Function calling hint

OpenAI.Chat.pas

@@ -98,6 +98,7 @@   TChatMessageBuild = record
     /// </summary>
     property Tag: string read FTag write FTag;
     class function Create(Role: TMessageRole; const Content: string; const Name: string = ''): TChatMessageBuild; static;
+    //Help functions
     class function User(const Content: string; const Name: string = ''): TChatMessageBuild; static;
     class function System(const Content: string; const Name: string = ''): TChatMessageBuild; static;
     class function Assistant(const Content: string; const Name: string = ''): TChatMessageBuild; static;
@@ -140,9 +141,10 @@   TChatParams = class(TJSONParam)
     /// </summary>
     function Functions(const Value: TArray<IChatFunction>): TChatParams;
     /// <summary>
-    /// Controls how the model responds to function calls.
-    /// "none" is the default when no functions are present.
-    /// "auto" is the default if functions are present
+    /// Controls how the model responds to function calls. "none" means the model does not call a function,
+    /// and responds to the end-user. "auto" means the model can pick between an end-user or calling a function.
+    /// Specifying a particular function via {"name":\ "my_function"} forces the model to call that function.
+    /// "none" is the default when no functions are present. "auto" is the default if functions are present.
     /// </summary>
     function FunctionCall(const Value: TFunctionCall): TChatParams;
     /// <summary>

README.md

@@ -194,6 +194,57 @@ end;
 
 Review [Images Documentation](https://platform.openai.com/docs/api-reference/images) for more info.
 
+### Function calling
+In an API call, you can describe functions to gpt-3.5-turbo-0613 and gpt-4-0613, and have the model intelligently choose to output a JSON object containing arguments to call those functions. The Chat Completions API does not call the function; instead, the model generates JSON that you can use to call the function in your code.
+
+The latest models (gpt-3.5-turbo-0613 and gpt-4-0613) have been fine-tuned to both detect when a function should to be called (depending on the input) and to respond with JSON that adheres to the function signature. With this capability also comes potential risks. We strongly recommend building in user confirmation flows before taking actions that impact the world on behalf of users (sending an email, posting something online, making a purchase, etc).
+
+```Pascal
+var Chat := OpenAI.Chat.Create(
+  procedure(Params: TChatParams)
+  begin
+    Params.Functions(Funcs);  //list of functions (TArray<IChatFunction>)
+    Params.FunctionCall(TFunctionCall.Auto);
+    Params.Messages([TChatMessageBuild.User(Text)]);
+    Params.MaxTokens(1024);
+  end);
+try
+  for var Choice in Chat.Choices do
+    if Choice.FinishReason = TFinishReason.FunctionCall then
+      ProcFunction(Choice.Message.FunctionCall)  // execute function (send result to chat, and continue)
+    else
+      MemoChat.Lines.Add(Choice.Message.Content);
+finally
+  Chat.Free;
+end;
+
+...
+
+procedure ProcFunction(Func: TChatFunctionCall);
+begin
+  var FuncResult := Execute(Func.Name, Func.Arguments);  //execute function and get result (json)
+  var Chat := OpenAI.Chat.Create(
+    procedure(Params: TChatParams)
+    begin
+      Params.Functions(Funcs);  //list of functions (TArray<IChatFunction>)
+      Params.FunctionCall(TFunctionCall.Auto);
+      Params.Messages([  //need all history
+         TChatMessageBuild.User(Text), 
+         TChatMessageBuild.NewAsistantFunc(Func.Name, Func.Arguments), 
+         TChatMessageBuild.Func(FuncResult, Func.Name)]);
+      Params.MaxTokens(1024);
+    end);
+  try
+    for var Choice in Chat.Choices do
+      MemoChat.Lines.Add(Choice.Message.Content);
+  finally
+    Chat.Free;
+  end;
+end;
+```
+
+Review [Functions Documentation](https://platform.openai.com/docs/guides/gpt/function-calling) for more info.
+
 ### Errors
 
 ```Pascal