Spaces:
Sleeping
Sleeping
File size: 2,146 Bytes
449b874 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
import os
from groq import Groq
import gradio as gr
import logging
# Set up logging
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
# Initialize the Groq client
api_key = os.environ.get("GROQ_API_KEY")
if not api_key:
logger.error("GROQ_API_KEY environment variable is not set.")
raise ValueError("GROQ_API_KEY environment variable is required.")
client = Groq(api_key=api_key)
MODEL_NAME = os.environ.get("MODEL_NAME", "llama3-8b-8192")
# Define a function to handle chat completions
def get_completion(user_input):
try:
completion = client.chat.completions.create(
model=MODEL_NAME,
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": user_input}
],
temperature=1,
max_tokens=1024,
top_p=1,
stream=True,
stop=None,
)
response = ""
for chunk in completion:
response += chunk.choices[0].delta.content or ""
return response
except Exception as e:
logger.error(f"Error during completion: {e}")
return "Sorry, I encountered an error while processing your request."
# Launch Gradio interface
def launch_interface():
demo = gr.Interface(
fn=get_completion,
inputs=gr.Textbox(
label="Enter your query:",
placeholder="Ask me anything...",
lines=2,
max_lines=5,
show_label=True,
interactive=True
),
outputs=gr.Textbox(
label="Response:",
interactive=False,
show_label=True,
lines=6,
max_lines=10
),
title="Mr AI",
description="Ask anything and get a helpful response.",
theme="default",
css=".gr-box { border-radius: 10px; border: 1px solid #ccc; padding: 10px; }",
allow_flagging="never"
)
logger.info("Starting Gradio interface")
demo.launch(share=True)
if __name__ == "__main__":
launch_interface() |