Fix up issues found during testing

LLama.Web/Extensions.cs

@@ -33,7 +33,7 @@ namespace LLama.Web
         /// <returns>Combined list with duplicates removed</returns>
         private static List<string> CombineCSV(List<string> list, string csv)
         {
-            var results = list?.Count == 0
+            var results = list is null || list.Count == 0
                 ? CommaSeperatedToList(csv)
                 : CommaSeperatedToList(csv).Concat(list);
             return results

LLama.Web/Hubs/SessionConnectionHub.cs

@@ -37,7 +37,7 @@ namespace LLama.Web.Hubs
 
 
         [HubMethodName("LoadModel")]
-        public async Task OnLoadModel(ISessionConfig sessionConfig, InferenceOptions inferenceConfig)
+        public async Task OnLoadModel(SessionConfig sessionConfig, InferenceOptions inferenceConfig)
         {
             _logger.Log(LogLevel.Information, "[OnLoadModel] - Load new model, Connection: {0}", Context.ConnectionId);
             await _modelSessionService.CloseAsync(Context.ConnectionId);

LLama.Web/Pages/Shared/_ChatTemplates.cshtml

@@ -25,7 +25,7 @@
         <div class="m-2 me-4">
             <img src="~/image/robot.png" width="60"/>
         </div>
-        <div id="{{id}}" class="d-flex flex-column flex-fill justify-content-between">
+        <div id="{{uniqueId}}" class="d-flex flex-column flex-fill justify-content-between">
             <span class="content"><img src="~/image/loading.gif" width="30" /></span>
             <div class="d-flex justify-content-end">
                 <div class="d-flex flex-column align-items-end">

LLama.Web/Pages/Shared/_Parameters.cshtml

@@ -1,7 +1,6 @@
 @page
 @using LLama.Common;
 @model LLama.Abstractions.IInferenceParams
-}
 
 <div class="d-flex flex-row gap-3">
     <div class="d-flex flex-column mb-2">

LLama.Web/Program.cs

@@ -14,6 +14,8 @@ namespace LLama.Web
             // Add services to the container.
             builder.Services.AddRazorPages();
             builder.Services.AddSignalR();
+            builder.Logging.ClearProviders();
+            builder.Services.AddLogging((loggingBuilder) => loggingBuilder.SetMinimumLevel(LogLevel.Trace).AddConsole());
 
             // Load InteractiveOptions
             builder.Services.AddOptions<LLamaOptions>()

LLama.Web/Services/ModelService.cs

@@ -1,6 +1,7 @@
 using LLama.Web.Async;
 using LLama.Web.Common;
 using LLama.Web.Models;
+using Microsoft.Extensions.Options;
 using System.Collections.Concurrent;
 
 namespace LLama.Web.Services
@@ -11,10 +12,10 @@ namespace LLama.Web.Services
     /// </summary>
     public class ModelService : IModelService
     {
-        private readonly ILogger _llamaLogger;
         private readonly AsyncLock _modelLock;
         private readonly AsyncLock _contextLock;
         private readonly LLamaOptions _configuration;
+        private readonly ILogger<ModelService> _llamaLogger;
         private readonly ConcurrentDictionary<string, LLamaModel> _modelInstances;
 
 
@@ -23,12 +24,12 @@ namespace LLama.Web.Services
         /// </summary>
         /// <param name="logger">The logger.</param>
         /// <param name="options">The options.</param>
-        public ModelService(LLamaOptions configuration, ILogger llamaLogger)
+        public ModelService(IOptions<LLamaOptions> configuration, ILogger<ModelService> llamaLogger)
         {
             _llamaLogger = llamaLogger;
             _modelLock = new AsyncLock();
             _contextLock = new AsyncLock();
-            _configuration = configuration;
+            _configuration = configuration.Value;
             _modelInstances = new ConcurrentDictionary<string, LLamaModel>();
         }
 

LLama.Web/appsettings.json

@@ -7,12 +7,12 @@
   },
   "AllowedHosts": "*",
   "LLamaOptions": {
-    "ModelLoadType": "Single",
+    "ModelLoadType": 0,
     "Models": [
       {
-        "Name": "WizardLM-7B",
+        "Name": "LLama2-7b-Chat",
         "MaxInstances": 20,
-        "ModelPath": "D:\\Repositories\\AI\\Models\\wizardLM-7B.ggmlv3.q4_0.bin",
+        "ModelPath": "..\\LLama.Unittest\\Models\\llama-2-7b-chat.Q4_0.gguf",
         "ContextSize": 2048,
         "BatchSize": 2048,
         "Threads": 4,

LLama.Web/wwwroot/js/sessionConnectionChat.js

@@ -43,8 +43,8 @@ const createConnectionSessionChat = () => {
             return;
 
         if (response.tokenType == Enums.TokenType.Begin) {
-            const uniqueId = randomString();
-            outputContainer.append(Mustache.render(outputBotTemplate, { id: uniqueId, ...response }));
+            let uniqueId = randomString();
+            outputContainer.append(Mustache.render(outputBotTemplate, { uniqueId: uniqueId, ...response }));
             responseContainer = $(`#${uniqueId}`);
             responseContent = responseContainer.find(".content");
             responseFirstToken = true;
@@ -102,6 +102,7 @@ const createConnectionSessionChat = () => {
     }
 
     const unloadModel = async () => {
+        await cancelPrompt();
         disableControls();
         enablePromptControls();
         $("#load").removeAttr("disabled");