Update app.py

app.py

@@ -9,7 +9,7 @@ from huggingface_hub import InferenceClient
 EXTRACTOR_MODEL = "meta-llama/Meta-Llama-3-8B-Instruct"
 PERSONALITY_MODEL = "HuggingFaceH4/zephyr-7b-beta"
 
-# Default Data: 30 Personality-focused messages
+# Default Data
 DEFAULT_LOGS = """
 1. User: I feel completely drained after large social gatherings.
 2. User: I enjoy abstract theories more than practical details.
@@ -51,22 +51,33 @@ def extract_memory(chat_logs, hf_token):
     client = InferenceClient(token=hf_token)
     
     system_prompt = """
-    Analyze the chat logs and extract a psychological profile.
-    JSON KEYS: "traits" (Big Five/MBTI), "values" (Logic, Harmony, etc), "struggles" (Anxiety, Procrastination).
-    OUTPUT: Valid JSON only.
+    You are a Psychological Analyst. Analyze the chat logs.
+    Extract a profile with these JSON KEYS: 
+    "traits" (Big Five/MBTI), "values" (Logic, Harmony, etc), "struggles" (Anxiety, Procrastination).
+    OUTPUT: Valid JSON only. Do not add markdown blocks like ```json.
     """
     
-    prompt = f"<|system|>\n{system_prompt}</s>\n<|user|>\n{chat_logs}</s>\n<|assistant|>"
+    # FIXED: Switched from text_generation to chat_completion
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": chat_logs}
+    ]
     
     try:
-        response = client.text_generation(
+        response = client.chat_completion(
             model=EXTRACTOR_MODEL,
-            prompt=prompt,
-            max_new_tokens=600,
+            messages=messages,
+            max_tokens=600,
             temperature=0.1
         )
+        
         # Parse JSON
-        text = response.strip()
+        text = response.choices[0].message.content.strip()
+        
+        # Cleaning potential markdown formatting from LLM response
+        if "```json" in text:
+            text = text.replace("```json", "").replace("```", "")
+        
         start = text.find("{")
         end = text.rfind("}") + 1
         return json.dumps(json.loads(text[start:end]), indent=2)
@@ -127,16 +138,16 @@ async def generate_response_and_audio(message, memory_json, persona, hf_token):
     
     return text_reply, output_file
 
-# Wrapper for Gradio (handling async)
+# Wrapper for Gradio
 def process_interaction(message, memory_json, persona, hf_token):
     return asyncio.run(generate_response_and_audio(message, memory_json, persona, hf_token))
 
 # --- GRADIO UI ---
 with gr.Blocks(title="Personality Engine") as demo:
-    gr.Markdown("# Personality Engine: Tones")
+    gr.Markdown("# 🧠 Personality Engine: Memory & Tones")
     
     with gr.Row():
-        token_input = gr.Textbox(label="Hugging Face Token", type="password", placeholder="hf_...")
+        token_input = gr.Textbox(label="Hugging Face Token", type="password", placeholder="Paste HF Token here...")
     
     with gr.Row():
         # Left Column: Memory