[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/utils/inference/openai_compat.py

@@ -4,17 +4,28 @@
 # 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, Optional
+from typing import AsyncGenerator, List, Optional
 
 from llama_models.llama3.api.chat_format import ChatFormat
 
-from llama_models.llama3.api.datatypes import StopReason
-
-from llama_stack.apis.inference import *  # noqa: F403
+from llama_models.llama3.api.datatypes import SamplingParams, StopReason
 from pydantic import BaseModel
 
 from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
 
+from llama_stack.apis.inference import (
+    ChatCompletionResponse,
+    ChatCompletionResponseEvent,
+    ChatCompletionResponseEventType,
+    ChatCompletionResponseStreamChunk,
+    CompletionMessage,
+    CompletionResponse,
+    CompletionResponseStreamChunk,
+    Message,
+    ToolCallDelta,
+    ToolCallParseStatus,
+)
+
 from llama_stack.providers.utils.inference.prompt_adapter import (
     convert_image_content_to_url,
 )

llama_stack/providers/utils/kvstore/kvstore.py

@@ -4,8 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .api import *  # noqa: F403
-from .config import *  # noqa: F403
+from typing import List, Optional
+
+from .api import KVStore
+from .config import KVStoreConfig, KVStoreType
 
 
 def kvstore_dependencies():

llama_stack/providers/utils/kvstore/redis/redis.py

@@ -9,7 +9,7 @@ from typing import List, Optional
 
 from redis.asyncio import Redis
 
-from ..api import *  # noqa: F403
+from ..api import KVStore
 from ..config import RedisKVStoreConfig
 
 

llama_stack/providers/utils/kvstore/sqlite/sqlite.py

@@ -11,7 +11,7 @@ from typing import List, Optional
 
 import aiosqlite
 
-from ..api import *  # noqa: F403
+from ..api import KVStore
 from ..config import SqliteKVStoreConfig
 
 

llama_stack/providers/utils/memory/vector_store.py

@@ -15,14 +15,17 @@ from urllib.parse import unquote
 import chardet
 import httpx
 import numpy as np
+
+from llama_models.llama3.api.tokenizer import Tokenizer
 from numpy.typing import NDArray
 from pypdf import PdfReader
 
-from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_models.llama3.api.tokenizer import Tokenizer
-
-from llama_stack.apis.common.content_types import InterleavedContent, TextContentItem
-from llama_stack.apis.memory import *  # noqa: F403
+from llama_stack.apis.common.content_types import (
+    InterleavedContent,
+    TextContentItem,
+    URL,
+)
+from llama_stack.apis.memory import Chunk, MemoryBankDocument, QueryDocumentsResponse
 from llama_stack.apis.memory_banks import VectorMemoryBank
 from llama_stack.providers.datatypes import Api
 from llama_stack.providers.utils.inference.prompt_adapter import (

llama_stack/providers/utils/telemetry/tracing.py

@@ -12,10 +12,18 @@ import threading
 import uuid
 from datetime import datetime
 from functools import wraps
-from typing import Any, Callable, Dict, List
+from typing import Any, Callable, Dict, List, Optional
 
-
-from llama_stack.apis.telemetry import *  # noqa: F403
+from llama_stack.apis.telemetry import (
+    LogSeverity,
+    Span,
+    SpanEndPayload,
+    SpanStartPayload,
+    SpanStatus,
+    StructuredLogEvent,
+    Telemetry,
+    UnstructuredLogEvent,
+)
 from llama_stack.providers.utils.telemetry.trace_protocol import serialize_value
 
 log = logging.getLogger(__name__)