Spaces:
Running
Running
File size: 3,708 Bytes
058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d 058a98e 6d09e4d |
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 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
# Import the necessary libraries
import gradio as gr
import openai
import base64
import io
import requests
# 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(api_key, instruction, json_prompt, low_quality_mode, image):
# Set the OpenAI API key
openai.api_key = api_key
# Encode the uploaded image to base64
base64_image = encode_image_to_base64(image)
instruction = instruction.strip()
if json_prompt.strip() != "":
instruction = f"{instruction}\n\nReturn in JSON format and include the following attributes:\n\n{json_prompt.strip()}"
# Create the payload with the base64 encoded image
payload = {
"model": "gpt-4-vision-preview",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": instruction,
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{base64_image}",
"detail": "low" if low_quality_mode else "high",
},
},
],
}
],
"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}"
json_schema = gr.Textbox(
label="JSON Attributes",
info="Define a list of attributes to force the model to respond in valid json format. Leave blank to disable json formatting.",
lines=3,
placeholder="""Example:
- name: Name of the object
- color: Color of the object
""",
)
instructions = gr.Textbox(
label="Instructions",
info="Instructions for the vision model to follow. Leave blank to use default.",
lines=2,
placeholder="""Default:
I've uploaded an image and I'd like to know what it depicts and any interesting details you can provide.""",
)
low_quality_mode = gr.Checkbox(
label="Low Quality Mode",
info="See here: https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding.",
)
# Create a Gradio interface
vision_playground = gr.Interface(
fn=ask_openai_with_image,
inputs=[
gr.Textbox(label="API Key"),
instructions,
json_schema,
low_quality_mode,
gr.Image(type="pil", label="Image"),
],
outputs=[gr.Markdown()],
title="GPT-4-Vision Playground",
description="Upload an image and get a description from GPT-4 with Vision.",
)
# Launch the app
vision_playground.launch()
|