Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

• Dify currently supports only text embedding.
• When working with files that contain many images, charts, and tables, these elements need to be converted to text using OCR (Optical Character Recognition) and Document Layout Detection tools.
• Colpali, a multi-modal embedding model, demonstrates impressive Retrieval-Augmented Generation (RAG) performance compared to traditional RAG models.

2. Additional context or comments

This my demo. The retrieves images (after converting pages in a file into images) related to a query and utilizes multimodal LLMs to generate answers. The results are highly impressive.

3. Can you help us with this feature?

• I am interested in contributing to this feature.