[remove import *][2/n] remove rest of import * in implementations (#690)

# What does this PR do?

- see https://github.com/meta-llama/llama-stack/pull/689
<img width="591" alt="image"
src="https://github.com/user-attachments/assets/76946a67-7373-43b5-8a03-0ad201aa543b"
/>

- leaving `tools/builtin.py` to avoid conflicts


## Test Plan

- see https://github.com/meta-llama/llama-stack/pull/689

## 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/remote/agents/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.agents import Agents
 from .config import SampleConfig
 
 
-from llama_stack.apis.agents import *  # noqa: F403
-
-
 class SampleAgentsImpl(Agents):
     def __init__(self, config: SampleConfig):
         self.config = config

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

@@ -5,11 +5,11 @@
 # the root directory of this source tree.
 from typing import Any, Dict, List, Optional
 
-from llama_stack.apis.datasetio import *  # noqa: F403
-
-
 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

@@ -4,8 +4,8 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import *  # noqa: F403
 import json
+from typing import AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
 
 from botocore.client import BaseClient
 from llama_models.datatypes import CoreModelId
@@ -13,6 +13,24 @@ from llama_models.llama3.api.chat_format import ChatFormat
 
 from llama_models.llama3.api.tokenizer import Tokenizer
 
+from llama_stack.apis.common.content_types import InterleavedContent
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ChatCompletionResponseStreamChunk,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+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,
@@ -29,11 +47,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )
 
-from llama_stack.apis.inference import *  # noqa: F403
-
-from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
-from llama_stack.providers.utils.bedrock.client import create_bedrock_client
-
 
 MODEL_ALIASES = [
     build_model_alias(

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

@@ -4,17 +4,31 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional, Union
 
 from cerebras.cloud.sdk import AsyncCerebras
 
+from llama_models.datatypes import CoreModelId
+
 from llama_models.llama3.api.chat_format import ChatFormat
 
 from llama_models.llama3.api.tokenizer import Tokenizer
 
-from llama_stack.apis.inference import *  # noqa: F403
-
-from llama_models.datatypes import CoreModelId
+from llama_stack.apis.common.content_types import InterleavedContent
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    CompletionRequest,
+    CompletionResponse,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
 
 from llama_stack.providers.utils.inference.model_registry import (
     build_model_alias,

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

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional
 
 from llama_models.datatypes import CoreModelId
 
@@ -14,7 +14,20 @@ from llama_models.llama3.api.tokenizer import Tokenizer
 
 from openai import OpenAI
 
-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,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
 
 from llama_stack.providers.utils.inference.model_registry import (
     build_model_alias,

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

@@ -11,7 +11,24 @@ from llama_models.datatypes import CoreModelId
 
 from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
-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,
+    CompletionRequest,
+    CompletionResponse,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    ResponseFormatType,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.utils.inference.model_registry import (
     build_model_alias,

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

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 import logging
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional, Union
 
 import httpx
 from llama_models.datatypes import CoreModelId
@@ -14,15 +14,33 @@ from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
 from ollama import AsyncClient
 
+from llama_stack.apis.common.content_types import (
+    ImageContentItem,
+    InterleavedContent,
+    TextContentItem,
+)
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    CompletionRequest,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+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,
     build_model_alias_with_just_provider_model_id,
     ModelRegistryHelper,
 )
-
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
-from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import (
     get_sampling_options,
     OpenAICompatCompletionChoice,

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

@@ -4,12 +4,11 @@
 # 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.inference import Inference
+from llama_stack.apis.models import Model
 from .config import SampleConfig
 
 
-from llama_stack.apis.inference import *  # noqa: F403
-
-
 class SampleInferenceImpl(Inference):
     def __init__(self, config: SampleConfig):
         self.config = config

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

@@ -13,10 +13,25 @@ from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import all_registered_models
 
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.models import *  # noqa: F403
+from llama_stack.apis.common.content_types import InterleavedContent
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    CompletionRequest,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    ResponseFormatType,
+    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.model_registry import (
     build_model_alias,
     ModelRegistryHelper,

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

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional, Union
 
 from llama_models.datatypes import CoreModelId
 
@@ -14,7 +14,22 @@ from llama_models.llama3.api.tokenizer import Tokenizer
 
 from together import Together
 
-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,
+    CompletionRequest,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    ResponseFormatType,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.utils.inference.model_registry import (
     build_model_alias,

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

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 import logging
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional, Union
 
 from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
@@ -13,7 +13,25 @@ from llama_models.sku_list import all_registered_models
 
 from openai import OpenAI
 
-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,
+    CompletionRequest,
+    CompletionResponse,
+    CompletionResponseStreamChunk,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    ResponseFormatType,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+from llama_stack.apis.models import Model, ModelType
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 
 from llama_stack.providers.utils.inference.model_registry import (

llama_stack/providers/remote/memory/chroma/chroma.py

@@ -12,8 +12,14 @@ from urllib.parse import urlparse
 import chromadb
 from numpy.typing import NDArray
 
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.memory_banks import MemoryBankType
+from llama_stack.apis.inference import InterleavedContent
+from llama_stack.apis.memory import (
+    Chunk,
+    Memory,
+    MemoryBankDocument,
+    QueryDocumentsResponse,
+)
+from llama_stack.apis.memory_banks import MemoryBank, MemoryBankType
 from llama_stack.providers.datatypes import Api, MemoryBanksProtocolPrivate
 from llama_stack.providers.inline.memory.chroma import ChromaInlineImplConfig
 from llama_stack.providers.utils.memory.vector_store import (

llama_stack/providers/remote/memory/pgvector/pgvector.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 import logging
-from typing import List, Tuple
+from typing import Any, Dict, List, Optional, Tuple
 
 import psycopg2
 from numpy.typing import NDArray
@@ -14,8 +14,14 @@ from psycopg2.extras import execute_values, Json
 
 from pydantic import BaseModel, parse_obj_as
 
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.memory_banks import MemoryBankType, VectorMemoryBank
+from llama_stack.apis.inference import InterleavedContent
+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.memory.vector_store import (

llama_stack/providers/remote/memory/qdrant/qdrant.py

@@ -6,16 +6,21 @@
 
 import logging
 import uuid
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional
 
 from numpy.typing import NDArray
 from qdrant_client import AsyncQdrantClient, models
 from qdrant_client.models import PointStruct
 
-from llama_stack.apis.memory_banks import *  # noqa: F403
+from llama_stack.apis.inference import InterleavedContent
+from llama_stack.apis.memory import (
+    Chunk,
+    Memory,
+    MemoryBankDocument,
+    QueryDocumentsResponse,
+)
+from llama_stack.apis.memory_banks import MemoryBank, MemoryBankType
 from llama_stack.providers.datatypes import Api, MemoryBanksProtocolPrivate
-from llama_stack.apis.memory import *  # noqa: F403
-
 from llama_stack.providers.remote.memory.qdrant.config import QdrantConfig
 from llama_stack.providers.utils.memory.vector_store import (
     BankWithIndex,

llama_stack/providers/remote/memory/sample/sample.py

@@ -4,12 +4,11 @@
 # 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.memory import Memory
+from llama_stack.apis.memory_banks import MemoryBank
 from .config import SampleConfig
 
 
-from llama_stack.apis.memory import *  # noqa: F403
-
-
 class SampleMemoryImpl(Memory):
     def __init__(self, config: SampleConfig):
         self.config = config

llama_stack/providers/remote/memory/weaviate/weaviate.py

@@ -14,8 +14,14 @@ from numpy.typing import NDArray
 from weaviate.classes.init import Auth
 from weaviate.classes.query import Filter
 
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.memory_banks import MemoryBankType
+from llama_stack.apis.common.content_types import InterleavedContent
+from llama_stack.apis.memory import (
+    Chunk,
+    Memory,
+    MemoryBankDocument,
+    QueryDocumentsResponse,
+)
+from llama_stack.apis.memory_banks import MemoryBank, MemoryBankType
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import Api, MemoryBanksProtocolPrivate
 from llama_stack.providers.utils.memory.vector_store import (

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

@@ -9,8 +9,15 @@ import logging
 
 from typing import Any, Dict, List
 
-from llama_stack.apis.safety import *  # noqa
-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.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.bedrock.client import create_bedrock_client
 

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

@@ -4,12 +4,11 @@
 # 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.safety import Safety
+from llama_stack.apis.shields import Shield
 from .config import SampleConfig
 
 
-from llama_stack.apis.safety import *  # noqa: F403
-
-
 class SampleSafetyImpl(Safety):
     def __init__(self, config: SampleConfig):
         self.config = config