Merge branch 'issues/10493-audio-content-openai' of https://github.com/rogerbarreto/semantic-kernel into issues/10493-audio-content-openai

Author: RogerBarreto

.github/workflows/label-needs-port.yml

@@ -21,21 +21,39 @@ jobs:
     steps:
       - name: Create dotnet issue
         if: contains(github.event.pull_request.labels.*.name, 'needs_port_to_dotnet') || contains(github.event.issue.labels.*.name, 'needs_port_to_dotnet')
+        env:
+          ORIGINAL_URL: ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
+          ORIGINAL_BODY: ${{ github.event.issue.body || github.event.pull_request.body }}
+          ORIGINAL_TITLE: ${{ github.event.issue.title || github.event.pull_request.title }}
+          ORIGINAL_NUMBER: ${{ github.event.issue.number || github.event.pull_request.number }}
         run: |
+          {
+           echo "# Original issue"
+           echo "$ORIGINAL_URL"
+           echo "## Description"
+           echo "$ORIGINAL_BODY"
+           echo "\n Relates to #$ORIGINAL_NUMBER"
+          } > issue_body.md
           new_issue_url=$(gh issue create \
             --title "Port python feature: ${{ github.event.issue.title || github.event.pull_request.title }}" \
             --label ".NET" \
-            --body "# Original issue
-            ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
-            ## Description
-            ${{ github.event.issue.body || github.event.pull_request.body }}")
+            --body-file issue_body.md)
       - name: Create python issue
         if: contains(github.event.pull_request.labels.*.name, 'needs_port_to_python') || contains(github.event.issue.labels.*.name, 'needs_port_to_python')
+        env:
+          ORIGINAL_URL: ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
+          ORIGINAL_BODY: ${{ github.event.issue.body || github.event.pull_request.body }}
+          ORIGINAL_TITLE: ${{ github.event.issue.title || github.event.pull_request.title }}
+          ORIGINAL_NUMBER: ${{ github.event.issue.number || github.event.pull_request.number }}
         run: |
+          {
+           echo "# Original issue"
+           echo "$ORIGINAL_URL"
+           echo "## Description"
+           echo "$ORIGINAL_BODY"
+           echo "\n Relates to #$ORIGINAL_NUMBER"
+          } > issue_body.md
           new_issue_url=$(gh issue create \
             --title "Port dotnet feature: ${{ github.event.issue.title || github.event.pull_request.title }}" \
             --label "python" \
-            --body "# Original issue
-            ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
-            ## Description
-            ${{ github.event.issue.body || github.event.pull_request.body }}")
+            --body-file issue_body.md)

dotnet/src/SemanticKernel.Abstractions/AI/ChatCompletion/AIFunctionKernelFunction.cs

@@ -66,6 +66,8 @@ private static IReadOnlyList<KernelParameterMetadata> MapParameterMetadata(AIFun
             return Array.Empty<KernelParameterMetadata>();
         }
 
+        HashSet<string>? requiredParameters = GetRequiredParameterNames(aiFunction.JsonSchema);
+
         List<KernelParameterMetadata> kernelParams = [];
         var parameterInfos = aiFunction.UnderlyingMethod?.GetParameters().ToDictionary(p => p.Name!, StringComparer.Ordinal);
         foreach (var param in properties.EnumerateObject())
@@ -76,7 +78,7 @@ private static IReadOnlyList<KernelParameterMetadata> MapParameterMetadata(AIFun
             {
                 Description = param.Value.TryGetProperty("description", out JsonElement description) ? description.GetString() : null,
                 DefaultValue = param.Value.TryGetProperty("default", out JsonElement defaultValue) ? defaultValue : null,
-                IsRequired = param.Value.TryGetProperty("required", out JsonElement required) && required.GetBoolean(),
+                IsRequired = requiredParameters?.Contains(param.Name) ?? false,
                 ParameterType = paramInfo?.ParameterType,
                 Schema = param.Value.TryGetProperty("schema", out JsonElement schema)
                     ? new KernelJsonSchema(schema)
@@ -86,4 +88,25 @@ private static IReadOnlyList<KernelParameterMetadata> MapParameterMetadata(AIFun
 
         return kernelParams;
     }
+
+    /// <summary>
+    /// Gets the names of the required parameters from the AI function's JSON schema.
+    /// </summary>
+    /// <param name="schema">The JSON schema of the AI function.</param>
+    /// <returns>The names of the required parameters.</returns>
+    private static HashSet<string>? GetRequiredParameterNames(JsonElement schema)
+    {
+        HashSet<string>? requiredParameterNames = null;
+
+        if (schema.TryGetProperty("required", out JsonElement requiredElement) && requiredElement.ValueKind == JsonValueKind.Array)
+        {
+            foreach (var node in requiredElement.EnumerateArray())
+            {
+                requiredParameterNames ??= [];
+                requiredParameterNames.Add(node.GetString()!);
+            }
+        }
+
+        return requiredParameterNames;
+    }
 }

dotnet/src/SemanticKernel.UnitTests/AI/ChatCompletion/AIFunctionKernelFunctionTests.cs

@@ -0,0 +1,28 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using System.Linq;
+using Microsoft.Extensions.AI;
+using Microsoft.SemanticKernel;
+using Microsoft.SemanticKernel.ChatCompletion;
+using Xunit;
+
+namespace SemanticKernel.UnitTests.AI.ChatCompletion;
+
+public class AIFunctionKernelFunctionTests
+{
+    [Fact]
+    public void ShouldAssignIsRequiredParameterMetadataPropertyCorrectly()
+    {
+        // Arrange and Act
+        AIFunction aiFunction = AIFunctionFactory.Create((string p1, int? p2 = null) => p1);
+
+        AIFunctionKernelFunction sut = new(aiFunction);
+
+        // Assert
+        KernelParameterMetadata? p1Metadata = sut.Metadata.Parameters.FirstOrDefault(p => p.Name == "p1");
+        Assert.True(p1Metadata?.IsRequired);
+
+        KernelParameterMetadata? p2Metadata = sut.Metadata.Parameters.FirstOrDefault(p => p.Name == "p2");
+        Assert.False(p2Metadata?.IsRequired);
+    }
+}

dotnet/src/SemanticKernel.UnitTests/SemanticKernel.UnitTests.csproj

@@ -24,7 +24,7 @@
     </PackageReference>
     <PackageReference Include="Microsoft.ML.Tokenizers" />
     <PackageReference Include="Microsoft.Extensions.Logging.Console" />
-    <PackageReference Include="Microsoft.Extensions.Logging.Abstractions" />
+    <PackageReference Include="Microsoft.Extensions.AI" />
   </ItemGroup>
 
   <ItemGroup>

python/pyproject.toml

@@ -25,7 +25,7 @@ classifiers = [
 dependencies = [
     "aiohttp ~= 3.8",
     "cloudevents ~=1.0",
-    "pydantic >=2.0,<2.11,!=2.10.0,!=2.10.1,!=2.10.2,!=2.10.3",
+    "pydantic >=2.0,!=2.10.0,!=2.10.1,!=2.10.2,!=2.10.3,<2.12",
     "pydantic-settings ~= 2.0",
     "defusedxml ~= 0.7",
     # azure identity
@@ -76,7 +76,7 @@ faiss = [
 ]
 hugging_face = [
     "transformers[torch] ~= 4.28",
-    "sentence-transformers >= 2.2,< 4.0",
+    "sentence-transformers >= 2.2,< 5.0",
     "torch == 2.6.0"
 ]
 mongo = [

python/samples/concepts/agents/chat_completion_agent/chat_completion_agent_function_termination.py

@@ -99,8 +99,7 @@ async def main():
     print("================================")
 
     # 4. Print out the chat history to view the different types of messages
-    chat_history = await thread.get_messages()
-    for message in chat_history.messages:
+    async for message in thread.get_messages():
         _write_content(message)
 
     """

python/samples/concepts/agents/chat_completion_agent/chat_completion_agent_summary_history_reducer_single_agent.py

@@ -3,14 +3,9 @@
 import asyncio
 import logging
 
-from semantic_kernel.agents import (
-    ChatCompletionAgent,
-    ChatHistoryAgentThread,
-)
+from semantic_kernel.agents import ChatCompletionAgent, ChatHistoryAgentThread
 from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
-from semantic_kernel.contents import (
-    ChatHistorySummarizationReducer,
-)
+from semantic_kernel.contents import ChatHistorySummarizationReducer
 
 """
 The following sample demonstrates how to implement a truncation chat 
@@ -55,14 +50,13 @@ async def main():
         # Attempt reduction
         is_reduced = await thread.reduce()
         if is_reduced:
-            print(f"@ History reduced to {len(thread.messages)} messages.")
+            print(f"@ History reduced to {len(thread)} messages.")
 
-        print(f"@ Message Count: {len(thread.messages)}\n")
+        print(f"@ Message Count: {len(thread)}\n")
 
         # If reduced, print summary if present
         if is_reduced:
-            chat_history = await thread.get_messages()
-            for msg in chat_history.messages:
+            async for msg in thread.get_messages():
                 if msg.metadata and msg.metadata.get("__summary__"):
                     print(f"\tSummary: {msg.content}")
                     break

python/samples/concepts/caching/semantic_caching.py

@@ -7,25 +7,22 @@
 from typing import Annotated
 from uuid import uuid4
 
+from semantic_kernel import Kernel
 from semantic_kernel.connectors.ai.embedding_generator_base import EmbeddingGeneratorBase
-from semantic_kernel.connectors.ai.open_ai.services.open_ai_chat_completion import OpenAIChatCompletion
-from semantic_kernel.connectors.ai.open_ai.services.open_ai_text_embedding import OpenAITextEmbedding
+from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion, OpenAITextEmbedding
 from semantic_kernel.connectors.memory.in_memory.in_memory_store import InMemoryVectorStore
-from semantic_kernel.data.record_definition import vectorstoremodel
-from semantic_kernel.data.record_definition.vector_store_record_fields import (
+from semantic_kernel.data import (
+    VectorizedSearchMixin,
+    VectorSearchOptions,
+    VectorStore,
+    VectorStoreRecordCollection,
     VectorStoreRecordDataField,
     VectorStoreRecordKeyField,
     VectorStoreRecordVectorField,
+    vectorstoremodel,
 )
-from semantic_kernel.data.vector_search.vector_search_options import VectorSearchOptions
-from semantic_kernel.data.vector_search.vectorized_search import VectorizedSearchMixin
-from semantic_kernel.data.vector_storage.vector_store import VectorStore
-from semantic_kernel.data.vector_storage.vector_store_record_collection import VectorStoreRecordCollection
-from semantic_kernel.filters.filter_types import FilterTypes
-from semantic_kernel.filters.functions.function_invocation_context import FunctionInvocationContext
-from semantic_kernel.filters.prompts.prompt_render_context import PromptRenderContext
-from semantic_kernel.functions.function_result import FunctionResult
-from semantic_kernel.kernel import Kernel
+from semantic_kernel.filters import FilterTypes, FunctionInvocationContext, PromptRenderContext
+from semantic_kernel.functions import FunctionResult
 
 COLLECTION_NAME = "llm_responses"
 RECORD_ID_KEY = "cache_record_id"

python/samples/concepts/chat_history/store_chat_history_in_cosmosdb.py

@@ -6,19 +6,18 @@
 
 from samples.concepts.setup.chat_completion_services import Services, get_chat_completion_service_and_request_settings
 from semantic_kernel import Kernel
-from semantic_kernel.connectors.ai.function_choice_behavior import FunctionChoiceBehavior
+from semantic_kernel.connectors.ai import FunctionChoiceBehavior
 from semantic_kernel.connectors.memory.azure_cosmos_db.azure_cosmos_db_no_sql_store import AzureCosmosDBNoSQLStore
-from semantic_kernel.contents import ChatHistory
-from semantic_kernel.contents.chat_message_content import ChatMessageContent
+from semantic_kernel.contents import ChatHistory, ChatMessageContent
 from semantic_kernel.core_plugins.math_plugin import MathPlugin
 from semantic_kernel.core_plugins.time_plugin import TimePlugin
-from semantic_kernel.data.record_definition.vector_store_model_decorator import vectorstoremodel
-from semantic_kernel.data.record_definition.vector_store_record_fields import (
+from semantic_kernel.data import (
+    VectorStore,
+    VectorStoreRecordCollection,
     VectorStoreRecordDataField,
     VectorStoreRecordKeyField,
+    vectorstoremodel,
 )
-from semantic_kernel.data.vector_storage.vector_store import VectorStore
-from semantic_kernel.data.vector_storage.vector_store_record_collection import VectorStoreRecordCollection
 
 """
 This sample demonstrates how to build a conversational chatbot

python/samples/concepts/memory/azure_ai_search_hotel_samples/step_1_interact_with_the_collection.py

@@ -2,6 +2,12 @@
 
 import asyncio
 
+from step_0_data_model import HotelSampleClass
+
+from semantic_kernel import Kernel
+from semantic_kernel.connectors.ai.open_ai import OpenAITextEmbedding
+from semantic_kernel.connectors.memory.azure_ai_search import AzureAISearchCollection
+
 ###
 # The data model used for this sample is based on the hotel data model from the Azure AI Search samples.
 # When deploying a new index in Azure AI Search using the import wizard you can choose to deploy the 'hotel-samples'
@@ -13,24 +19,19 @@
 # This sample assumes the index is deployed, the vector fields can be empty.
 # If the vector fields are empty, change the first_run parameter to True to add the vectors.
 ###
-from step_0_data_model import HotelSampleClass
-
-from semantic_kernel import Kernel
-from semantic_kernel.connectors.ai.open_ai import OpenAITextEmbedding
-from semantic_kernel.connectors.memory.azure_ai_search import AzureAISearchCollection
 from semantic_kernel.data import (
     VectorSearchOptions,
-    VectorStoreRecordUtils,
 )
+from semantic_kernel.data.vector_search import add_vector_to_records
 
 first_run = False
 
 # Note: you may need to update this `collection_name` depending upon how your index is named.
 COLLECTION_NAME = "hotels-sample-index"
 
 
-async def add_vectors(collection: AzureAISearchCollection, vectorizer: VectorStoreRecordUtils):
-    """This is a simple function that uses the VectorStoreRecordUtils to add vectors to the records in the collection.
+async def add_vectors(collection: AzureAISearchCollection, kernel: Kernel):
+    """This is a simple function that uses the add_vector_to_records function to add vectors.
 
     It first uses the search_client within the collection to get a list of ids.
     and then uses the upsert to add the vectors to the records.
@@ -42,7 +43,7 @@ async def add_vectors(collection: AzureAISearchCollection, vectorizer: VectorSto
     if hotels is not None and isinstance(hotels, list):
         for hotel in hotels:
             if not hotel.description_vector or not hotel.description_fr_vector:
-                hotel = await vectorizer.add_vector_to_records(hotel, HotelSampleClass)
+                hotel = await add_vector_to_records(kernel, hotel, HotelSampleClass)
                 await collection.upsert(hotel)
 
 
@@ -52,10 +53,8 @@ async def main(query: str, first_run: bool = False):
     # Add the OpenAI text embedding service
     embeddings = OpenAITextEmbedding(service_id="embedding", ai_model_id="text-embedding-3-small")
     kernel.add_service(embeddings)
-    # Create the VectorStoreRecordUtils object
-    vectorizer = VectorStoreRecordUtils(kernel)
     # Create the Azure AI Search collection
-    collection = AzureAISearchCollection[HotelSampleClass](
+    collection = AzureAISearchCollection[str, HotelSampleClass](
         collection_name=COLLECTION_NAME, data_model_type=HotelSampleClass
     )
     # Check if the collection exists.
@@ -71,7 +70,7 @@ async def main(query: str, first_run: bool = False):
 
     # If it is the first run and there are no vectors, add them.
     if first_run:
-        await add_vectors(collection, vectorizer)
+        await add_vectors(collection, kernel)
 
     # Search using just text, by default this will search all the searchable text fields in the index.
     results = await collection.text_search(search_text=query)