Spaces:
Runtime error
Runtime error
from typing import Iterator, List, Tuple | |
import gradio as gr | |
from model import get_input_token_length, run | |
DEFAULT_SYSTEM_PROMPT = """\ | |
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. | |
Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. | |
Please ensure that your responses are socially unbiased and positive in nature. | |
INPUTTED JSON | |
"[{\n \"TEXT\": \"2PI AI TECH | 2\u00cf\u0080 360\u00c2\u00b0 AI | Irrational Is The New Rational\",\n \"IMAGES\": [\"assets/images/logo-1.png\", \"assets/images/banner/PROJECTS.png\"],\n \"VIDEOS\": [],\n \"URLs\": [\n \"index.html\",\n \"products.html\",\n \"team.html\",\n \"index.html#about\",\n \"contact.html\",\n \"https://www.linkedin.com/company/2piai\",\n \"darwin.html\",\n \"fashion.html\n \"coming-soon.html\",\n \"http://chatbot.thomascook.mwater.nl/\",\n \"fraud.html\",\n \"mailto:[email protected]\"\n ],\n \"EMAILS\": [\"[email protected]\"]\n},\n{\n \"TEXT\": \"AI Powered ChatBot\",\n \"IMAGES\": [\"assets/videos/AI_CHATBOT.png\"],\n \"VIDEOS\": []\n},\n{\n \"TEXT\": \"Model Training Platform\",\n \"IMAGES\": [\"assets/videos/DARWIN_AI.png\"],\n \"VIDEOS\": []\n},\n{\n \"TEXT\": \"Fashion Powered by AI\",\n \"IMAGES\": [\"assets/videos/NEYSA_AI.png\"],\n \"VIDEOS\": []\n},\n{\n \"TEXT\": \"Quant AI\",\n \"IMAGES\": [\"assets/videos/QUANT_AI.png\"],\n \"VIDEOS\": []\n},\n{\n \"TEXT\": \"Search Engine Powered by AI\",\n \"IMAGES\": [\"assets/videos/AI_QA_SEARCH.png\"],\n \"VIDEOS\": []\n},\n{\n \"TEXT\": \"Fraud Detection\",\n \"IMAGES\": [\"assets/videos/FRAUD_AI.png\"],\n \"VIDEOS\": []\n}]" | |
""" | |
MAX_MAX_NEW_TOKENS = 1024 * 2 | |
DEFAULT_MAX_NEW_TOKENS = 1024 * 0.25 | |
MAX_INPUT_TOKEN_LENGTH = 1024 * 8 | |
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)] | |
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 = get_input_token_length(message, chat_history, system_prompt) | |
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() as demo: | |
with gr.Group(): | |
chatbot = gr.Chatbot(label='Chatbot') | |
with gr.Row(): | |
textbox = gr.Textbox( | |
container=False, | |
show_label=False, | |
placeholder='Type a message...', | |
scale=10, | |
) | |
submit_button = gr.Button('Submit', | |
variant='primary', | |
scale=1, | |
min_width=0) | |
with gr.Row(): | |
retry_button = gr.Button('π Retry', variant='secondary') | |
undo_button = gr.Button('β©οΈ Undo', variant='secondary') | |
clear_button = gr.Button('ποΈ Clear', variant='secondary') | |
saved_input = gr.State() | |
with gr.Accordion(label='Advanced options', open=True): | |
system_prompt = gr.Textbox(label='System prompt', | |
value=DEFAULT_SYSTEM_PROMPT, | |
lines=6) | |
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=0.99, | |
) | |
top_p = gr.Slider( | |
label='Top-p (nucleus sampling)', | |
minimum=0.05, | |
maximum=1.0, | |
step=0.05, | |
value=0.99, | |
) | |
top_k = gr.Slider( | |
label='Top-k', | |
minimum=1, | |
maximum=1000, | |
step=1, | |
value=1000, | |
) | |
gr.Examples( | |
examples=[ | |
'Hello there! How are you doing?', | |
'Can you explain briefly to me what is the Python programming language?', | |
'Explain the plot of Cinderella in a sentence.', | |
'How many hours does it take a man to eat a Helicopter?', | |
"Write a 100-word article on 'Benefits of Open-Source in AI research'", | |
], | |
inputs=textbox, | |
outputs=[textbox, chatbot], | |
fn=process_example, | |
cache_examples=True, | |
) | |
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, | |
) | |
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, | |
) | |
clear_button.click( | |
fn=lambda: ([], ''), | |
outputs=[chatbot, saved_input], | |
queue=False, | |
api_name=False, | |
) | |
if __name__ == '__main__': | |
demo.queue(max_size=20).launch(server_name='0.0.0.0', server_port=8080, debug=True, show_error=True) | |