File size: 2,654 Bytes
7efd637 c33dbd2 ca8dc25 c33dbd2 ca8dc25 c33dbd2 e98c6cb c33dbd2 d107cdf c33dbd2 9dc7fb7 c33dbd2 6a8b740 c33dbd2 6719d1c c33dbd2 81fc138 c33dbd2 3807c9a c33dbd2 82ee039 c33dbd2 5e6f5c8 c33dbd2 4d26ed5 7efd637 c33dbd2 |
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 |
import gradio as gr
import os
from together import Together
from typing import List, Tuple
# Initialize Together client
client = Together()
# Ensure API key is set
if "TOGETHER_API_KEY" not in os.environ:
raise ValueError("Please set the TOGETHER_API_KEY environment variable")
def call_llama_vision_api(prompt: str, image_url: str) -> str:
getDescriptionPrompt = "You are a UX/UI designer. Describe the attached screenshot or UI mockup in detail. I will feed in the output you give me to a coding model that will attempt to recreate this mockup, so please think step by step and describe the UI in detail. Pay close attention to background color, text color, font size, font family, padding, margin, border, etc. Match the colors and sizes exactly. Make sure to mention every part of the screenshot including any headers, footers, etc. Use the exact text from the screenshot."
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": getDescriptionPrompt + "\n\n" + prompt},
{
"type": "image_url",
"image_url": {
"url": image_url,
},
},
],
}
]
stream = client.chat.completions.create(
model="meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
messages=messages,
stream=True,
)
response = ""
for chunk in stream:
content = chunk.choices[0].delta.content or ""
response += content
yield response
def chat(message: str, history: List[Tuple[str, str]], image_url: str) -> Tuple[str, List[Tuple[str, str]]]:
if not message:
return "", history
full_response = ""
for partial_response in call_llama_vision_api(message, image_url):
full_response = partial_response
yield "", history + [(message, full_response)]
history.append((message, full_response))
return "", history
# Define the Gradio interface
with gr.Blocks() as demo:
gr.Markdown("# Llama 3.2 Vision Chatbot Demo")
gr.Markdown("Enter your message and an image URL to analyze using the Llama 3.2 Vision model.")
chatbot = gr.Chatbot()
msg = gr.Textbox(label="Your message")
image_url = gr.Textbox(label="Image URL", value="https://napkinsdev.s3.us-east-1.amazonaws.com/next-s3-uploads/d96a3145-472d-423a-8b79-bca3ad7978dd/trello-board.png")
clear = gr.Button("Clear")
msg.submit(chat, [msg, chatbot, image_url], [msg, chatbot])
clear.click(lambda: None, None, chatbot, queue=False)
if __name__ == "__main__":
demo.launch() |