|
|
import gradio as gr |
|
|
from openai import OpenAI |
|
|
|
|
|
|
|
|
token = "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" |
|
|
endpoint = "https://models.github.ai/inference" |
|
|
model = "openai/gpt-4.1" |
|
|
|
|
|
client = OpenAI( |
|
|
base_url=endpoint, |
|
|
api_key=token, |
|
|
) |
|
|
|
|
|
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 = client.chat.completions.create( |
|
|
messages=messages, |
|
|
temperature=temperature, |
|
|
top_p=top_p, |
|
|
model=model, |
|
|
max_tokens=max_tokens |
|
|
) |
|
|
|
|
|
return response.choices[0].message.content |
|
|
|
|
|
""" |
|
|
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() |
|
|
|
