#help me kapa.ai
1 messages · Page 1 of 1 (latest)
Hi @celest chasm. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Based on the information provided in the knowledge sources, OpenAI's GPT-4 Turbo, released in November 2023, supports image uploads in the Chat Completions API. You can find more details in the vision developer guide (https://platform.openai.com/docs/guides/vision) which provides best practices, rate limits, and more.
If you're using the API, you can upload a file using the following Python code:
from openai import OpenAI
client = OpenAI()
file = client.files.create(
file=open("myfile.pdf", "rb"),
purpose="assistant"
)
Please replace "myfile.pdf" with the path to your image file.
If you're using the GPT Builder, you can upload your own image under the Configure tab.
Please note that you need to have at least $5 in the API for credits and be in at least tier 1 to use the vision API, or any other GPT-4 models. Also, the ability to generate images with DALL·E is not supported in the Free tier and is available to all users on Plus, Team, and Enterprise plans.
If you're still having trouble, it might be a good idea to check the OpenAI community forum (https://community.openai.com/) for similar issues or contact OpenAI support for further assistance.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
@celest chasm kapa.ai is still learning and improving, please let us know how it did by reacting below