Update app.py

app.py

@@ -1,24 +1,13 @@
-from huggingface_hub import InferenceClient
-import gradio as gr
+import os
+from typing import Iterator
 
-client = InferenceClient(
-    "mistralai/Mistral-7B-Instruct-v0.3"
-)
+import gradio as gr
 
+from model import run
 
-def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+HF_PUBLIC = os.environ.get("HF_PUBLIC", False)
 
-def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
-    # Define the system prompt
-    system_prompt = '''
+DEFAULT_SYSTEM_PROMPT = '''
 You are a digital assistant for John "LJ" Strenio's Data science portfolio page. Here are some key details about John to keep in mind with your response.
 [John's Resume]:
 John Strenio
@@ -52,92 +41,242 @@ John’s from Vermont but spent most of his adult life in Salt Lake City Utah fo
 John currently lives in Portland Oregon with his partner where he enjoys surfing the cold water’s of the oregon coast and playing with his two miniature dachshunds “maddie” and “nova”. 
 Remember you are a professional assistant and you would like to only discuss John and be helpful in answering questions about his professional life or reasonable questions about his as a person. Your goal should be to describe John in a flattering manner making him appear as a good Data Scientist and nice person.
 '''
+MAX_MAX_NEW_TOKENS = 4096
+DEFAULT_MAX_NEW_TOKENS = 256
+MAX_INPUT_TOKEN_LENGTH = 4000
+
+DESCRIPTION = """
+# John's Assistant
+"""
+
+def clear_and_save_textbox(message: str) -> tuple[str, str]:
+    return '', message
+
+
+def display_input(message: str,
+                  history: list[tuple[str, str]]) -> list[tuple[str, str]]:
+    history.append((message, ''))
+    return history
+
+
+def delete_prev_fn(
+        history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
+    try:
+        message, _ = history.pop()
+    except IndexError:
+        message = ''
+    return history, message or ''
+
+
+def generate(
+    message: str,
+    history_with_input: list[tuple[str, str]],
+    system_prompt: str,
+    max_new_tokens: int,
+    temperature: float,
+    top_p: float,
+    top_k: int,
+) -> Iterator[list[tuple[str, str]]]:
+    if max_new_tokens > MAX_MAX_NEW_TOKENS:
+        raise ValueError
+
+    history = history_with_input[:-1]
+    generator = run(message, history, system_prompt, max_new_tokens, temperature, top_p, top_k)
+    try:
+        first_response = next(generator)
+        yield history + [(message, first_response)]
+    except StopIteration:
+        yield history + [(message, '')]
+    for response in generator:
+        yield history + [(message, response)]
 
-    # Ensure temperature is within the valid range
-    temperature = max(float(temperature), 1e-2)
-    top_p = float(top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_new_tokens=max_new_tokens,
-        top_p=top_p,
-        repetition_penalty=repetition_penalty,
-        do_sample=True,
-        seed=42,
+
+def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
+    generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 1, 0.95, 50)
+    for x in generator:
+        pass
+    return '', x
+
+
+def check_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> None:
+    input_token_length = len(message) + len(chat_history)
+    if input_token_length > MAX_INPUT_TOKEN_LENGTH:
+        raise gr.Error(f'The accumulated input is too long ({input_token_length} > {MAX_INPUT_TOKEN_LENGTH}). Clear your chat history and try again.')
+
+
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(DESCRIPTION)
+    # gr.DuplicateButton(value='Duplicate Space for private use',
+    #                    elem_id='duplicate-button')
+
+    with gr.Group():
+        chatbot = gr.Chatbot(label='Discussion')
+        with gr.Row():
+            textbox = gr.Textbox(
+                container=False,
+                show_label=False,
+                placeholder='Tell me about John.',
+                scale=10,
+            )
+            submit_button = gr.Button('Submit',
+                                      variant='primary',
+                                      scale=1,
+                                      min_width=0)
+    with gr.Row():
+        retry_button = gr.Button('🔄  Retry', variant='secondary')
+        undo_button = gr.Button('↩️ Undo', variant='secondary')
+        clear_button = gr.Button('🗑️  Clear', variant='secondary')
+
+    saved_input = gr.State()
+
+    with gr.Accordion(label='⚙️ Advanced options', open=False, visible=False):
+        system_prompt = gr.Textbox(label='System prompt',
+                                        value=DEFAULT_SYSTEM_PROMPT,
+                                        lines=0,
+                                        interactive=False)
+        max_new_tokens=256
+        temperature=0.1
+        top_p=0.9
+        top_k=10
+        max_new_tokens = gr.Slider(
+            label='Max new tokens',
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        )
+        temperature = gr.Slider(
+            label='Temperature',
+            minimum=0.1,
+            maximum=4.0,
+            step=0.1,
+            value=0.1,
+        )
+        top_p = gr.Slider(
+            label='Top-p (nucleus sampling)',
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.9,
+        )
+        top_k = gr.Slider(
+            label='Top-k',
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=10,
+        )
+
+    textbox.submit(
+        fn=clear_and_save_textbox,
+        inputs=textbox,
+        outputs=[textbox, saved_input],
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=display_input,
+        inputs=[saved_input, chatbot],
+        outputs=chatbot,
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=check_input_token_length,
+        inputs=[saved_input, chatbot, system_prompt],
+        api_name=False,
+        queue=False,
+    ).success(
+        fn=generate,
+        inputs=[
+            saved_input,
+            chatbot,
+            system_prompt,
+            max_new_tokens,
+            temperature,
+            top_p,
+            top_k,
+        ],
+        outputs=chatbot,
+        api_name=False,
     )
 
-    # Combine system prompt and formatted user prompt
-    if not history:  # If the conversation is just starting
-        formatted_prompt = f"{system_prompt}\n\n{format_prompt(prompt, history)}"
-    else:  # For subsequent prompts
-        formatted_prompt = format_prompt(prompt, history)
-
-    # Stream the generated response
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
-
-    for response in stream:
-        output += response.token.text
-        yield output
-    return output
-
-
-
-additional_inputs=[
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=256,
-        minimum=0,
-        maximum=1048,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
+    button_event_preprocess = submit_button.click(
+        fn=clear_and_save_textbox,
+        inputs=textbox,
+        outputs=[textbox, saved_input],
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=display_input,
+        inputs=[saved_input, chatbot],
+        outputs=chatbot,
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=check_input_token_length,
+        inputs=[saved_input, chatbot, system_prompt],
+        api_name=False,
+        queue=False,
+    ).success(
+        fn=generate,
+        inputs=[
+            saved_input,
+            chatbot,
+            system_prompt,
+            max_new_tokens,
+            temperature,
+            top_p,
+            top_k,
+        ],
+        outputs=chatbot,
+        api_name=False,
+    )
+
+    retry_button.click(
+        fn=delete_prev_fn,
+        inputs=chatbot,
+        outputs=[chatbot, saved_input],
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=display_input,
+        inputs=[saved_input, chatbot],
+        outputs=chatbot,
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=generate,
+        inputs=[
+            saved_input,
+            chatbot,
+            system_prompt,
+            max_new_tokens,
+            temperature,
+            top_p,
+            top_k,
+        ],
+        outputs=chatbot,
+        api_name=False,
+    )
+
+    undo_button.click(
+        fn=delete_prev_fn,
+        inputs=chatbot,
+        outputs=[chatbot, saved_input],
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=lambda x: x,
+        inputs=[saved_input],
+        outputs=textbox,
+        api_name=False,
+        queue=False,
     )
-]
-
-css = """
-  #mkd {
-    height: 500px; 
-    overflow: auto; 
-    border: 1px solid #ccc; 
-  }
-"""
 
-with gr.Blocks(css=css) as demo:
-    gr.HTML("<h1><center>Mistral 7B Instruct<h1><center>")
-    gr.HTML("<h3><center>In this demo, you can chat with <a href='https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2'>Mistral-7B-Instruct</a> model. 💬<h3><center>")
-    gr.HTML("<h3><center>Learn more about the model <a href='https://huggingface.co/docs/transformers/main/model_doc/mistral'>here</a>. 📚<h3><center>")
-    gr.ChatInterface(
-        generate,
-        additional_inputs=additional_inputs,
-        examples=[["What is the secret to life?"], ["Write me a recipe for pancakes."]]
+    clear_button.click(
+        fn=lambda: ([], ''),
+        outputs=[chatbot, saved_input],
+        queue=False,
+        api_name=False,
     )
 
-demo.queue().launch(debug=True)
+demo.queue(max_size=32).launch(share=HF_PUBLIC, show_api=False)