Merge branch 'dev' into big-refactor

Author: vansangpfiev

docs/docusaurus.config.ts

@@ -476,7 +476,7 @@ const config: Config = {
             },
             {
               label: "Careers",
-              href: "https://homebrew.bamboohr.com/careers",
+              href: "https://menlo.bamboohr.com/careers",
             },
           ],
         },

engine/common/assistant_code_interpreter_tool.h

@@ -20,7 +20,7 @@ struct AssistantCodeInterpreterTool : public AssistantTool {
 
   static cpp::result<AssistantCodeInterpreterTool, std::string> FromJson() {
     AssistantCodeInterpreterTool tool;
-    return std::move(tool);
+    return tool;
   }
 
   cpp::result<Json::Value, std::string> ToJson() override {

engine/common/thread.h

@@ -150,9 +150,11 @@ struct Thread : JsonSerializable {
         if (auto code_interpreter =
                 dynamic_cast<CodeInterpreter*>(tool_resources.get())) {
           tool_json["code_interpreter"] = tool_result.value();
+          (void) code_interpreter;
         } else if (auto file_search =
                        dynamic_cast<FileSearch*>(tool_resources.get())) {
           tool_json["file_search"] = tool_result.value();
+          (void) file_search;
         }
         json["tool_resources"] = tool_json;
       }

engine/e2e-test/api/engines/test_api_engine.py

@@ -28,7 +28,7 @@ def test_engines_get_llamacpp_should_be_successful(self):
 
     # engines install
     def test_engines_install_llamacpp_specific_version_and_variant(self):
-        data = {"version": "v0.1.40-b4354", "variant": "linux-amd64-avx-cuda-11-7"}
+        data = {"version": "v0.1.40-b4354", "variant": "linux-amd64-avx"}
         response = requests.post(
             "http://localhost:3928/v1/engines/llama-cpp/install", json=data
         )

engine/e2e-test/api/engines/test_api_engine_install_nightly.py

@@ -23,7 +23,7 @@ def test_engines_install_llamacpp_should_be_successful(self):
         assert response.status_code == 200
 
     def test_engines_install_llamacpp_specific_version_and_variant(self):
-        data = {"version": latest_pre_release_tag, "variant": "linux-amd64-avx-cuda-11-7"}
+        data = {"version": latest_pre_release_tag, "variant": "linux-amd64-avx"}
         response = requests.post(
             "http://localhost:3928/v1/engines/llama-cpp/install", json=data
         )

engine/e2e-test/api/engines/test_api_get_default_engine.py

@@ -24,7 +24,7 @@ def setup_and_teardown(self):
     def test_api_get_default_engine_successfully(self):
         # Data test
         engine= "llama-cpp"
-        name= "linux-amd64-avx-cuda-11-7"
+        name= "linux-amd64-avx"
         version= "v0.1.35-27.10.24"
 
         data = {"version": version, "variant": name}

engine/e2e-test/api/engines/test_api_get_list_engine.py

@@ -26,6 +26,11 @@ def test_api_get_list_engines_successfully(self):
         engine= "llama-cpp"
         name= "linux-amd64-avx"
         version= "v0.1.35-27.10.24"
+        
+        post_install_url = f"http://localhost:3928/v1/engines/{engine}/install"
+        response = requests.delete(
+            post_install_url
+        )
 
         data = {"version": version, "variant": name}
         post_install_url = f"http://localhost:3928/v1/engines/{engine}/install"

engine/extensions/python-engine/python_engine.cc

@@ -56,7 +56,7 @@ size_t StreamWriteCallback(char* ptr, size_t size, size_t nmemb,
   return size * nmemb;
 }
 
-static size_t WriteCallback(char* ptr, size_t size, size_t nmemb,
+[[maybe_unused]] static size_t WriteCallback(char* ptr, size_t size, size_t nmemb,
                             std::string* data) {
   data->append(ptr, size * nmemb);
   return size * nmemb;
@@ -185,6 +185,7 @@ void PythonEngine::GetModels(
   status["status_code"] = k200OK;
 
   callback(std::move(status), std::move(response_json));
+  (void) json_body;
 }
 
 void PythonEngine::LoadModel(
@@ -386,6 +387,8 @@ void PythonEngine::HandleChatCompletion(
     std::shared_ptr<Json::Value> json_body,
     std::function<void(Json::Value&&, Json::Value&&)>&& callback) {
   LOG_WARN << "Does not support yet!";
+  (void) json_body;
+  (void) callback;
 }
 
 CurlResponse PythonEngine::MakeStreamPostRequest(
@@ -623,7 +626,9 @@ Json::Value PythonEngine::GetRemoteModels() {
   return Json::Value();
 }
 
-void PythonEngine::StopInferencing(const std::string& model_id) {}
+void PythonEngine::StopInferencing(const std::string& model_id) {
+  (void)model_id;
+}
 
 void PythonEngine::HandleRouteRequest(
     std::shared_ptr<Json::Value> json_body,
@@ -893,12 +898,14 @@ void PythonEngine::SetLogLevel(trantor::Logger::LogLevel log_level) {
 
 void PythonEngine::Load(EngineLoadOption opts) {
   // Develop register model here on loading engine
+  (void) opts;
 };
 
 void PythonEngine::Unload(EngineUnloadOption opts) {
   for (const auto& pair : models_) {
     TerminateModelProcess(pair.first);
   }
+  (void) opts;
 };
 
-}  // namespace python_engine
+}  // namespace python_engine

engine/main.cc

@@ -63,7 +63,7 @@ void RunServer(std::optional<std::string> host, std::optional<int> port,
                bool ignore_cout) {
 #if defined(__unix__) || (defined(__APPLE__) && defined(__MACH__))
   auto signal_handler = +[](int sig) -> void {
-    std::cout << "\rCaught interrupt signal, shutting down\n";
+    std::cout << "\rCaught interrupt signal:" << sig << ", shutting down\n";;
     shutdown_signal = true;
   };
   signal(SIGINT, signal_handler);
@@ -145,7 +145,7 @@ void RunServer(std::optional<std::string> host, std::optional<int> port,
     return;
   }
 
-  using Event = cortex::event::Event;
+  // using Event = cortex::event::Event; //unused
   using EventQueue =
       eventpp::EventQueue<EventType,
                           void(const eventpp::AnyData<eventMaxSize>&)>;

engine/services/download_service.h

@@ -234,6 +234,8 @@ class DownloadService {
         break;
       }
     }
+    (void) ultotal;
+    (void) ulnow;
 
     return 0;
   }