Initial deployment: Medical AI Semantic Translator

.gitignore

@@ -0,0 +1,10 @@
+# Local development files
+*.pyc
+__pycache__/
+.env
+*.log
+.DS_Store
+
+# Never commit API keys!
+*.key
+secrets.txt

app.py

@@ -0,0 +1,260 @@
+"""
+Module 1: Cross-Cultural Semantic Translator MVP
+=================================================
+A medical AI platform for translating cultural pain metaphors into structured medical ontologies.
+
+Deployed on Hugging Face Spaces.
+"""
+
+import gradio as gr
+import json
+import os
+from typing import Dict, Tuple, Optional
+
+# ============================================================================
+# CONFIGURATION - 从环境变量读取
+# ============================================================================
+
+# SECURITY: NEVER hardcode API keys in public repos
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "")
+
+# Transcription mode: Force API mode on Hugging Face (no GPU access)
+TRANSCRIPTION_MODE = "api"
+
+# OpenAI model for analysis
+OPENAI_MODEL = "gpt-4-turbo-preview"  # Use newer model name
+
+# ============================================================================
+# IMPORTS AND SETUP
+# ============================================================================
+
+try:
+    from openai import OpenAI
+    client = OpenAI(api_key=OPENAI_API_KEY) if OPENAI_API_KEY else None
+except ImportError:
+    print("ERROR: OpenAI library not installed.")
+    client = None
+
+# ============================================================================
+# SYSTEM PROMPT FOR LLM
+# ============================================================================
+
+MEDICAL_ANTHROPOLOGIST_PROMPT = """You are an expert Medical Anthropologist. Your goal is to translate cultural pain metaphors into structured medical ontologies. Do NOT act as a doctor making a final diagnosis. Analyze the patient's transcript and output a strict JSON object with these exact keys: 'literal_translation', 'metaphor_mapping', 'mcgill_pain_ontology', 'psychological_and_stoicism_flags', 'physician_action_note'. Make sure to include English and original language in metaphor_mapping for reference."""
+
+# ============================================================================
+# AUDIO TRANSCRIPTION FUNCTION
+# ============================================================================
+
+def transcribe_audio(audio_path: Optional[str]) -> Tuple[str, str]:
+    """
+    Transcribe audio using OpenAI Whisper API.
+    """
+    if audio_path is None:
+        return "", "⚠️ No audio recorded. Please record audio first."
+    
+    if client is None:
+        return "", "❌ OpenAI client not initialized. API key missing."
+    
+    try:
+        with open(audio_path, "rb") as audio_file:
+            transcript = client.audio.transcriptions.create(
+                model="whisper-1",
+                file=audio_file,
+                response_format="text"
+            )
+        transcription = transcript.strip()
+        status = f"✓ Transcribed via OpenAI Whisper API"
+        
+        if not transcription:
+            return "", "⚠️ Transcription is empty. Please check your audio quality."
+        
+        return transcription, status
+    
+    except Exception as e:
+        error_msg = f"❌ Transcription error: {str(e)}"
+        print(error_msg)
+        return "", error_msg
+
+# ============================================================================
+# LLM ANALYSIS FUNCTION
+# ============================================================================
+
+def analyze_with_llm(transcription: str) -> Tuple[str, str]:
+    """
+    Send transcription to OpenAI API for medical anthropological analysis.
+    """
+    if not transcription or transcription.strip() == "":
+        return "<div style='padding: 20px; color: #ffc107;'>⚠️ No transcription to analyze.</div>", "{}"
+    
+    if client is None:
+        return "<div style='padding: 20px; color: #ff6b6b;'>❌ OpenAI client not initialized. Please set OPENAI_API_KEY in Space secrets.</div>", "{}"
+    
+    try:
+        response = client.chat.completions.create(
+            model=OPENAI_MODEL,
+            messages=[
+                {"role": "system", "content": MEDICAL_ANTHROPOLOGIST_PROMPT},
+                {"role": "user", "content": f"Patient transcript:\n\n{transcription}"}
+            ],
+            response_format={"type": "json_object"},
+            temperature=0.7
+        )
+        
+        json_text = response.choices[0].message.content
+        
+        if not json_text or json_text.strip() == "":
+            return "<div style='padding: 20px; color: #ff6b6b;'>❌ Empty response from LLM</div>", "{}"
+        
+        try:
+            parsed_json = json.loads(json_text)
+        except json.JSONDecodeError as je:
+            error_html = f"""
+            <div style='padding: 20px; background-color: #f8d7da; border-left: 5px solid #dc3545; border-radius: 8px;'>
+                <h3 style='color: #721c24;'>⚠️ JSON Parse Error</h3>
+                <p style='color: #721c24;'>{str(je)}</p>
+            </div>
+            """
+            return error_html, json_text
+        
+        formatted_output = format_json_for_display(parsed_json)
+        return formatted_output, json_text
+    
+    except Exception as e:
+        import traceback
+        error_details = traceback.format_exc()
+        error_html = f"""
+        <div style='padding: 20px; background-color: #f8d7da; border-left: 5px solid #dc3545; border-radius: 8px;'>
+            <h3 style='color: #721c24;'>❌ LLM Analysis Error</h3>
+            <pre style='color: #721c24; font-size: 12px; overflow-x: auto;'>{error_details}</pre>
+        </div>
+        """
+        return error_html, "{}"
+
+# ============================================================================
+# JSON FORMATTING FOR DISPLAY
+# ============================================================================
+
+def format_json_for_display(data: Dict) -> str:
+    """Format the JSON output into a human-readable medical report."""
+    # [保留你原来的 format_json_for_display 函数的完整代码]
+    # 这里为了简洁省略，实际部署时复制完整函数
+    html_parts = ['''
+    <div style="font-family: 'Segoe UI', Arial, sans-serif; padding: 30px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); border-radius: 15px; color: #ffffff; box-shadow: 0 10px 25px rgba(0,0,0,0.2); line-height: 1.8;">
+    ''']
+    
+    # [完整的格式化逻辑...]
+    
+    html_parts.append('</div>')
+    return ''.join(html_parts)
+
+# ============================================================================
+# MAIN PROCESSING FUNCTION
+# ============================================================================
+
+def process_patient_audio(audio) -> Tuple[str, str, str]:
+    """Main processing pipeline"""
+    try:
+        transcription, trans_status = transcribe_audio(audio)
+        
+        if "Error" in trans_status or not transcription.strip():
+            return trans_status, transcription, "<div style='padding: 20px; color: #ff6b6b;'>⚠️ Cannot analyze without transcription.</div>"
+        
+        formatted_html, json_output = analyze_with_llm(transcription)
+        
+        if "Error" in formatted_html:
+            return "❌ Analysis failed", transcription, formatted_html
+        
+        return "✅ Analysis complete", transcription, formatted_html
+    
+    except Exception as e:
+        import traceback
+        error_details = traceback.format_exc()
+        error_html = f"""
+        <div style='padding: 20px; background-color: #f8d7da; border-left: 5px solid #dc3545; border-radius: 8px;'>
+            <h3 style='color: #721c24;'>❌ Unexpected Error</h3>
+            <pre style='color: #721c24; font-size: 12px; overflow-x: auto;'>{error_details}</pre>
+        </div>
+        """
+        return "❌ Processing error", "Error during processing", error_html
+
+# ============================================================================
+# GRADIO UI SETUP
+# ============================================================================
+
+def create_ui():
+    """Create the Gradio interface"""
+    
+    with gr.Blocks(title="Medical AI Semantic Translator", theme=gr.themes.Soft()) as app:
+        gr.Markdown(
+            """
+            # 🏥 Module 1: Cross-Cultural Semantic Translator
+            ### Translating Cultural Pain Metaphors into Medical Ontologies
+            
+            **Instructions:** Record your audio description of pain symptoms, then click Analyze.
+            
+            ⚠️ **Note:** This demo uses OpenAI's API. The Space owner must configure API keys.
+            """
+        )
+        
+        status_output = gr.Textbox(label="Status", interactive=False, lines=1)
+        
+        with gr.Row():
+            with gr.Column(scale=1):
+                gr.Markdown("### 🎤 Audio Input")
+                audio_input = gr.Audio(
+                    sources=["microphone"],
+                    type="filepath",
+                    label="Record Your Pain Description"
+                )
+                submit_btn = gr.Button("🔍 Analyze", variant="primary", size="lg")
+                
+                gr.Markdown("### 📄 Transcription")
+                transcription_output = gr.Textbox(
+                    label="Whisper Transcription Output",
+                    interactive=False,
+                    lines=8
+                )
+            
+            with gr.Column(scale=1):
+                gr.Markdown("### 🤖 AI Medical Anthropologist Analysis")
+                analysis_output = gr.HTML(
+                    label="Structured Medical Ontology",
+                    value='<div style="padding: 20px; text-align: center; color: #6c757d;">Analysis results will appear here...</div>'
+                )
+        
+        gr.Markdown(
+            f"""
+            ---
+            **Configuration:** Transcription: `API` | LLM Model: `{OPENAI_MODEL}`
+            
+            **Deployed on:** [Hugging Face Spaces](https://huggingface.co/spaces/DIrtyCha/Module1demo)
+            """
+        )
+        
+        submit_btn.click(
+            fn=process_patient_audio,
+            inputs=[audio_input],
+            outputs=[status_output, transcription_output, analysis_output]
+        )
+    
+    return app
+
+# ============================================================================
+# MAIN ENTRY POINT
+# ============================================================================
+
+if __name__ == "__main__":
+    print("="  * 70)
+    print("🚀 Medical AI Semantic Translator MVP - Hugging Face Spaces")
+    print("=" * 70)
+    
+    if not OPENAI_API_KEY:
+        print("⚠️  WARNING: OPENAI_API_KEY not set in Space secrets!")
+        print("   Go to: Settings → Repository Secrets → Add OPENAI_API_KEY")
+    else:
+        print("✅ OpenAI API key loaded from environment")
+    
+    print("=" * 70)
+    
+    app = create_ui()
+    app.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio==4.44.0
+openai>=1.0.0
+numpy