Update app.py

app.py

@@ -1,64 +1,161 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import requests
+import json
+import speech_recognition as sr
+from tempfile import NamedTemporaryFile
+import pyttsx3
+import logging
+import time
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Groq API setup
+GROQ_API_KEY = os.getenv("GROQ_API_KEY", "your_key_here")
+GROQ_MODEL = os.getenv("GROQ_MODEL", "mixtral-8x7b-32768")
+GROQ_API_URL = "https://api.groq.com/openai/v1/chat/completions"
+
+headers = {
+    "Authorization": f"Bearer {GROQ_API_KEY}",
+    "Content-Type": "application/json"
+}
+
+# Emotion options
+emotion_options = {
+    "neutral": "Neutral or balanced mood",
+    "positive": "Generally positive or optimistic",
+    "happy": "Feeling joy or happiness",
+    "excited": "Feeling enthusiastic or energetic",
+    "sad": "Feeling down or unhappy",
+    "angry": "Feeling frustrated or irritated",
+    "negative": "Generally negative or pessimistic",
+    "anxious": "Feeling worried or nervous"
+}
+
+# Initialize conversation history
+conversation_history = []
+
+# Transcribe audio to text
+def transcribe_audio(audio_path):
+    recognizer = sr.Recognizer()
+    try:
+        with sr.AudioFile(audio_path) as source:
+            audio_data = recognizer.record(source)
+            transcription = recognizer.recognize_google(audio_data)
+            return transcription
+    except Exception as e:
+        logger.error(f"Audio transcription failed: {e}")
+        return ""
+
+# Get Groq response
+def get_groq_response(prompt, history):
+    messages = [{"role": "system", "content": prompt}]
+    for message in history:
+        if message.startswith("User: "):
+            messages.append({"role": "user", "content": message[6:]})
+        elif message.startswith("AI: "):
+            messages.append({"role": "assistant", "content": message[4:]})
+    data = {
+        "model": GROQ_MODEL,
+        "messages": messages,
+        "temperature": 0.7,
+        "max_tokens": 1024
+    }
+    try:
+        response = requests.post(GROQ_API_URL, headers=headers, json=data)
+        return response.json()["choices"][0]["message"]["content"]
+    except Exception as e:
+        logger.error(f"Groq API error: {e}")
+        return "Error contacting AI."
+
+# Generate speech using pyttsx3 and save to WAV
+def generate_speech(text):
+    try:
+        tts = pyttsx3.init()
+        temp_file = NamedTemporaryFile(delete=False, suffix=".wav")
+        temp_path = temp_file.name
+        tts.save_to_file(text, temp_path)
+        tts.runAndWait()
+        time.sleep(1)  # Ensure file is saved
+        return temp_path
+    except Exception as e:
+        logger.error(f"TTS error: {e}")
+        return None
+
+# Main interaction
+def chat_with_ai(audio, text_input, emotion, history):
+    global conversation_history
+    user_text = text_input or ""
+    if audio:
+        transcription = transcribe_audio(audio)
+        if transcription:
+            user_text = transcription
+        else:
+            return "Couldn't understand the audio.", None, history
+    if not user_text.strip():
+        return "No input provided.", None, history
+
+    conversation_history.append(f"User: {user_text}")
+    recent_messages = conversation_history[-20:]
+
+    prompt = f"""You are an empathetic AI assistant. The user is feeling {emotion} ({emotion_options[emotion]}). Respond supportively."""
+    ai_response = get_groq_response(prompt, recent_messages)
+    conversation_history.append(f"AI: {ai_response}")
+
+    audio_path = generate_speech(ai_response)
+    return ai_response, audio_path, history + [[user_text, ai_response]]
+
+def clear_conversation():
+    global conversation_history
+    conversation_history = []
+    return [], None, None, "Conversation cleared."
+
+# Gradio Interface
+iface = gr.Blocks()
+
+with iface:
+    gr.Markdown("# Mind AID AI Assistant")
+    gr.Markdown("Talk or type to the AI assistant. Your emotional state helps tailor the response.")
+    
+    with gr.Row():
+        with gr.Column(scale=3):
+            emotion = gr.Dropdown(label="Your emotion?", choices=list(emotion_options.keys()), value="neutral")
+            emotion_description = gr.Markdown("**Current mood:** Neutral")
+            def update_emotion_desc(em):
+                return f"**Current mood:** {emotion_options.get(em, 'Unknown')}"
+            emotion.change(fn=update_emotion_desc, inputs=[emotion], outputs=[emotion_description])
+        with gr.Column(scale=1):
+            clear_btn = gr.Button("Clear Conversation")
+            status = gr.Textbox(label="Status")
+
+    chat_history = gr.Chatbot(label="Chat History", height=300)
+
+    with gr.Row():
+        text_input = gr.Textbox(label="Type your message", lines=2)
+        audio_input = gr.Audio(label="Or speak", type="filepath", sources=["microphone"])
+
+    output_audio = gr.Audio(label="AI Voice Response")
+    submit_btn = gr.Button("Send", variant="primary")
+
+    submit_btn.click(
+        fn=chat_with_ai,
+        inputs=[audio_input, text_input, emotion, chat_history],
+        outputs=[status, output_audio, chat_history]
+    )
+
+    text_input.submit(
+        fn=chat_with_ai,
+        inputs=[audio_input, text_input, emotion, chat_history],
+        outputs=[status, output_audio, chat_history]
+    )
+
+    clear_btn.click(
+        fn=clear_conversation,
+        inputs=[],
+        outputs=[chat_history, audio_input, text_input, status]
+    )
+
+# Launch (MUST be outside if __name__ == "__main__")
+iface.launch()