feat: add openviking-server init interactive setup wizard for local Ollama model deployment

openviking_cli/doctor.py

@@ -160,6 +160,10 @@ def check_embedding() -> tuple[bool, str, Optional[str]]:
     if provider == "unknown":
         return False, "No embedding provider configured", "Add embedding.dense section to ov.conf"
 
+    # Ollama doesn't need an API key
+    if provider == "ollama":
+        return True, f"{provider}/{model}", None
+
     api_key = dense.get("api_key", "")
     if not api_key or api_key.startswith("{"):
         return (
@@ -188,6 +192,10 @@ def check_vlm() -> tuple[bool, str, Optional[str]]:
     if not provider:
         return False, "No VLM provider configured", "Add vlm section to ov.conf"
 
+    # Ollama via LiteLLM doesn't need a real API key
+    if provider == "litellm" and model.startswith("ollama/"):
+        return True, f"{provider}/{model}", None
+
     api_key = vlm.get("api_key", "")
     if not api_key or api_key.startswith("{"):
         return (

openviking_cli/rust_cli.py

@@ -54,6 +54,11 @@ def main():
         from openviking_cli.doctor import main as doctor_main
 
         sys.exit(doctor_main())
+
+    if len(sys.argv) > 1 and sys.argv[1] == "init":
+        from openviking_cli.setup_wizard import main as init_main
+
+        sys.exit(init_main())
     # 1. 检查开发环境（仅在直接运行脚本时有效）
     try:
         # __file__ is openviking_cli/rust_cli.py, so parent is openviking_cli directory