Spaces:
Sleeping
Sleeping
File size: 2,578 Bytes
e9b1dea 4b6721a e9b1dea 4b6721a e9b1dea 4b6721a e9b1dea 4b6721a e9b1dea 4b6721a bb0fd16 4b6721a bb0fd16 4b6721a bb0fd16 4b6721a bb0fd16 4b6721a bb0fd16 4b6721a e9b1dea 4b6721a |
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 75 76 77 78 79 80 81 82 83 |
import os
import requests
import gradio as gr
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
# Fetch token from environment variables
CLOUDFLARE_TOKEN = os.getenv("CLOUDFLARE_TOKEN")
if not CLOUDFLARE_TOKEN:
raise EnvironmentError("CLOUDFLARE_TOKEN not found in environment variables.")
# Function to send API requests to the Gemma model
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
try:
# Construct the messages payload
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})
# Define API endpoint and headers
url = "https://api.cloudflare.com/client/v4/accounts/e16531aac7469b4b54ef1e8108e93495/ai/run/@cf/google/gemma-2b-it-lora"
headers = {
"Authorization": f"Bearer {CLOUDFLARE_TOKEN}",
"Content-Type": "application/json",
}
# Payload with model settings and messages
payload = {
"messages": messages,
"raw": "true",
"lora": "1b3c4e5c-ba8a-4e98-973b-573c572cfb34",
"max_tokens": max_tokens,
"temperature": temperature,
"top_p": top_p,
}
# Make the API request
response = requests.post(url, headers=headers, json=payload)
if response.status_code == 200:
data = response.json()
# Extract response content
result = data.get("result", {}).get("response", "No response found.")
return result
else:
return f"Error: {response.status_code} - {response.text}"
except Exception as e:
return f"An error occurred: {str(e)}"
# Gradio Interface
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()
|