Hi everyone, I’m working on a task where the model needs to generate text based on both an image and some input text (an image-text-to-text task). I want to use few-shot prompting to guide the model, providing examples of the desired input/output behavior. However, I’m running into a conceptual bl…

[image] How can you use the API to merge two pictures? API Yes. You can use multiple base64 images as one user message, and can interleave text with the images sequentially. This is the style of a complete app request with multiple base64 images that only send…

Thanks for the reply. Isn’t there typically an image encoder that creates an image embedding before it is parsed along side the text? If so, passing the base64 image as text to the VLM won’t yield the same results?

The images must be contained in a role message, and only the “user” message is allowed vision input. Your are not passing the image as text if you use the “type” of the user message part correctly. It is just a method of providing the data to the API, a data URL, just as an API request with an int…

How to Include Image-Text Pairs as Few-Shot Examples in Prompts?

Prompting

_j April 17, 2025, 10:37am 2

Topic		Replies	Views
Few shots with multiple images API api , lost-user	1	490	January 28, 2025
How can you use the API to merge two pictures? API	3	1113	January 16, 2025
Gpt-4 vision few shot prompting with images API	3	4501	May 29, 2024
Use base64 encoded images or urls within prompts? API gpt-4	3	13191	August 11, 2025
How to add correct examples for image-to-text task Prompting gpt-4-vision	5	2524	December 29, 2023

How to Include Image-Text Pairs as Few-Shot Examples in Prompts?

Related topics