aaaaa

app.py

@@ -27,7 +27,7 @@ def respond(
         history = []
 
     if use_local_model:
-        # Simulate local inference (ignoring history)
+        # local inference 
         messages = [{"role": "system", "content": system_message}]
         for val in history:
             if val[0]:
@@ -53,7 +53,7 @@ def respond(
             yield history + [(message, response)]  # Yield history + new response
 
     else:
-        # API-based inference (ignoring history)
+        # API-based inference 
         messages = [{"role": "system", "content": system_message}]
         for val in history:
             if val[0]:

app_interface.py

@@ -1,141 +0,0 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-import time
-
-# Inference client setup
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-# Global flag to handle cancellation
-stop_inference = False
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    use_local_model,
-):
-    global stop_inference
-    stop_inference = False  # Reset cancellation flag
-
-    if use_local_model:
-        # Simulate local inference
-        time.sleep(2)  # simulate a delay
-        response = "This is a response from the local model."
-        history.append((message, response))
-        yield history
-    else:
-        # API-based inference
-        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,
-        ):
-            if stop_inference:
-                history.append((message, "Inference cancelled."))
-                yield history
-                break
-            token = message.choices[0].delta.content
-            response += token
-            history.append((message, response))
-            yield history
-
-def cancel_inference():
-    global stop_inference
-    stop_inference = True
-
-# Custom CSS for a fancy look
-custom_css = """
-#main-container {
-    background-color: #f0f0f0;
-    font-family: 'Arial', sans-serif;
-}
-
-.gradio-container {
-    max-width: 700px;
-    margin: 0 auto;
-    padding: 20px;
-    background: white;
-    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
-    border-radius: 10px;
-}
-
-.gr-button {
-    background-color: #4CAF50;
-    color: white;
-    border: none;
-    border-radius: 5px;
-    padding: 10px 20px;
-    cursor: pointer;
-    transition: background-color 0.3s ease;
-}
-
-.gr-button:hover {
-    background-color: #45a049;
-}
-
-.gr-slider input {
-    color: #4CAF50;
-}
-
-.gr-chat {
-    font-size: 16px;
-}
-
-#title {
-    text-align: center;
-    font-size: 2em;
-    margin-bottom: 20px;
-    color: #333;
-}
-"""
-
-# Define the interface
-with gr.Blocks(css=custom_css) as demo:
-    gr.Markdown("<h1 style='text-align: center;'>🌟 Fancy AI Chatbot 🌟</h1>")
-    gr.Markdown("Interact with the AI chatbot using customizable settings below.")
-
-    with gr.Row():
-        system_message = gr.Textbox(value="You are a friendly Chatbot.", label="System message", interactive=True)
-        use_local_model = gr.Checkbox(label="Use Local Model", value=False)
-
-    with gr.Row():
-        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
-        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
-        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
-
-    chat_history = gr.Chatbot(label="Chat")
-
-    user_input = gr.Textbox(show_label=False, placeholder="Type your message here...")
-
-    cancel_button = gr.Button("Cancel Inference", variant="danger")
-
-    def chat_fn(message, history):
-        return respond(
-            message,
-            history,
-            system_message.value,
-            max_tokens.value,
-            temperature.value,
-            top_p.value,
-            use_local_model.value,
-        )
-
-    user_input.submit(chat_fn, [user_input, chat_history], chat_history)
-    cancel_button.click(cancel_inference)
-
-if __name__ == "__main__":
-    demo.launch(share=True)

app_original.py

@@ -1,63 +0,0 @@
-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()

app_update_title.py

@@ -1,104 +0,0 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-# Inference client setup
-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
-
-# Custom CSS for a fancy look
-custom_css = """
-#main-container {
-    background-color: #f0f0f0;
-    font-family: 'Arial', sans-serif;
-}
-
-.gradio-container {
-    max-width: 700px;
-    margin: 0 auto;
-    padding: 20px;
-    background: white;
-    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
-    border-radius: 10px;
-}
-
-.gr-button {
-    background-color: #4CAF50;
-    color: white;
-    border: none;
-    border-radius: 5px;
-    padding: 10px 20px;
-    cursor: pointer;
-    transition: background-color 0.3s ease;
-}
-
-.gr-button:hover {
-    background-color: #45a049;
-}
-
-.gr-slider input {
-    color: #4CAF50;
-}
-
-.gr-chat {
-    font-size: 16px;
-}
-
-#title {
-    text-align: center;
-    font-size: 2em;
-    margin-bottom: 20px;
-    color: #333;
-}
-"""
-
-# Define the interface
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message", interactive=True),
-        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)",
-        ),
-    ],
-    css=custom_css,
-    title="🌟 Fancy AI Chatbot 🌟",
-    description="Interact with the AI chatbot using customizable settings below."
-)
-
-if __name__ == "__main__":
-    demo.launch()