Python: bug fixes from graphrag insights (#10270)

### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Based on insights from the graphrag team, several bug fixes related to
data and model validators.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
For all cases of model_validator in before mode, there is no guarantee
that the data passed is a dict,
especially when a model is used as a field in another model, then a
string is passed to the before validator.
So in those cases we check before doing logic, otherwise just pass it on
and let Pydantic handle the invalid data.

Some small logic fixes in the vector store model decorator:
- updated docstring with the right exceptions
- additional checks on attributes
- additional checks on VectorFields with tests

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

Author: eavanvalkenburg

python/.vscode/tasks.json

@@ -135,7 +135,14 @@
         {
             "label": "Python: Tests - Code Coverage",
             "type": "shell",
-            "command": "uv run pytest --cov=semantic_kernel --cov-report=term-missing:skip-covered tests/unit/",
+            "command": "uv",
+            "args": [
+                "run",
+                "pytest",
+                "--cov=semantic_kernel",
+                "--cov-report=term-missing:skip-covered",
+                "tests/unit/"
+            ],
             "group": "test",
             "presentation": {
                 "reveal": "always",

python/semantic_kernel/agents/group_chat/broadcast_queue.py

@@ -4,6 +4,7 @@
 import asyncio
 from collections import deque
 from dataclasses import dataclass, field
+from typing import Any
 
 from pydantic import Field, SkipValidation, ValidationError, model_validator
 
@@ -28,11 +29,12 @@ def is_empty(self):
         return len(self.queue) == 0
 
     @model_validator(mode="before")
-    def validate_receive_task(cls, values):
+    def validate_receive_task(cls, values: Any):
         """Validate the receive task."""
-        receive_task = values.get("receive_task")
-        if receive_task is not None and not isinstance(receive_task, asyncio.Task):
-            raise ValidationError("receive_task must be an instance of asyncio.Task or None")
+        if isinstance(values, dict):
+            receive_task = values.get("receive_task")
+            if receive_task is not None and not isinstance(receive_task, asyncio.Task):
+                raise ValidationError("receive_task must be an instance of asyncio.Task or None")
         return values
 
 

python/semantic_kernel/connectors/ai/open_ai/prompt_execution_settings/open_ai_prompt_execution_settings.py

@@ -121,8 +121,10 @@ def validate_function_call(cls, v: str | list[dict[str, Any]] | None = None):
         return v
 
     @model_validator(mode="before")
-    def validate_response_format_and_set_flag(cls, values) -> Any:
+    def validate_response_format_and_set_flag(cls, values: Any) -> Any:
         """Validate the response_format and set structured_json_response accordingly."""
+        if not isinstance(values, dict):
+            return values
         response_format = values.get("response_format", None)
 
         if response_format is None:
@@ -153,7 +155,7 @@ def validate_response_format_and_set_flag(cls, values) -> Any:
 
     @model_validator(mode="before")
     @classmethod
-    def validate_function_calling_behaviors(cls, data) -> Any:
+    def validate_function_calling_behaviors(cls, data: Any) -> Any:
         """Check if function_call_behavior is set and if so, move to use function_choice_behavior instead."""
         # In an attempt to phase out the use of `function_call_behavior` in favor of `function_choice_behavior`,
         # we are syncing the `function_call_behavior` with `function_choice_behavior` if the former is set.

python/semantic_kernel/connectors/ai/prompt_execution_settings.py

@@ -38,14 +38,15 @@ class PromptExecutionSettings(KernelBaseModel):
 
     @model_validator(mode="before")
     @classmethod
-    def parse_function_choice_behavior(cls: type[_T], data: dict[str, Any]) -> dict[str, Any]:
+    def parse_function_choice_behavior(cls: type[_T], data: Any) -> dict[str, Any]:
         """Parse the function choice behavior data."""
-        function_choice_behavior_data = data.get("function_choice_behavior")
-        if function_choice_behavior_data:
-            if isinstance(function_choice_behavior_data, str):
-                data["function_choice_behavior"] = FunctionChoiceBehavior.from_string(function_choice_behavior_data)
-            elif isinstance(function_choice_behavior_data, dict):
-                data["function_choice_behavior"] = FunctionChoiceBehavior.from_dict(function_choice_behavior_data)
+        if isinstance(data, dict):
+            function_choice_behavior_data = data.get("function_choice_behavior")
+            if function_choice_behavior_data:
+                if isinstance(function_choice_behavior_data, str):
+                    data["function_choice_behavior"] = FunctionChoiceBehavior.from_string(function_choice_behavior_data)
+                elif isinstance(function_choice_behavior_data, dict):
+                    data["function_choice_behavior"] = FunctionChoiceBehavior.from_dict(function_choice_behavior_data)
         return data
 
     def __init__(self, service_id: str | None = None, **kwargs: Any):

python/semantic_kernel/connectors/memory/qdrant/qdrant_settings.py

@@ -26,9 +26,15 @@ class QdrantSettings(KernelBaseSettings):
     prefer_grpc: bool = False
 
     @model_validator(mode="before")
-    def validate_settings(cls, values):
+    def validate_settings(cls, values: dict):
         """Validate the settings."""
-        if "url" not in values and "host" not in values and "path" not in values and "location" not in values:
+        if (
+            isinstance(values, dict)
+            and "url" not in values
+            and "host" not in values
+            and "path" not in values
+            and "location" not in values
+        ):
             values["location"] = IN_MEMORY_STRING
         return values
 

python/semantic_kernel/connectors/memory/weaviate/weaviate_settings.py

@@ -39,24 +39,25 @@ class WeaviateSettings(KernelBaseSettings):
 
     @model_validator(mode="before")
     @classmethod
-    def validate_settings(cls, data: dict[str, Any]) -> dict[str, Any]:
+    def validate_settings(cls, data: Any) -> dict[str, Any]:
         """Validate Weaviate settings."""
-        enabled = sum([
-            cls.is_using_weaviate_cloud(data),
-            cls.is_using_local_weaviate(data),
-            cls.is_using_client_embedding(data),
-        ])
-
-        if enabled == 0:
-            raise ServiceInvalidExecutionSettingsError(
-                "Weaviate settings must specify either a ",
-                "Weaviate Cloud instance, a local Weaviate instance, or the client embedding options.",
-            )
-        if enabled > 1:
-            raise ServiceInvalidExecutionSettingsError(
-                "Weaviate settings must specify only one of the following: ",
-                "Weaviate Cloud instance, a local Weaviate instance, or the client embedding options.",
-            )
+        if isinstance(data, dict):
+            enabled = sum([
+                cls.is_using_weaviate_cloud(data),
+                cls.is_using_local_weaviate(data),
+                cls.is_using_client_embedding(data),
+            ])
+
+            if enabled == 0:
+                raise ServiceInvalidExecutionSettingsError(
+                    "Weaviate settings must specify either a ",
+                    "Weaviate Cloud instance, a local Weaviate instance, or the client embedding options.",
+                )
+            if enabled > 1:
+                raise ServiceInvalidExecutionSettingsError(
+                    "Weaviate settings must specify only one of the following: ",
+                    "Weaviate Cloud instance, a local Weaviate instance, or the client embedding options.",
+                )
 
         return data
 

python/semantic_kernel/contents/utils/data_uri.py

@@ -41,9 +41,9 @@ def update_data(self, value: str | bytes):
 
     @model_validator(mode="before")
     @classmethod
-    def _validate_data(cls, values: dict[str, Any]) -> dict[str, Any]:
+    def _validate_data(cls, values: Any) -> dict[str, Any]:
         """Validate the data."""
-        if not values.get("data_bytes") and not values.get("data_str"):
+        if isinstance(values, dict) and not values.get("data_bytes") and not values.get("data_str"):
             raise ContentInitializationError("Either data_bytes or data_str must be provided.")
         return values
 

python/semantic_kernel/data/filter_clauses/any_tags_equal_to_filter_clause.py

@@ -1,7 +1,7 @@
 # Copyright (c) Microsoft. All rights reserved.
 
 
-from pydantic import Field
+from typing import ClassVar
 
 from semantic_kernel.data.filter_clauses.filter_clause_base import FilterClauseBase
 from semantic_kernel.utils.experimental_decorator import experimental_class
@@ -16,4 +16,4 @@ class AnyTagsEqualTo(FilterClauseBase):
         value: The value to compare against the list of tags.
     """
 
-    filter_clause_type: str = Field("any_tags_equal_to", init=False)  # type: ignore
+    filter_clause_type: ClassVar[str] = "any_tags_equal_to"

python/semantic_kernel/data/filter_clauses/equal_to_filter_clause.py

@@ -1,6 +1,6 @@
 # Copyright (c) Microsoft. All rights reserved.
 
-from pydantic import Field
+from typing import ClassVar
 
 from semantic_kernel.data.filter_clauses.filter_clause_base import FilterClauseBase
 from semantic_kernel.utils.experimental_decorator import experimental_class
@@ -16,4 +16,4 @@ class EqualTo(FilterClauseBase):
 
     """
 
-    filter_clause_type: str = Field("equal_to", init=False)  # type: ignore
+    filter_clause_type: ClassVar[str] = "equal_to"

python/semantic_kernel/data/filter_clauses/filter_clause_base.py

@@ -2,9 +2,7 @@
 
 
 from abc import ABC
-from typing import Any
-
-from pydantic import Field
+from typing import Any, ClassVar
 
 from semantic_kernel.kernel_pydantic import KernelBaseModel
 from semantic_kernel.utils.experimental_decorator import experimental_class
@@ -14,6 +12,10 @@
 class FilterClauseBase(ABC, KernelBaseModel):
     """A base for all filter clauses."""
 
-    filter_clause_type: str = Field("FilterClauseBase", init=False)  # type: ignore
+    filter_clause_type: ClassVar[str] = "FilterClauseBase"
     field_name: str
     value: Any
+
+    def __str__(self) -> str:
+        """Return a string representation of the filter clause."""
+        return f"filter_clause_type='{self.filter_clause_type}' field_name='{self.field_name}' value='{self.value}'"