feat: Updated

Author: HavenDV

docs/index.md

@@ -24,12 +24,12 @@ Examples and documentation can be found here: https://tryagi.github.io/OpenAI/
 using var api = new OpenAiApi("API_KEY");
 string response = await api.Chat.CreateChatCompletionAsync(
     messages: ["Generate five random words."],
-    model: CreateChatCompletionRequestModel.Gpt4oMini);
+    model: ModelIdsEnum.Gpt4oMini);
 Console.WriteLine(response); // "apple, banana, cherry, date, elderberry"
 
 var enumerable = api.Chat.CreateChatCompletionAsStreamAsync(
     messages: ["Generate five random words."],
-    model: CreateChatCompletionRequestModel.Gpt4oMini);
+    model: ModelIdsEnum.Gpt4oMini);
 
 await foreach (string response in enumerable)
 {
@@ -96,7 +96,7 @@ var messages = new List<ChatCompletionRequestMessage>
     "You are a helpful weather assistant.".AsSystemMessage(),
     "What is the current temperature in Dubai, UAE in Celsius?".AsUserMessage(),
 };
-var model = CreateChatCompletionRequestModel.Gpt4oMini;
+var model = ModelIdsEnum.Gpt4oMini;
 var result = await api.Chat.CreateChatCompletionAsync(
     messages,
     model: model,
@@ -141,7 +141,7 @@ using var api = new OpenAiApi("API_KEY");
 
 var response = await api.Chat.CreateChatCompletionAsAsync<Weather>(
     messages: ["Generate random weather."],
-    model: CreateChatCompletionRequestModel.Gpt4oMini,
+    model: ModelIdsEnum.Gpt4oMini,
     jsonSerializerOptions: new JsonSerializerOptions
     {
         Converters = {new JsonStringEnumConverter()},
@@ -150,7 +150,7 @@ var response = await api.Chat.CreateChatCompletionAsAsync<Weather>(
 var response = await api.Chat.CreateChatCompletionAsAsync(
     jsonTypeInfo: SourceGeneratedContext.Default.Weather,
     messages: ["Generate random weather."],
-    model: CreateChatCompletionRequestModel.Gpt4oMini);
+    model: ModelIdsEnum.Gpt4oMini);
 
 // response.Value1 contains the structured output
 // response.Value2 contains the CreateChatCompletionResponse object
@@ -198,10 +198,10 @@ There also non-try methods that throw an exception if the value is not found.
 using OpenAI;
 
 // You can try to get the enum from string using:
-var model = CreateChatCompletionRequestModelExtensions.ToEnum("gpt-4o") ?? throw new Exception("Invalid model");
+var model = ModelIdsEnumExtensions.ToEnum("gpt-4o") ?? throw new Exception("Invalid model");
 
 // Chat
-var model = CreateChatCompletionRequestModel.Gpt4oMini;
+var model = ModelIdsEnum.Gpt4oMini;
 double? priceInUsd = model.TryGetPriceInUsd(
     inputTokens: 500,
     outputTokens: 500)

docs/samples/Chat.ChatWithVision.md

@@ -6,7 +6,7 @@ CreateChatCompletionResponse response = await api.Chat.CreateChatCompletionAsync
         "Please describe the following image.",
         H.Resources.images_dog_and_cat_png.AsBytes().AsUserMessage(mimeType: "image/png"),
     ],
-    model: CreateChatCompletionRequestModel.Gpt4o);
+    model: ModelIdsEnum.Gpt4o);
 
 Console.WriteLine("[ASSISTANT]:");
 Console.WriteLine($"{response.Choices[0].Message.Content}");

docs/samples/Chat.FunctionCalling.md

@@ -15,7 +15,7 @@ do
     requiresAction = false;
     CreateChatCompletionResponse chatCompletion = await api.Chat.CreateChatCompletionAsync(
         messages,
-        model: CreateChatCompletionRequestModel.Gpt4o20240806,
+        model: ModelIdsEnum.Gpt4o20240806,
         tools: tools);
 
     switch (chatCompletion.Choices[0].FinishReason)

docs/samples/Chat.FunctionCallingStreaming.md

@@ -20,7 +20,7 @@ do
     IAsyncEnumerable<CreateChatCompletionStreamResponse> chatUpdates
         = api.Chat.CreateChatCompletionAsStreamAsync(
             messages,
-            model: CreateChatCompletionRequestModel.Gpt4o20240806,
+            model: ModelIdsEnum.Gpt4o20240806,
             tools: tools);
 
     await foreach (CreateChatCompletionStreamResponse chatUpdate in chatUpdates)

docs/samples/Chat.SimpleChat.md

@@ -3,7 +3,7 @@ using var api = GetAuthenticatedClient();
 
 CreateChatCompletionResponse response = await api.Chat.CreateChatCompletionAsync(
     messages: ["Say 'this is a test.'"],
-    model: CreateChatCompletionRequestModel.Gpt4o);
+    model: ModelIdsEnum.Gpt4o);
 
 Console.WriteLine("[ASSISTANT]:");
 Console.WriteLine($"{response.Choices[0].Message.Content}");

docs/samples/Chat.SimpleChatStreaming.md

@@ -3,7 +3,7 @@ using var api = GetAuthenticatedClient();
 
 IAsyncEnumerable<CreateChatCompletionStreamResponse> enumerable = api.Chat.CreateChatCompletionAsStreamAsync(
     messages: ["Say 'this is a test.'"],
-    model: CreateChatCompletionRequestModel.Gpt4o);
+    model: ModelIdsEnum.Gpt4o);
 
 Console.WriteLine("[ASSISTANT]:");
 await foreach (CreateChatCompletionStreamResponse chatUpdate in enumerable)

docs/samples/Chat.StructuredOutputs.md

@@ -3,7 +3,7 @@ using var api = GetAuthenticatedClient();
 
 MathReasoning? mathReasoning = await api.Chat.CreateChatCompletionAsAsync<MathReasoning>(
     messages: ["How can I solve 8x + 7 = -23?"],
-    model: CreateChatCompletionRequestModel.Gpt4o20240806,
+    model: ModelIdsEnum.Gpt4o20240806,
     strict: true);
 
 Console.WriteLine($"Final answer: {mathReasoning?.FinalAnswer}");

docs/samples/Combination.CuriousCreatureCreator.md

@@ -3,7 +3,7 @@ using var api = GetAuthenticatedClient();
 
 // First, we'll use gpt-4o to have a creative helper imagine a twist on a household pet
 CreateChatCompletionResponse creativeWriterResult = await api.Chat.CreateChatCompletionAsync(
-    model: CreateChatCompletionRequestModel.Gpt4o,
+    model: ModelIdsEnum.Gpt4o,
     messages:
     [
         "You're a creative helper that specializes in brainstorming designs for concepts that fuse ordinary, mundane items with a fantastical touch. In particular, you can provide good one-paragraph descriptions of concept images.".AsSystemMessage(),

src/libs/tryAGI.OpenAI/AssistantClient.CreateRun.AsStream.cs

@@ -118,6 +118,15 @@ public partial class AssistantsClient
         /// The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.<br/>
         /// Example: gpt-4o
         /// </param>
+        /// <param name="reasoningEffort">
+        /// **o-series models only** <br/>
+        /// Constrains effort on reasoning for <br/>
+        /// [reasoning models](https://platform.openai.com/docs/guides/reasoning).<br/>
+        /// Currently supported values are `low`, `medium`, and `high`. Reducing<br/>
+        /// reasoning effort can result in faster responses and fewer tokens used<br/>
+        /// on reasoning in a response.<br/>
+        /// Default Value: medium
+        /// </param>
         /// <param name="instructions">
         /// Overrides the [instructions](/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis.
         /// </param>
@@ -131,15 +140,20 @@ public partial class AssistantsClient
         /// Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
         /// </param>
         /// <param name="metadata">
-        /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.
+        /// Set of 16 key-value pairs that can be attached to an object. This can be<br/>
+        /// useful for storing additional information about the object in a structured<br/>
+        /// format, and querying for objects via API or the dashboard. <br/>
+        /// Keys are strings with a maximum length of 64 characters. Values are strings<br/>
+        /// with a maximum length of 512 characters.
         /// </param>
         /// <param name="temperature">
-        /// empty<br/>
+        /// What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.<br/>
         /// Default Value: 1<br/>
         /// Example: 1
         /// </param>
         /// <param name="topP">
-        /// empty<br/>
+        /// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.<br/>
+        /// We generally recommend altering this or temperature but not both.<br/>
         /// Default Value: 1<br/>
         /// Example: 1
         /// </param>
@@ -152,52 +166,49 @@ public partial class AssistantsClient
         /// <param name="maxCompletionTokens">
         /// The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info.
         /// </param>
-        /// <param name="truncationStrategy">
-        /// Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.
-        /// </param>
-        /// <param name="toolChoice">
-        /// Controls which (if any) tool is called by the model.<br/>
-        /// `none` means the model will not call any tools and instead generates a message.<br/>
-        /// `auto` is the default value and means the model can pick between generating a message or calling one or more tools.<br/>
-        /// `required` means the model must call one or more tools before responding to the user.<br/>
-        /// Specifying a particular tool like `{"type": "file_search"}` or `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool.
-        /// </param>
+        /// <param name="truncationStrategy"></param>
+        /// <param name="toolChoice"></param>
         /// <param name="parallelToolCalls">
-        /// Whether to enable [parallel function calling](/docs/guides/function-calling/parallel-function-calling) during tool use.
+        /// Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use.
         /// </param>
         /// <param name="responseFormat">
-        /// Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models/gpt-4o), [GPT-4 Turbo](/docs/models/gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.<br/>
-        /// Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which guarantees the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](/docs/guides/structured-outputs).<br/>
-        /// Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON.<br/>
+        /// Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.<br/>
+        /// Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](/docs/guides/structured-outputs).<br/>
+        /// Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the message the model generates is valid JSON.<br/>
         /// **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length.
         /// </param>
         /// <param name="cancellationToken">The token to cancel the operation with</param>
         /// <exception cref="global::System.InvalidOperationException"></exception>
+#if NET8_0_OR_GREATER
+        [global::System.Diagnostics.CodeAnalysis.Experimental(diagnosticId: "TRYAGI_OPENAI_BETA_001")]
+#endif
         public async IAsyncEnumerable<global::tryAGI.OpenAI.AssistantStreamEvent> CreateRunAsStreamAsync(
             string threadId,
             string assistantId,
             global::System.Collections.Generic.IList<global::tryAGI.OpenAI.CreateRunIncludeItem>? include = default,
             global::tryAGI.OpenAI.AnyOf<string, global::tryAGI.OpenAI.AssistantSupportedModels?>? model = default,
+            global::tryAGI.OpenAI.ReasoningEffort? reasoningEffort = default,
             string? instructions = default,
             string? additionalInstructions = default,
             global::System.Collections.Generic.IList<global::tryAGI.OpenAI.CreateMessageRequest>? additionalMessages = default,
-            global::System.Collections.Generic.IList<global::tryAGI.OpenAI.ToolsItem4>? tools = default,
+            global::System.Collections.Generic.IList<global::tryAGI.OpenAI.OneOf<global::tryAGI.OpenAI.AssistantToolsCode, global::tryAGI.OpenAI.AssistantToolsFileSearch, global::tryAGI.OpenAI.AssistantToolsFunction>>? tools = default,
             global::System.Collections.Generic.Dictionary<string, string>? metadata = default,
-            double? temperature = 1,
-            double? topP = 1,
+            double? temperature = default,
+            double? topP = default,
             bool? stream = default,
             int? maxPromptTokens = default,
             int? maxCompletionTokens = default,
-            global::tryAGI.OpenAI.TruncationObject? truncationStrategy = default,
-            global::tryAGI.OpenAI.AssistantsApiToolChoiceOption? toolChoice = default,
+            global::tryAGI.OpenAI.AllOf<global::tryAGI.OpenAI.TruncationObject, object>? truncationStrategy = default,
+            global::tryAGI.OpenAI.AllOf<global::tryAGI.OpenAI.AssistantsApiToolChoiceOption?, object>? toolChoice = default,
             bool? parallelToolCalls = default,
             global::tryAGI.OpenAI.AssistantsApiResponseFormatOption? responseFormat = default,
             [EnumeratorCancellation] global::System.Threading.CancellationToken cancellationToken = default)
         {
-            var request = new global::tryAGI.OpenAI.CreateRunRequest
+            var __request = new global::tryAGI.OpenAI.CreateRunRequest
             {
                 AssistantId = assistantId,
                 Model = model,
+                ReasoningEffort = reasoningEffort,
                 Instructions = instructions,
                 AdditionalInstructions = additionalInstructions,
                 AdditionalMessages = additionalMessages,
@@ -208,9 +219,7 @@ public partial class AssistantsClient
                 Stream = stream,
                 MaxPromptTokens = maxPromptTokens,
                 MaxCompletionTokens = maxCompletionTokens,
-                TruncationStrategy = truncationStrategy != null
-                    ? (global::tryAGI.OpenAI.AllOf<global::tryAGI.OpenAI.TruncationObject, object>?)truncationStrategy
-                    : null,
+                TruncationStrategy = truncationStrategy,
                 ToolChoice = toolChoice,
                 ParallelToolCalls = parallelToolCalls,
                 ResponseFormat = responseFormat,
@@ -219,7 +228,7 @@ public partial class AssistantsClient
             await foreach (var response in CreateRunAsStreamAsync(
                threadId: threadId,
                include: include,
-               request: request,
+               request: __request,
                cancellationToken: cancellationToken).ConfigureAwait(false))
             {
                 yield return response;