Update app.py

app.py

@@ -1,76 +1,42 @@
+\import requests
 import gradio as gr
-import requests
-import speech_recognition as sr
 import pyttsx3
+import speech_recognition as sr
 
-# Define the Groq Cloud API key and model name
-API_KEY = "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"  # Replace with your Groq Cloud API Key
-MODEL_NAME = "groq-model-id"  # Replace with the actual model ID from Groq Cloud
+# Replace with your actual API key
+API_KEY = "AIzaSyAm0RSpUKY38494Fug8SPIpdHLXE2d3cps"  # Replace with your Gemini 2.0 Flash API key
+MODEL_NAME = "gemini-2.0-flash"  # Replace with your Gemini model name, e.g., "Gemini 2.0 flash"
 
-# Groq Cloud API endpoint
-API_URL = f"https://api.groq.ai/v1/models/{MODEL_NAME}/predict"
+# API URL for Gemini 2.0 Flash
+API_URL = "https://api.gemini.com/v1/predict"  # Example URL; make sure to replace with actual endpoint if different
 
-# Verify API Key with Groq Cloud
+# Headers to pass the API Key
 headers = {"Authorization": f"Bearer {API_KEY}"}
-response = requests.get("https://api.groq.ai/v1/whoami", headers=headers)
-
-# Check if API Key is valid
-if response.status_code != 200:
-    raise ValueError(f"Invalid API Key! Error: {response.json()}")
-else:
-    print("API Key is valid!")
-
-# Function to process the chat input
-def respond(message, history=None, audio_input=None):
-    if history is None:
-        history = []
 
-    # If audio input is provided, convert it to text
-    if audio_input:
-        message = voice_to_text(audio_input)
-
-    # Prepare message history for context
-    messages = [{"role": "system", "content": "You are a friendly chatbot."}]
-    for user_msg, bot_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if bot_msg:
-            messages.append({"role": "assistant", "content": bot_msg})
-    messages.append({"role": "user", "content": message})
-
-    # Send message to Groq Cloud API
+# Function to make the API call to Gemini
+def gemini_api_request(message):
     try:
-        # API request payload
-        payload = {
-            "inputs": message,
-            "parameters": {"max_new_tokens": 512}
-        }
-
-        # Send POST request to the Groq Cloud API
-        response = requests.post(API_URL, headers=headers, json=payload)
-
-        if response.status_code == 200:
-            # Get the chatbot's response from the API
-            chat_response = response.json()
-            chatbot_reply = chat_response.get("generated_text", "")
-        else:
-            raise ValueError(f"API Error: {response.status_code}, {response.text}")
-
-    except Exception as e:
-        chatbot_reply = f"Error: {str(e)}"
-
-    # Convert text response to speech
-    audio_output = text_to_voice(chatbot_reply)
-    return chatbot_reply, audio_output
-
-
-# Convert voice input (audio) to text
+        response = requests.post(
+            API_URL,
+            headers=headers,
+            json={"input": message}
+        )
+        
+        # Check if the response status code is OK
+        response.raise_for_status()
+        result = response.json()
+        return result.get("output", "Error: No output returned from API.")
+    
+    except requests.exceptions.RequestException as e:
+        return f"Error: {str(e)}"
+
+# Convert audio to text
 def voice_to_text(audio_path):
     recognizer = sr.Recognizer()
     try:
         with sr.AudioFile(audio_path) as source:
             audio_data = recognizer.record(source)
-            text = recognizer.recognize_google(audio_data)  # Using Google's speech recognition
+            text = recognizer.recognize_google(audio_data)
     except sr.UnknownValueError:
         text = "Sorry, I could not understand the audio."
     except sr.RequestError:
@@ -79,8 +45,7 @@ def voice_to_text(audio_path):
         text = f"Audio Processing Error: {str(e)}"
     return text
 
-
-# Convert text to speech (voice output)
+# Convert text to speech
 def text_to_voice(text):
     try:
         audio_filename = "response.mp3"
@@ -89,16 +54,37 @@ def text_to_voice(text):
         engine.runAndWait()
         return audio_filename
     except Exception as e:
-        print(f"Error converting text to speech: {e}")
+        print(f"TTS Error: {e}")
         return None
 
+# Function to handle both text and voice input/output
+def respond(message, history=None, audio_input=None):
+    try:
+        if history is None:
+            history = []
+        
+        if audio_input:
+            message = voice_to_text(audio_input)
+        
+        if not message.strip():
+            return "Error: No input provided.", None
+        
+        # Make request to Gemini API for processing
+        response = gemini_api_request(message)
+        
+        # Convert response to audio
+        audio_output = text_to_voice(response)
+        
+        return response, audio_output
+    except Exception as e:
+        return f"Error: {str(e)}", None
 
-# Create the Gradio interface
+# Gradio UI
 demo = gr.Interface(
     fn=respond,
     inputs=[
         gr.Textbox(label="Text Input", placeholder="Enter your message..."),
-        gr.Audio(type="filepath", label="Audio Input"),
+        gr.Audio(type="filepath", label="Audio Input")
     ],
     outputs=[
         gr.Textbox(label="Chatbot Response"),