fix: resolve type hint issues and import dependencies

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

@@ -231,7 +231,7 @@ def worker_process_entrypoint(
     while True:
         try:
             task = req_gen.send(result)
-            if isinstance(task, str) and task == _END_SENTINEL:
+            if isinstance(task, str) and task == EndSentinel():
                 break
 
             assert isinstance(task, TaskRequest)

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

@@ -12,6 +12,7 @@
 from typing import Any, Dict, List, Optional
 
 import torch
+from fairscale.nn.model_parallel.initialize import get_model_parallel_rank
 from fairscale.nn.model_parallel.layers import ColumnParallelLinear, RowParallelLinear
 from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
 from llama_models.llama3.api.args import ModelArgs

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

@@ -73,7 +73,10 @@ def show():
         image_data.append({"image_base64": image_base64})
         buf.close()
 
-    req_con, resp_con = _open_connections()
+    # The _open_connections method is dynamically made available to
+    # the interpreter by bundling code from "code_env_prefix.py" -- by literally prefixing it -- and
+    # then "eval"ing it within a sandboxed interpreter.
+    req_con, resp_con = _open_connections()  # noqa: F821
 
     _json_dump = _json.dumps(
         {

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

@@ -24,6 +24,7 @@
     SamplingParams,
     TextTruncation,
     ToolChoice,
+    ToolConfig,
     ToolDefinition,
     ToolPromptFormat,
 )

llama_stack/providers/tests/post_training/test_post_training.py

@@ -3,6 +3,8 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+from typing import List
+
 import pytest
 
 from llama_stack.apis.common.job_types import JobStatus

llama_stack/providers/utils/inference/embedding_mixin.py

@@ -5,7 +5,10 @@
 # the root directory of this source tree.
 
 import logging
-from typing import List, Optional
+from typing import TYPE_CHECKING, List, Optional
+
+if TYPE_CHECKING:
+    from sentence_transformers import SentenceTransformer
 
 from llama_stack.apis.inference import (
     EmbeddingsResponse,
@@ -40,7 +43,7 @@ async def embeddings(
         )
         return EmbeddingsResponse(embeddings=embeddings)
 
-    def _load_sentence_transformer_model(self, model: str) -> "SentenceTransformer":
+    def _load_sentence_transformer_model(self, model: str) -> SentenceTransformer:
         global EMBEDDING_MODELS
 
         loaded_model = EMBEDDING_MODELS.get(model)

pyproject.toml

@@ -129,7 +129,6 @@ ignore = [
     "E721",
     "E741",
     "F405",
-    "F821",
     "F841",
     "C408", # ignored because we like the dict keyword argument syntax
     "E302",