Update app.py

app.py

@@ -13,9 +13,9 @@ LLM_MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.2"
 # Initial system prompt
 system_prompt = """"<s>[INST] You are Friday, a helpful and conversational AI assistant, and you respond with one to two sentences. [/INST] Hello there! I'm Friday, how can I help you?</s>"""
 
-# Global variables for initial history
-initial_instruct_history = system_prompt
-initial_formatted_history = ""
+# Global variables for history
+instruct_history = system_prompt
+formatted_history = ""
 
 # Create inference client for text generation
 client = InferenceClient(LLM_MODEL_NAME)
@@ -51,7 +51,9 @@ def generate(instruct_history, temperature=0.1, max_new_tokens=128, top_p=0.95,
     return output
 
 @spaces.GPU(duration=60)
-def transcribe(audio, instruct_history, formatted_history):
+def transcribe(audio, past_history):
+    global instruct_history, formatted_history
+
     sr, y = audio
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
@@ -60,7 +62,8 @@ def transcribe(audio, instruct_history, formatted_history):
     transcribed_user_audio = pipe({"sampling_rate": sr, "raw": y})["text"]
 
     # Append user input to history
-    formatted_history += f"Human: {transcribed_user_audio}\n\n"
+    formatted_history += past_history
+    formatted_history += f"😃 Human: {transcribed_user_audio}\n\n"
     instruct_history += f"<s>[INST] {transcribed_user_audio} [/INST] "
 
     # Generate LLM response
@@ -68,21 +71,19 @@ def transcribe(audio, instruct_history, formatted_history):
 
     # Append AI response to history
     instruct_history += f" {llm_response}</s>"
-    formatted_history += f"Friday: {llm_response}\n\n"
+    formatted_history += f"🤖 Friday: {llm_response}\n\n"
 
     # Convert AI response to audio
     audio_response = gTTS(llm_response)
     audio_response.save("response.mp3")
 
-    # Return the updated history and audio
-    return "response.mp3", formatted_history, instruct_history
+    print("Formatted History: ", formatted_history)
 
-with gr.Blocks() as demo:
-    gr.HTML("<center><h1>Friday: AI Virtual Assistant</h1><center>")
+    # Return the full conversation history
+    return "response.mp3", formatted_history
 
-    # Initialize state
-    instruct_state = gr.State(value=initial_instruct_history)
-    formatted_state = gr.State(value=initial_formatted_history)
+with gr.Blocks() as demo:
+    gr.HTML("<center><h1>Friday: AI Virtual Assistant 🤖</h1><center>")
 
     with gr.Row():
         audio_input = gr.Audio(label="Human", sources="microphone")
@@ -93,13 +94,8 @@ with gr.Blocks() as demo:
     # Textbox to display the full conversation history
     transcription_box = gr.Textbox(label="Transcription", lines=10, placeholder="Conversation History...")
 
-    # Pass states to the transcribe function and update them after each click
-    transcribe_btn.click(
-        fn=transcribe,
-        inputs=[audio_input, instruct_state, formatted_state],
-        outputs=[output_audio, transcription_box, instruct_state, formatted_state]
-    )
+    transcribe_btn.click(fn=transcribe, inputs=[audio_input, transcription_box], outputs=[output_audio, transcription_box])
 
 if __name__ == "__main__":
     demo.queue()
-    demo.launch()
+    demo.launch()