Added vLLM support (#524)

Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>

app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs

@@ -285,7 +285,7 @@ public static class LLMProvidersExtensions
         LLMProviders.GWDG => true,
         LLMProviders.HUGGINGFACE => true,
         
-        LLMProviders.SELF_HOSTED => host is Host.OLLAMA,
+        LLMProviders.SELF_HOSTED => host is (Host.OLLAMA or Host.VLLM),
         
         _ => false,
     };
@@ -322,6 +322,7 @@ public static class LLMProvidersExtensions
 
                 case Host.OLLAMA:
                 case Host.LM_STUDIO:
+                case Host.VLLM:
                     return true;
             }
         }

app/MindWork AI Studio/Provider/SelfHosted/ChatRequest.cs

@@ -6,11 +6,8 @@ namespace AIStudio.Provider.SelfHosted;
 /// <param name="Model">Which model to use for chat completion.</param>
 /// <param name="Messages">The chat messages.</param>
 /// <param name="Stream">Whether to stream the chat completion.</param>
-/// <param name="MaxTokens">The maximum number of tokens to generate.</param>
 public readonly record struct ChatRequest(
     string Model,
     IList<Message> Messages,
-    bool Stream,
-    
-    int MaxTokens
+    bool Stream
 );

app/MindWork AI Studio/Provider/SelfHosted/Host.cs

@@ -7,4 +7,5 @@ public enum Host
     LM_STUDIO,
     LLAMACPP,
     OLLAMA,
+    VLLM,
 }

app/MindWork AI Studio/Provider/SelfHosted/HostExtensions.cs

@@ -9,6 +9,7 @@ public static class HostExtensions
         Host.LM_STUDIO => "LM Studio",
         Host.LLAMACPP => "llama.cpp",
         Host.OLLAMA => "ollama",
+        Host.VLLM => "vLLM",
 
         _ => "Unknown",
     };
@@ -29,6 +30,7 @@ public static class HostExtensions
         {
             case Host.LM_STUDIO:
             case Host.OLLAMA:
+            case Host.VLLM:
                 return true;
             
             default:

app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs

@@ -58,8 +58,7 @@ public sealed class ProviderSelfHosted(ILogger logger, Host host, string hostnam
             }).ToList()],
             
             // Right now, we only support streaming completions:
-            Stream = true,
-            MaxTokens = -1,
+            Stream = true
         }, JSON_SERIALIZER_OPTIONS);
 
         async Task<HttpRequestMessage> RequestBuilder()
@@ -101,6 +100,7 @@ public sealed class ProviderSelfHosted(ILogger logger, Host host, string hostnam
             
                 case Host.LM_STUDIO:
                 case Host.OLLAMA:
+                case Host.VLLM:
                     return await this.LoadModels(["embed"], [], token, apiKeyProvisional);
             }
 
@@ -127,6 +127,7 @@ public sealed class ProviderSelfHosted(ILogger logger, Host host, string hostnam
             {
                 case Host.LM_STUDIO:
                 case Host.OLLAMA:
+                case Host.VLLM:
                     return await this.LoadModels([], ["embed"], token, apiKeyProvisional);
             }