Update examples

LLama.Examples/NewVersion/BatchedDecoding.cs → LLama.Examples/Examples/BatchedDecoding.cs

@@ -4,7 +4,7 @@
 using LLama.Common;
 using LLama.Native;
 
-namespace LLama.Examples.NewVersion;
+namespace LLama.Examples.Examples;
 
 /// <summary>
 /// This demonstrates generating multiple replies to the same prompt, with a shared cache

LLama.Examples/NewVersion/ChatSessionStripRoleName.cs → LLama.Examples/Examples/ChatSessionStripRoleName.cs

@@ -1,6 +1,6 @@
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class ChatSessionStripRoleName
     {

LLama.Examples/NewVersion/ChatSessionWithRoleName.cs → LLama.Examples/Examples/ChatSessionWithRoleName.cs

@@ -1,6 +1,6 @@
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class ChatSessionWithRoleName
     {

LLama.Examples/NewVersion/CodingAssistant.cs → LLama.Examples/Examples/CodingAssistant.cs

@@ -1,4 +1,4 @@
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     using LLama.Common;
     using System;

LLama.Examples/NewVersion/GetEmbeddings.cs → LLama.Examples/Examples/GetEmbeddings.cs

@@ -1,6 +1,6 @@
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class GetEmbeddings
     {

LLama.Examples/NewVersion/GrammarJsonResponse.cs → LLama.Examples/Examples/GrammarJsonResponse.cs

@@ -1,7 +1,7 @@
 using LLama.Common;
 using LLama.Grammars;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class GrammarJsonResponse
     {

LLama.Examples/NewVersion/InstructModeExecute.cs → LLama.Examples/Examples/InstructModeExecute.cs

@@ -1,6 +1,6 @@
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class InstructModeExecute
     {

LLama.Examples/NewVersion/InteractiveModeExecute.cs → LLama.Examples/Examples/InteractiveModeExecute.cs

@@ -1,6 +1,6 @@
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class InteractiveModeExecute
     {

LLama.Examples/NewVersion/KernelMemory.cs → LLama.Examples/Examples/KernelMemory.cs

@@ -7,7 +7,7 @@
 using Microsoft.KernelMemory;
 using Microsoft.KernelMemory.Handlers;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class KernelMemory
     {

LLama.Examples/NewVersion/LoadAndSaveSession.cs → LLama.Examples/Examples/LoadAndSaveSession.cs

@@ -1,6 +1,6 @@
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class SaveAndLoadSession
     {

LLama.Examples/NewVersion/LoadAndSaveState.cs → LLama.Examples/Examples/LoadAndSaveState.cs

@@ -1,6 +1,6 @@
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class LoadAndSaveState
     {

LLama.Examples/NewVersion/QuantizeModel.cs → LLama.Examples/Examples/QuantizeModel.cs

@@ -1,4 +1,4 @@
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class QuantizeModel
     {

LLama.Examples/Examples/Runner.cs

@@ -0,0 +1,53 @@
+using Spectre.Console;
+
+namespace LLama.Examples.Examples;
+
+public class Runner
+{
+    static Dictionary<string, Func<Task>> Examples = new()
+    {
+        {"Run a chat session without stripping the role names.", () => ChatSessionWithRoleName.Run()},
+        {"Run a chat session with the role names stripped.",()=> ChatSessionStripRoleName.Run()},
+        {"Interactive mode chat by using executor.",()=> InteractiveModeExecute.Run()},
+        {"Instruct mode chat by using executor.",()=> InstructModeExecute.Run()},
+        {"Stateless mode chat by using executor.",()=> StatelessModeExecute.Run()},
+        {"Load and save chat session.",()=> SaveAndLoadSession.Run()},
+        {"Load and save state of model and executor.",()=> LoadAndSaveState.Run()},
+        {"Get embeddings from LLama model.",()=> Task.Run(GetEmbeddings.Run)},
+        {"Quantize the model.",()=> Task.Run(QuantizeModel.Run)},
+        {"Automatic conversation.",()=> TalkToYourself.Run()},
+        {"Constrain response to json format using grammar.",()=> GrammarJsonResponse.Run()},
+        {"Semantic Kernel Prompt.",()=> SemanticKernelPrompt.Run()},
+        {"Semantic Kernel Chat.",()=> SemanticKernelChat.Run()},
+        {"Semantic Kernel Memory.",()=> SemanticKernelMemory.Run()},
+        {"Coding Assistant.",()=> CodingAssistant.Run()},
+        {"Batch Decoding.",()=> BatchedDecoding.Run()},
+        {"SK Kernel Memory.",()=> KernelMemory.Run()},
+        {"Exit", ()=> Task.CompletedTask}
+    };
+    public static async Task Run()
+    {
+        AnsiConsole.Write(new Rule("LLamaSharp Examples"));
+
+        while (true)
+        {
+            var choice = AnsiConsole.Prompt(
+                new SelectionPrompt<string>()
+                    .Title("Please choose[green] an example[/] to run: ")
+                    .AddChoices(Examples.Keys));
+
+
+            if (Examples.TryGetValue(choice, out var example))
+            {
+                if (choice == "Exit")
+                {
+                    break;
+                }
+                AnsiConsole.Write(new Rule(choice));
+                await example();
+            }
+
+            AnsiConsole.Clear();
+        }
+    }
+}

LLama.Examples/NewVersion/SemanticKernelChat.cs → LLama.Examples/Examples/SemanticKernelChat.cs

@@ -3,7 +3,7 @@
 using Microsoft.SemanticKernel.AI.ChatCompletion;
 using LLamaSharp.SemanticKernel.ChatCompletion;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class SemanticKernelChat
     {

LLama.Examples/NewVersion/SemanticKernelMemory.cs → LLama.Examples/Examples/SemanticKernelMemory.cs

@@ -5,7 +5,7 @@
 using Microsoft.SemanticKernel.AI.Embeddings;
 using Microsoft.SemanticKernel.Plugins.Memory;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class SemanticKernelMemory
     {

LLama.Examples/NewVersion/SemanticKernelPrompt.cs → LLama.Examples/Examples/SemanticKernelPrompt.cs

@@ -5,7 +5,7 @@
 using Microsoft.SemanticKernel.AI.TextCompletion;
 using LLamaSharp.SemanticKernel.TextCompletion;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class SemanticKernelPrompt
     {

LLama.Examples/NewVersion/StatelessModeExecute.cs → LLama.Examples/Examples/StatelessModeExecute.cs

@@ -1,7 +1,7 @@
 using LLama.Common;
 using LLama.Examples.Extensions;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class StatelessModeExecute
     {

LLama.Examples/NewVersion/TalkToYourself.cs → LLama.Examples/Examples/TalkToYourself.cs

@@ -3,7 +3,7 @@
 using LLama.Abstractions;
 using LLama.Common;
 
-namespace LLama.Examples.NewVersion
+namespace LLama.Examples.Examples
 {
     public class TalkToYourself
     {

LLama.Examples/Program.cs

@@ -1,4 +1,4 @@
-using LLama.Examples.NewVersion;
+using LLama.Examples.Examples;
 using LLama.Native;
 
 Console.WriteLine("======================================================================================================");
@@ -12,4 +12,4 @@
 NativeApi.llama_empty_call();
 Console.WriteLine();
 
-await NewVersionTestRunner.Run();
+await Runner.Run();