers/inline/scoring/llm_as_judge/scoring.py

@@ -8,7 +8,6 @@ from typing import Any, Dict, List, Optional
 from llama_stack.apis.datasetio import DatasetIO
 from llama_stack.apis.datasets import Datasets
 from llama_stack.apis.inference.inference import Inference
-
 from llama_stack.apis.scoring import (
     ScoreBatchResponse,
     ScoreResponse,
@@ -26,7 +25,6 @@ from llama_stack.providers.utils.common.data_schema_validator import (
 from .config import LlmAsJudgeScoringConfig
 from .scoring_fn.llm_as_judge_scoring_fn import LlmAsJudgeScoringFn
 
-
 LLM_JUDGE_FNS = [LlmAsJudgeScoringFn]
 
 

llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py

@@ -7,7 +7,6 @@
 from llama_stack.apis.common.type_system import NumberType
 from llama_stack.apis.scoring_functions import LLMAsJudgeScoringFnParams, ScoringFn
 
-
 llm_as_judge_base = ScoringFn(
     identifier="llm-as-judge::base",
     description="Llm As Judge Scoring Function",

llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py

@@ -4,18 +4,14 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 import re
-
 from typing import Any, Dict, Optional
 
 from llama_stack.apis.inference.inference import Inference
-
 from llama_stack.apis.scoring import ScoringResultRow
 from llama_stack.apis.scoring_functions import ScoringFnParams
-
 from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn
 
 from .fn_defs.llm_as_judge_405b_simpleqa import llm_as_judge_405b_simpleqa
-
 from .fn_defs.llm_as_judge_base import llm_as_judge_base
 
 

llama_stack/providers/inline/telemetry/sample/sample.py

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

llama_stack/providers/inline/tool_runtime/code_interpreter/code_env_prefix.py

@@ -82,7 +82,11 @@ import sys as _sys
 # them with linters - they're used in code_execution.py
 from contextlib import (  # noqa
     contextmanager as _contextmanager,
+)
+from contextlib import (
     redirect_stderr as _redirect_stderr,
+)
+from contextlib import (
     redirect_stdout as _redirect_stdout,
 )
 from multiprocessing.connection import Connection as _Connection

llama_stack/providers/inline/tool_runtime/rag/context_retriever.py

@@ -9,7 +9,6 @@ from jinja2 import Template
 
 from llama_stack.apis.common.content_types import InterleavedContent
 from llama_stack.apis.inference import UserMessage
-
 from llama_stack.apis.tools.rag_tool import (
     DefaultRAGQueryGeneratorConfig,
     LLMRAGQueryGeneratorConfig,

llama_stack/providers/inline/tool_runtime/rag/memory.py

@@ -11,9 +11,9 @@ import string
 from typing import Any, Dict, List, Optional
 
 from llama_stack.apis.common.content_types import (
+    URL,
     InterleavedContent,
     TextContentItem,
-    URL,
 )
 from llama_stack.apis.inference import Inference
 from llama_stack.apis.tools import (

llama_stack/providers/inline/vector_io/faiss/__init__.py

@@ -7,6 +7,7 @@
 from typing import Dict
 
 from llama_stack.providers.datatypes import Api, ProviderSpec
+
 from .config import FaissImplConfig
 
 

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -8,11 +8,9 @@ import base64
 import io
 import json
 import logging
-
 from typing import Any, Dict, List, Optional
 
 import faiss
-
 import numpy as np
 from numpy.typing import NDArray
 

llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py

@@ -5,7 +5,9 @@
 # the root directory of this source tree.
 
 from typing import Dict
+
 from llama_stack.providers.datatypes import Api, ProviderSpec
+
 from .config import SQLiteVectorIOConfig
 
 

llama_stack/providers/inline/vector_io/sqlite_vec/config.py

@@ -5,9 +5,10 @@
 # the root directory of this source tree.
 
 # config.py
-from pydantic import BaseModel
 from typing import Any, Dict
 
+from pydantic import BaseModel
+
 from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,

llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py

@@ -4,13 +4,14 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import sqlite3
-import sqlite_vec
-import struct
 import logging
+import sqlite3
+import struct
+from typing import Any, Dict, List, Optional
+
 import numpy as np
+import sqlite_vec
 from numpy.typing import NDArray
-from typing import List, Optional, Dict, Any
 
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO