Spaces:
Running
Running
File size: 2,769 Bytes
058a98e |
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 |
# Import the necessary libraries
import gradio as gr
import openai
import base64
from PIL import Image
import io
import requests
import os
# Consider using environment variables or a configuration file for API keys.
# WARNING: Do not hardcode API keys in your code, especially if sharing or using version control.
openai.api_key = os.getenv('OPENAI_API_KEY')
if openai.api_key is None:
raise ValueError("Please set the OPENAI_API_KEY environment variable.")
# Function to encode the image to base64
def encode_image_to_base64(image):
buffered = io.BytesIO()
image.save(buffered, format="JPEG")
img_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
return img_str
# Function to send the image to the OpenAI API and get a response
def ask_openai_with_image(image):
# Encode the uploaded image to base64
base64_image = encode_image_to_base64(image)
# Create the payload with the base64 encoded image
payload = {
"model": "gpt-4-vision-preview",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "I've uploaded an image and I'd like to know what it depicts and any interesting details you can provide."
},
{
"type": "image_url",
"image_url": f"data:image/jpeg;base64,{base64_image}"
}
]
}
],
"max_tokens": 4095
}
# Send the request to the OpenAI API
response = requests.post(
"https://api.openai.com/v1/chat/completions",
headers={"Authorization": f"Bearer {openai.api_key}"},
json=payload
)
# Check if the request was successful
if response.status_code == 200:
response_json = response.json()
print("Response JSON:", response_json) # Print the raw response JSON
try:
# Attempt to extract the content text
return response_json["choices"][0]["message"]["content"]
except Exception as e:
# If there is an error in the JSON structure, print it
print("Error in JSON structure:", e)
print("Full JSON response:", response_json)
return "Error processing the image response."
else:
# If an error occurred, return the error message
return f"Error: {response.text}"
# Create a Gradio interface
iface = gr.Interface(
fn=ask_openai_with_image,
inputs=gr.Image(type="pil"),
outputs="text",
title="GPT-4 with Vision",
description="Upload an image and get a description from GPT-4 with Vision."
)
# Launch the app
iface.launch() |