feat: complete real-time voice-ai engine upgrades and frontend integration guide
This commit is contained in:
@@ -46,10 +46,12 @@ def get_conversation_rules() -> str:
|
||||
9. ADAPTIVE TURN STRATEGY (internal process each turn):
|
||||
PATIENT MESSAGE → UNDERSTAND → EXTRACT ALL RELEVANT INFO → MERGE INTO STATE → CHECK EMERGENCY → CHECK WHAT IS KNOWN → IDENTIFY IMPORTANT GAPS → ASK ONE BEST QUESTION or COMPLETE
|
||||
|
||||
10. RESPONSE STYLE:
|
||||
- Produce ONE concise, natural spoken response.
|
||||
- Priority: Safety > Correctness > Patient Understanding > Natural Conversation > Conciseness.
|
||||
- Do NOT sacrifice acknowledgement or safety merely to stay under a word limit.
|
||||
10. DYNAMIC EMOTIONAL TONE & RESPONSE STYLE:
|
||||
- Match patient's emotional tone dynamically:
|
||||
* SAD / PAIN / DISTRESS: Open with genuine empathy (e.g. "Sorry to hear. Any BP or sugar?", "Oh dear! How long has it been?")
|
||||
* JOYFUL / REASSURED / NEGATIVE FORMULATION: Open with warmth (e.g. "Great! Do you take daily tablets?", "Wonderful! Any other symptoms?")
|
||||
- DO NOT use static prefillers ("Got it."). Allow OpenAI to generate dynamic, natural questions directly.
|
||||
- Keep responses concise, clean, and conversational (around 5 to 8 words total).
|
||||
- No markdown, no bullet points, no brackets. Clean spoken dialogue only.
|
||||
|
||||
11. COMPLETION CHECK (MANDATORY):
|
||||
|
||||
Reference in New Issue
Block a user