feat: integrate Google Gemini with dynamic model fetching and UI support

- Added Gemini AI model integration with automatic model list fetching
- Updated configuration system to support Gemini API settings
- Enhanced SettingsDialog with Gemini model selection options
- Updated dependencies in package.json for Gemini support
- Improved provider configuration in index.ts for better model management
- Added Gemini API key field in sample configuration template
- Updated route configuration for Gemini support

sample.config.toml

@@ -1,13 +1,14 @@
-[GENERAL]
-PORT = 3001 # Port to run the server on
-SIMILARITY_MEASURE = "cosine" # "cosine" or "dot"
-KEEP_ALIVE = "5m" # How long to keep Ollama models loaded into memory. (Instead of using -1 use "-1m")
-
 [API_KEYS]
-OPENAI = "" # OpenAI API key - sk-1234567890abcdef1234567890abcdef
-GROQ = "" # Groq API key - gsk_1234567890abcdef1234567890abcdef
-ANTHROPIC = "" # Anthropic API key - sk-ant-1234567890abcdef1234567890abcdef
+OPENAI = ""
+GROQ = ""
+ANTHROPIC = ""
+GEMINI = ""
 
 [API_ENDPOINTS]
-SEARXNG = "http://localhost:32768" # SearxNG API URL
-OLLAMA = "" # Ollama API URL - http://host.docker.internal:11434
+OLLAMA = ""
+SEARXNG = "http://localhost:32768"
+
+[GENERAL]
+PORT = 3_001
+SIMILARITY_MEASURE = "cosine"
+KEEP_ALIVE = "5m"