v1

app.py

@@ -0,0 +1,120 @@
+import gradio as gr
+import speech_recognition as sr
+
+def speech_to_text(audio):
+    recognizer = sr.Recognizer()
+    try:
+        with sr.AudioFile(audio) as source:
+            audio_data = recognizer.record(source)
+            try:
+                text = recognizer.recognize_google(audio_data)
+            except sr.UnknownValueError:
+                text = "Google Speech Recognition could not understand the audio"
+            except sr.RequestError as e:
+                text = f"Could not request results from Google Speech Recognition service; {e}"
+    except Exception as e:
+        text = f"Could not process the audio, please try to record one more time"
+    return text
+
+def chatbot_response(user_input):
+    if user_input.lower() == "hello":
+        return "Hi there! How can I help you?"
+    elif user_input.lower() == "how are you?":
+        return "I'm just a bot, but I'm functioning well! How about you?"
+    elif user_input.lower() == "what can you do?":
+        return "I can help answer questions, provide information, and assist with various tasks."
+    else:
+        return "I'm not sure how to respond to that. Can you please ask something else?"
+
+def llm_ui():
+    with gr.Blocks() as demo:
+        gr.Markdown("# AI Chatbot")
+
+        def respond(message, chat_history):
+            bot_message = chatbot_response(message)
+            chat_history.append((message, bot_message))
+            return "", chat_history
+
+        def clear_chat(chat_history):
+            return []
+
+        def load_previous_conversation():
+            # Logic to load previous conversation
+            return []
+
+        def transcribe_audio(audio):
+            text = speech_to_text(audio)
+            return text
+
+        with gr.Row():
+            chatbot = gr.Chatbot()
+        with gr.Row():
+            model_selection = gr.Dropdown(["Model 1", "Model 2", "Model 3"], label="Select Model", scale=3)
+            clear_button = gr.Button("Clear Chat", scale=2)
+            load_button = gr.Button("Load Previous Conversation", scale=2)
+        with gr.Row():
+            user_input = gr.Textbox(placeholder="Type your message here...", label="User Input", show_label=False, scale=8)
+            send_button = gr.Button("Send", scale=2, elem_id="send-button")
+        with gr.Row():
+            voice_input = gr.Microphone(type="filepath", label="Voice Input", scale=7)
+            voice_button = gr.Button("Use Audio as User Input", scale=3)
+            voice_button.click(transcribe_audio, inputs=voice_input, outputs=user_input)
+
+        send_button.click(respond, [user_input, chatbot], [user_input, chatbot])
+        clear_button.click(clear_chat, [chatbot], [chatbot])
+        load_button.click(load_previous_conversation, [], [chatbot])
+
+        demo.css = """
+        #send-button {
+            background-color: orange;
+        }
+        """
+    return demo
+
+def multimodal_llm_ui():
+    with gr.Blocks() as demo:
+        gr.Markdown("# AI Chatbot")
+
+        def respond(message, chat_history):
+            bot_message = chatbot_response(message)
+            chat_history.append((message, bot_message))
+            return "", chat_history
+
+        def clear_chat(chat_history):
+            return []
+
+        def load_previous_conversation():
+            # Logic to load previous conversation
+            return []
+
+        def transcribe_audio(audio):
+            text = speech_to_text(audio)
+            return text
+
+        with gr.Row():
+            chatbot = gr.Chatbot(height=550)
+            with gr.Column():
+                with gr.Row():
+                    model_selection = gr.Dropdown(["Model 1", "Model 2", "Model 3"], label="Select Model", scale=3)
+                    clear_button = gr.Button("Clear Chat", scale=2)
+                    load_button = gr.Button("Load Previous Conversation", scale=2)
+
+                image_input = gr.Image(type="filepath", label="Input your Image Here....")
+                with gr.Row():
+                    user_input = gr.Textbox(placeholder="Type your message here...", label="User Input", show_label=False, scale=8)
+                    send_button = gr.Button("Send", scale=2, elem_id="send-button")
+
+                with gr.Row():
+                    voice_input = gr.Microphone(type="filepath", label="Voice Input", scale=7)
+                    voice_button = gr.Button("Use Audio as User Input", scale=3)
+                    voice_button.click(transcribe_audio, inputs=voice_input, outputs=user_input)
+
+        send_button.click(respond, [user_input, chatbot], [user_input, chatbot])
+        clear_button.click(clear_chat, [chatbot], [chatbot])
+        load_button.click(load_previous_conversation, [], [chatbot])
+    return demo
+
+demo = gr.TabbedInterface([llm_ui(), multimodal_llm_ui()], ["LLM", "Image + LLM"],
+                         theme='snehilsanyal/scikit-learn')
+
+demo.launch()