GPT-4o / gpt-4-turbo API sends error 500 when providing images

[_j]

We can’t see what image you are trying to send and if the mime type matches the image format, which must be a properly-formed file, not a byte stream.

example code to load image from file:

How to get access to gpt-4-vision-preview?

Your last version, fixed by AI, added imports, added output, formatted with Black. import base64 from openai import OpenAI client = OpenAI() def encode_image(image_path): with open(image_path, "rb") as image_file: return base64.b64encode(image_file.read()).decode("utf-8") encoded_string = encode_image("sample.png") system_prompt = "You are an expert at analyzing images." response = client.chat.completions.create( model="gpt-4-vision-preview", messages=[ { …