llama-3-70b / app.py
mipo57's picture
Update app.py
11a3f65 verified
raw
history blame
2.38 kB
import gradio as gr
from openai import OpenAI
from openai import OpenAI
from os import getenv
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key=getenv("OPENROUTER_API_KEY"),
)
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 = ""
completion = client.chat.completions.create(
model="nvidia/llama-3.1-nemotron-70b-instruct",
messages=messages,
stream=True,
# temperature=temperature,
# top_p=top_p,
# max_tokens=max_tokens,
)
for message in completion:
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
"""
with gr.Blocks() as demo:
credentials = gr.State("")
print("CREDENTIALS:")
print(credentials)
@gr.render(inputs=credentials)
def app(app_credentials):
if app_credentials == "2024":
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)",
# ),
],
)
else:
password = gr.Textbox(placeholder="Provide password...")
def set_password(password):
return password
gr.Button("Login").click(set_password, [password], credentials)
if __name__ == "__main__":
demo.launch()