[remove import *] clean up import *'s (#689)

# What does this PR do?

- as title, cleaning up `import *`'s
- upgrade tests to make them more robust to bad model outputs
- remove import *'s in llama_stack/apis/* (skip __init__ modules)
<img width="465" alt="image"
src="https://github.com/user-attachments/assets/d8339c13-3b40-4ba5-9c53-0d2329726ee2"
/>

- run `sh run_openapi_generator.sh`, no types gets affected

## Test Plan

### Providers Tests

**agents**
```
pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "together" --safety-shield meta-llama/Llama-Guard-3-8B --inference-model meta-llama/Llama-3.1-405B-Instruct-FP8
```

**inference**
```bash
# meta-reference
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py

# together
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py

pytest ./llama_stack/providers/tests/inference/test_prompt_adapter.py 
```

**safety**
```
pytest -v -s llama_stack/providers/tests/safety/test_safety.py -m together --safety-shield meta-llama/Llama-Guard-3-8B
```

**memory**
```
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "sentence_transformers" --env EMBEDDING_DIMENSION=384
```

**scoring**
```
pytest -v -s -m llm_as_judge_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct
pytest -v -s -m basic_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py
pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py
```


**datasetio**
```
pytest -v -s -m localfs llama_stack/providers/tests/datasetio/test_datasetio.py
pytest -v -s -m huggingface llama_stack/providers/tests/datasetio/test_datasetio.py
```


**eval**
```
pytest -v -s -m meta_reference_eval_together_inference llama_stack/providers/tests/eval/test_eval.py
pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py
```

### Client-SDK Tests
```
LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v ./tests/client-sdk
```

### llama-stack-apps
```
PORT=5000
LOCALHOST=localhost

python -m examples.agents.hello $LOCALHOST $PORT
python -m examples.agents.inflation $LOCALHOST $PORT
python -m examples.agents.podcast_transcript $LOCALHOST $PORT
python -m examples.agents.rag_as_attachments $LOCALHOST $PORT
python -m examples.agents.rag_with_memory_bank $LOCALHOST $PORT
python -m examples.safety.llama_guard_demo_mm $LOCALHOST $PORT
python -m examples.agents.e2e_loop_with_custom_tools $LOCALHOST $PORT

# Vision model
python -m examples.interior_design_assistant.app
python -m examples.agent_store.app $LOCALHOST $PORT
```

### CLI
```
which llama
llama model prompt-format -m Llama3.2-11B-Vision-Instruct
llama model list
llama stack list-apis
llama stack list-providers inference

llama stack build --template ollama --image-type conda
```

### Distributions Tests
**ollama**
```
llama stack build --template ollama --image-type conda
ollama run llama3.2:1b-instruct-fp16
llama stack run ./llama_stack/templates/ollama/run.yaml --env INFERENCE_MODEL=meta-llama/Llama-3.2-1B-Instruct
```

**fireworks**
```
llama stack build --template fireworks --image-type conda
llama stack run ./llama_stack/templates/fireworks/run.yaml
```

**together**
```
llama stack build --template together --image-type conda
llama stack run ./llama_stack/templates/together/run.yaml
```

**tgi**
```
llama stack run ./llama_stack/templates/tgi/run.yaml --env TGI_URL=http://0.0.0.0:5009 --env INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
```

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

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

@@ -13,19 +13,64 @@ import secrets
 import string
 import uuid
 from datetime import datetime
-from typing import AsyncGenerator, List, Tuple
+from typing import AsyncGenerator, Dict, List, Optional, Tuple
 from urllib.parse import urlparse
 
 import httpx
 
+from llama_models.llama3.api.datatypes import BuiltinTool
 
-from llama_stack.apis.agents import *  # noqa: F403
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.memory_banks import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentTool,
+    AgentTurnCreateRequest,
+    AgentTurnResponseEvent,
+    AgentTurnResponseEventType,
+    AgentTurnResponseStepCompletePayload,
+    AgentTurnResponseStepProgressPayload,
+    AgentTurnResponseStepStartPayload,
+    AgentTurnResponseStreamChunk,
+    AgentTurnResponseTurnCompletePayload,
+    AgentTurnResponseTurnStartPayload,
+    Attachment,
+    CodeInterpreterToolDefinition,
+    FunctionCallToolDefinition,
+    InferenceStep,
+    MemoryRetrievalStep,
+    MemoryToolDefinition,
+    PhotogenToolDefinition,
+    SearchToolDefinition,
+    ShieldCallStep,
+    StepType,
+    ToolExecutionStep,
+    Turn,
+    WolframAlphaToolDefinition,
+)
 
-from llama_stack.apis.common.content_types import InterleavedContent, TextContentItem
+from llama_stack.apis.common.content_types import (
+    InterleavedContent,
+    TextContentItem,
+    URL,
+)
+from llama_stack.apis.inference import (
+    ChatCompletionResponseEventType,
+    CompletionMessage,
+    Inference,
+    Message,
+    SamplingParams,
+    StopReason,
+    SystemMessage,
+    ToolCallDelta,
+    ToolCallParseStatus,
+    ToolChoice,
+    ToolDefinition,
+    ToolResponse,
+    ToolResponseMessage,
+    UserMessage,
+)
+from llama_stack.apis.memory import Memory, MemoryBankDocument, QueryDocumentsResponse
+from llama_stack.apis.memory_banks import MemoryBanks, VectorMemoryBankParams
+from llama_stack.apis.safety import Safety
 
 from llama_stack.providers.utils.kvstore import KVStore
 from llama_stack.providers.utils.memory.vector_store import concat_interleaved_content

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

@@ -9,15 +9,26 @@ import logging
 import shutil
 import tempfile
 import uuid
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional, Union
 
 from termcolor import colored
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentCreateResponse,
+    Agents,
+    AgentSessionCreateResponse,
+    AgentStepResponse,
+    AgentTurnCreateRequest,
+    Attachment,
+    Session,
+    Turn,
+)
+
+from llama_stack.apis.inference import Inference, ToolResponseMessage, UserMessage
 from llama_stack.apis.memory import Memory
 from llama_stack.apis.memory_banks import MemoryBanks
 from llama_stack.apis.safety import Safety
-from llama_stack.apis.agents import *  # noqa: F403
 
 from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
 

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

@@ -10,9 +10,11 @@ import uuid
 from datetime import datetime
 
 from typing import List, Optional
-from llama_stack.apis.agents import *  # noqa: F403
+
 from pydantic import BaseModel
 
+from llama_stack.apis.agents import Turn
+
 from llama_stack.providers.utils.kvstore import KVStore
 
 log = logging.getLogger(__name__)

llama_stack/providers/inline/agents/meta_reference/rag/context_retriever.py

@@ -7,8 +7,6 @@
 from typing import List
 
 from jinja2 import Template
-from llama_models.llama3.api import *  # noqa: F403
-
 
 from llama_stack.apis.agents import (
     DefaultMemoryQueryGeneratorConfig,
@@ -16,7 +14,7 @@ from llama_stack.apis.agents import (
     MemoryQueryGenerator,
     MemoryQueryGeneratorConfig,
 )
-from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.apis.inference import Message, UserMessage
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )

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

@@ -9,7 +9,9 @@ import logging
 
 from typing import List
 
-from llama_stack.apis.safety import *  # noqa: F403
+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

@@ -8,10 +8,26 @@ from typing import AsyncIterator, List, Optional, Union
 
 import pytest
 
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
-from llama_stack.apis.agents import *  # noqa: F403
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentTurnCreateRequest,
+    AgentTurnResponseTurnCompletePayload,
+)
+
+from llama_stack.apis.inference import (
+    ChatCompletionResponse,
+    ChatCompletionResponseEvent,
+    ChatCompletionResponseStreamChunk,
+    CompletionMessage,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    UserMessage,
+)
+from llama_stack.apis.memory import MemoryBank
+from llama_stack.apis.safety import RunShieldResponse
 
 from ..agents import (
     AGENT_INSTANCES_BY_ID,

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

@@ -7,7 +7,7 @@
 from typing import List
 
 from llama_stack.apis.inference import Message
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.safety import Safety
 
 from ..safety import ShieldRunnerMixin
 from .builtin import BaseTool

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

@@ -3,7 +3,7 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from llama_stack.apis.datasetio import *  # noqa: F401, F403
+from pydantic import BaseModel
 
 
 class LocalFSDatasetIOConfig(BaseModel): ...

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

@@ -3,18 +3,19 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from typing import Any, Dict, List, Optional
-
-import pandas
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-
-from llama_stack.apis.datasetio import *  # noqa: F403
 import base64
 import os
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
+from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse
 
+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
 

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

@@ -5,13 +5,15 @@
 # the root directory of this source tree.
 from enum import Enum
 from typing import Any, Dict, List, Optional
-from llama_models.llama3.api.datatypes import *  # noqa: F403
+
 from tqdm import tqdm
 
-from .....apis.common.job_types import Job
-from .....apis.eval.eval import Eval, EvalTaskConfig, EvaluateResponse, JobStatus
-from llama_stack.apis.common.type_system import *  # noqa: F403
 from llama_stack.apis.agents import Agents
+from llama_stack.apis.common.type_system import (
+    ChatCompletionInputType,
+    CompletionInputType,
+    StringType,
+)
 from llama_stack.apis.datasetio import DatasetIO
 from llama_stack.apis.datasets import Datasets
 from llama_stack.apis.eval_tasks import EvalTask
@@ -20,6 +22,9 @@ from llama_stack.apis.scoring import Scoring
 from llama_stack.providers.datatypes import EvalTasksProtocolPrivate
 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

@@ -6,11 +6,10 @@
 
 from typing import Any, Dict, Optional
 
-from llama_models.datatypes import *  # noqa: F403
-
-from llama_stack.apis.inference import *  # noqa: F401, F403
 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

@@ -32,11 +32,16 @@ from llama_models.llama3.reference_impl.multimodal.model import (
     CrossAttentionTransformer,
 )
 from llama_models.sku_list import resolve_model
-from pydantic import BaseModel
-
-from llama_stack.apis.inference import *  # noqa: F403
 
 from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
+from pydantic import BaseModel
+
+from llama_stack.apis.inference import (
+    Fp8QuantizationConfig,
+    Int4QuantizationConfig,
+    ResponseFormat,
+    ResponseFormatType,
+)
 
 from llama_stack.distribution.utils.model_utils import model_local_dir
 from llama_stack.providers.utils.inference.prompt_adapter import (
@@ -44,12 +49,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     CompletionRequestWithRawContent,
 )
 
-from .config import (
-    Fp8QuantizationConfig,
-    Int4QuantizationConfig,
-    MetaReferenceInferenceConfig,
-    MetaReferenceQuantizedInferenceConfig,
-)
+from .config import MetaReferenceInferenceConfig, MetaReferenceQuantizedInferenceConfig
 
 log = logging.getLogger(__name__)
 

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

@@ -7,10 +7,10 @@
 import logging
 import os
 import uuid
-from typing import AsyncGenerator, Optional
+from typing import AsyncGenerator, List, Optional
 
 from llama_models.llama3.api.chat_format import ChatFormat
-from llama_models.llama3.api.datatypes import *  # noqa: F403
+
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import resolve_model
 
@@ -18,9 +18,26 @@ from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.engine.async_llm_engine import AsyncLLMEngine
 from vllm.sampling_params import SamplingParams as VLLMSamplingParams
 
-from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.apis.common.content_types import InterleavedContent
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ChatCompletionResponseStreamChunk,
+    CompletionResponse,
+    CompletionResponseStreamChunk,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+from llama_stack.apis.models import Model
 
-from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
+from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import (
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,

llama_stack/providers/inline/memory/faiss/faiss.py

@@ -16,11 +16,14 @@ import faiss
 import numpy as np
 from numpy.typing import NDArray
 
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-
-from llama_stack.apis.memory import *  # noqa: F403
 from llama_stack.apis.inference import InterleavedContent
-from llama_stack.apis.memory_banks import MemoryBankType, VectorMemoryBank
+from llama_stack.apis.memory import (
+    Chunk,
+    Memory,
+    MemoryBankDocument,
+    QueryDocumentsResponse,
+)
+from llama_stack.apis.memory_banks import MemoryBank, MemoryBankType, VectorMemoryBank
 from llama_stack.providers.datatypes import Api, MemoryBanksProtocolPrivate
 from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.memory.vector_store import (

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

@@ -14,11 +14,10 @@ from enum import Enum
 from typing import Any, Callable, Dict, List
 
 import torch
-from llama_stack.apis.datasets import Datasets
-from llama_stack.apis.common.type_system import *  # noqa
 from llama_models.datatypes import Model
 from llama_models.sku_list import resolve_model
-from llama_stack.apis.common.type_system import ParamType
+from llama_stack.apis.common.type_system import ParamType, StringType
+from llama_stack.apis.datasets import Datasets
 
 from torchtune.models.llama3 import llama3_tokenizer, lora_llama3_8b
 from torchtune.models.llama3._tokenizer import Llama3Tokenizer

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

@@ -3,11 +3,26 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+from datetime import datetime
+from typing import Any, Dict, List, Optional
+
+from llama_models.schema_utils import webmethod
+
 from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.post_training import (
+    AlgorithmConfig,
+    DPOAlignmentConfig,
+    JobStatus,
+    LoraFinetuningConfig,
+    PostTrainingJob,
+    PostTrainingJobArtifactsResponse,
+    PostTrainingJobStatusResponse,
+    TrainingConfig,
+)
 from llama_stack.providers.inline.post_training.torchtune.config import (
     TorchtunePostTrainingConfig,
 )
-from llama_stack.apis.post_training import *  # noqa
 from llama_stack.providers.inline.post_training.torchtune.recipes.lora_finetuning_single_device import (
     LoraFinetuningSingleDevice,
 )

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

@@ -14,27 +14,33 @@ from typing import Any, Dict, List, Optional, Tuple
 import torch
 from llama_models.sku_list import resolve_model
 
+from llama_stack.apis.common.training_types import PostTrainingMetric
 from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.post_training import (
+    AlgorithmConfig,
+    Checkpoint,
+    LoraFinetuningConfig,
+    OptimizerConfig,
+    TrainingConfig,
+)
 
 from llama_stack.distribution.utils.config_dirs import DEFAULT_CHECKPOINT_DIR
-from llama_stack.providers.inline.post_training.torchtune.common.checkpointer import (
-    TorchtuneCheckpointer,
-)
-from torch import nn
-from torchtune import utils as torchtune_utils
-from torchtune.training.metric_logging import DiskLogger
-from tqdm import tqdm
-from llama_stack.apis.post_training import *  # noqa
+
 from llama_stack.distribution.utils.model_utils import model_local_dir
 
 from llama_stack.providers.inline.post_training.torchtune.common import utils
+from llama_stack.providers.inline.post_training.torchtune.common.checkpointer import (
+    TorchtuneCheckpointer,
+)
 from llama_stack.providers.inline.post_training.torchtune.config import (
     TorchtunePostTrainingConfig,
 )
 from llama_stack.providers.inline.post_training.torchtune.datasets.sft import SFTDataset
+from torch import nn
 from torch.optim import Optimizer
 from torch.utils.data import DataLoader, DistributedSampler
-from torchtune import modules, training
+from torchtune import modules, training, utils as torchtune_utils
 from torchtune.data import AlpacaToMessages, padded_collate_sft
 
 from torchtune.modules.loss import CEWithChunkedOutputLoss
@@ -47,6 +53,8 @@ from torchtune.modules.peft import (
     validate_missing_and_unexpected_for_lora,
 )
 from torchtune.training.lr_schedulers import get_cosine_schedule_with_warmup
+from torchtune.training.metric_logging import DiskLogger
+from tqdm import tqdm
 
 log = logging.getLogger(__name__)
 

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

@@ -7,8 +7,14 @@
 import logging
 from typing import Any, Dict, List
 
-from llama_stack.apis.safety import *  # noqa: F403
 from llama_stack.apis.inference import Message
+from llama_stack.apis.safety import (
+    RunShieldResponse,
+    Safety,
+    SafetyViolation,
+    ViolationLevel,
+)
+from llama_stack.apis.shields import Shield
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )

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

@@ -9,10 +9,24 @@ import re
 from string import Template
 from typing import Any, Dict, List, Optional
 
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_models.datatypes import CoreModelId
+from llama_models.llama3.api.datatypes import Role
+
 from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
+from llama_stack.apis.inference import (
+    ChatCompletionResponseEventType,
+    Inference,
+    Message,
+    UserMessage,
+)
+from llama_stack.apis.safety import (
+    RunShieldResponse,
+    Safety,
+    SafetyViolation,
+    ViolationLevel,
+)
+
+from llama_stack.apis.shields import Shield
 from llama_stack.distribution.datatypes import Api
 
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate

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

@@ -11,11 +11,16 @@ import torch
 
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
-from llama_stack.distribution.utils.model_utils import model_local_dir
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
-from llama_models.llama3.api.datatypes import *  # noqa: F403
+from llama_stack.apis.inference import Message
+from llama_stack.apis.safety import (
+    RunShieldResponse,
+    Safety,
+    SafetyViolation,
+    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 (
     interleaved_content_as_str,

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

@@ -3,14 +3,17 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from typing import List
+from typing import Any, Dict, List, Optional
 
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_stack.apis.scoring import *  # noqa: F403
-from llama_stack.apis.scoring_functions import *  # noqa: F403
-from llama_stack.apis.common.type_system import *  # noqa: F403
-from llama_stack.apis.datasetio import *  # noqa: F403
-from llama_stack.apis.datasets import *  # noqa: F403
+from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.scoring import (
+    ScoreBatchResponse,
+    ScoreResponse,
+    Scoring,
+    ScoringResult,
+)
+from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
 from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
 
 from .config import BasicScoringConfig

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

@@ -3,20 +3,23 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from typing import List
-
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_stack.apis.scoring import *  # noqa: F403
-from llama_stack.apis.scoring_functions import *  # noqa: F403
-from llama_stack.apis.common.type_system import *  # noqa: F403
-from llama_stack.apis.datasetio import *  # noqa: F403
-from llama_stack.apis.datasets import *  # noqa: F403
-
 import os
+from typing import Any, Dict, List, Optional
 
 from autoevals.llm import Factuality
 from autoevals.ragas import AnswerCorrectness
 
+from llama_stack.apis.datasetio import DatasetIO
+from llama_stack.apis.datasets import Datasets
+from llama_stack.apis.scoring import (
+    ScoreBatchResponse,
+    ScoreResponse,
+    Scoring,
+    ScoringResult,
+    ScoringResultRow,
+)
+from llama_stack.apis.scoring_functions import AggregationFunctionType, ScoringFn
+
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate
 

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

@@ -3,7 +3,9 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from llama_stack.apis.scoring import *  # noqa: F401, F403
+from typing import Any, Dict, Optional
+
+from pydantic import BaseModel, Field
 
 
 class BraintrustScoringConfig(BaseModel):

llama_stack/providers/inline/telemetry/meta_reference/telemetry.py

@@ -17,6 +17,22 @@ from opentelemetry.sdk.trace import TracerProvider
 from opentelemetry.sdk.trace.export import BatchSpanProcessor
 from opentelemetry.semconv.resource import ResourceAttributes
 
+from llama_stack.apis.telemetry import (
+    Event,
+    MetricEvent,
+    QueryCondition,
+    SpanEndPayload,
+    SpanStartPayload,
+    SpanStatus,
+    SpanWithStatus,
+    StructuredLogEvent,
+    Telemetry,
+    Trace,
+    UnstructuredLogEvent,
+)
+
+from llama_stack.distribution.datatypes import Api
+
 from llama_stack.providers.inline.telemetry.meta_reference.console_span_processor import (
     ConsoleSpanProcessor,
 )
@@ -27,10 +43,6 @@ from llama_stack.providers.inline.telemetry.meta_reference.sqlite_span_processor
 from llama_stack.providers.utils.telemetry.dataset_mixin import TelemetryDatasetMixin
 from llama_stack.providers.utils.telemetry.sqlite_trace_store import SQLiteTraceStore
 
-from llama_stack.apis.telemetry import *  # noqa: F403
-
-from llama_stack.distribution.datatypes import Api
-
 from .config import TelemetryConfig, TelemetrySink
 
 _GLOBAL_STORAGE = {

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

@@ -4,12 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from llama_stack.apis.telemetry import Telemetry
 from .config import SampleConfig
 
 
-from llama_stack.apis.telemetry import *  # noqa: F403
-
-
 class SampleTelemetryImpl(Telemetry):
     def __init__(self, config: SampleConfig):
         self.config = config