feat: implement voice-based patient onboarding pipeline with AI orchestration, multi-language STT/TTS support, and clinical state extraction.

ai-patient-onboarding/app/ai/gemini_client.py

@@ -71,3 +71,21 @@ Return ONLY JSON:
                 "allergies_found": [],
                 "summary": f"Could not extract document details: {e}",
             }
+
+    async def generate_response(
+        self,
+        system_prompt: str,
+        user_message: str,
+    ) -> str:
+        if not self.api_key or self.api_key in ["your_gemini_key", "your_gemini_api_key", ""]:
+            raise ValueError("Gemini API key not configured")
+
+        import google.generativeai as genai
+        genai.configure(api_key=self.api_key)
+        model = genai.GenerativeModel(
+            model_name=self.model or "gemini-1.5-flash",
+            generation_config={"response_mime_type": "application/json"},
+        )
+        full_prompt = f"{system_prompt}\n\nPATIENT SAID: {user_message}"
+        response = await model.generate_content_async(full_prompt)
+        return response.text