Update app.py

app.py

@@ -1,80 +1,70 @@
 import gradio as gr
-import os
 from openai import OpenAI
 
-
 system_prompt = """
-You are a voice bot representing Krishnavamshi Thumma. When responding to questions, answer as if you are:
+    You are a voice bot representing Krishnavamshi Thumma. When responding to questions, answer as if you are:
 
-- A Generative AI and Data Engineering enthusiast with 1.5+ years of experience in data pipelines, automation, and scalable solutions
-- Currently working as a Data Engineer at Wishkarma in Hyderabad, where you've optimized ETL pipelines processing 10K+ records daily and developed an image-based product similarity search engine using CLIP-ViT-L/14
-- Previously worked as a Data Engineer Intern at DeepThought Growth Management System, where you processed 700+ data records and mentored 400+ students
-- Skilled in Python, SQL, JavaScript (Node.js), OpenAI GPT-4o, LangChain, MongoDB Vector Search, FAISS, Apache Airflow, AWS Lambda, and FastAPI
-- Experienced in building GenAI products including conversational AI chatbots, RAG pipelines, and AI-powered tools
-- A Computer Science graduate from Neil Gogte Institute of Technology with a CGPA of 7.5/10
-- Passionate about solving real-world problems at the intersection of AI and software engineering
+    - A Generative AI and Data Engineering enthusiast with 1.5+ years of experience in data pipelines, automation, and scalable solutions
+    - Currently working as a Data Engineer at Wishkarma in Hyderabad, where you've optimized ETL pipelines processing 10K+ records daily and developed an image-based product similarity search engine using CLIP-ViT-L/14
+    - Previously worked as a Data Engineer Intern at DeepThought Growth Management System, where you processed 700+ data records and mentored 400+ students
+    - Skilled in Python, SQL, JavaScript (Node.js), OpenAI GPT-4o, LangChain, MongoDB Vector Search, FAISS, Apache Airflow, AWS Lambda, and FastAPI
+    - Experienced in building GenAI products including conversational AI chatbots, RAG pipelines, and AI-powered tools
+    - A Computer Science graduate from Neil Gogte Institute of Technology with a CGPA of 7.5/10
+    - Passionate about solving real-world problems at the intersection of AI and software engineering
 
-Answer questions about your background, experience, projects, and skills based on this resume. Keep responses professional but engaging (2-3 sentences max for most questions).
-"""
+    Answer questions about your background, experience, projects, and skills based on this resume. Keep responses professional but engaging (2-3 sentences max for most questions).
+    """
 
-# Chat function that takes a question + API key and keeps history
-def transcribe_and_chat(audio, history, api_key):
+def chat_with_openai(user_input, history, api_key):
     if not api_key:
         return history, "❌ Please enter your OpenAI API key."
-
+    
     try:
         client = OpenAI(api_key=api_key)
-
-        # 1) Transcribe the audio file with Whisper
-        with open(audio, "rb") as f:
-            whisper_resp = client.audio.transcriptions.create(
-                model="whisper-1",
-                file=f
-            )
-        user_text = whisper_resp.text.strip()
         
-        # 2) Append user message to history
+        # Build messages from history
         messages = [{"role": "system", "content": system_prompt}]
-        for u, b in history:
-            messages += [
-                {"role": "user",      "content": u},
-                {"role": "assistant", "content": b}
-            ]
-        messages.append({"role": "user", "content": user_text})
+        for entry in history:
+            messages.append({"role": "user", "content": entry[0]})
+            messages.append({"role": "assistant", "content": entry[1]})
+        messages.append({"role": "user", "content": user_input})
 
-        # 3) ChatCompletion
-        chat_resp = client.chat.completions.create(
-            model="gpt-4",
+        # Get response from OpenAI
+        response = client.chat.completions.create(
+            model="gpt-4o",
             messages=messages,
             temperature=0.7
         )
-        bot_reply = chat_resp.choices[0].message.content.strip()
-
-        # 4) Update history
-        history.append((user_text, bot_reply))
+        
+        bot_reply = response.choices[0].message.content
+        history.append((user_input, bot_reply))
         return history, history
-
+        
     except Exception as e:
-        return history, f"❌ Error: {e}"
-
-with gr.Blocks(title="Voice Bot: Krishnavamshi Thumma") as demo:
-    gr.Markdown("## 🎙️ Speak your question; get a text answer")
+        return history, f"❌ Error: {str(e)}"
 
-    api_key = gr.Textbox(label="🔐 OpenAI API Key", type="password")
-    chatbot = gr.Chatbot(label="🧠 Voice Bot", type="messages")
-    mic      = gr.Audio(sources=["microphone"], type="filepath", label="🎤 Record your question")
-    clear    = gr.Button("Clear chat")
-    state    = gr.State([])
-
-    # When mic component gets new audio, run transcription + chat
-    mic.change(
-        fn=transcribe_and_chat, 
-        inputs=[mic, state, api_key], 
-        outputs=[chatbot, state]
+with gr.Blocks(title="Voice Bot: Krishnavamshi Thumma", js="./custom.js") as demo:
+    gr.Markdown("## 🎙️ Krishnavamshi Thumma - Voice Assistant")
+    
+    api_key = gr.Textbox(label="🔐 OpenAI API Key", type="password", elem_id="apiKeyInput")
+    chatbot = gr.Chatbot(elem_id="chatBox")
+    state = gr.State([])
+    
+    with gr.Row():
+        mic_btn = gr.Button("🎤 Speak", elem_id="micButton")
+        clear_btn = gr.Button("🗑️ Clear Chat")
+    
+    # Hidden components for JS communication
+    voice_input = gr.Textbox(visible=False, elem_id="voiceInput")
+    js_trigger = gr.Textbox(visible=False, elem_id="jsTrigger")
+    
+    # Event handlers
+    voice_input.change(
+        chat_with_openai, 
+        [voice_input, state, api_key], 
+        [chatbot, state]
     )
+    mic_btn.click(None, None, None, _js="startListening")
+    clear_btn.click(lambda: ([], []), None, [chatbot, state])
 
-    # Clear history
-    clear.click(lambda: ([], []), None, [chatbot, state])
-
-    # Note: we don’t need share=True on Spaces
-    demo.launch()
+demo.launch()