Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
merveΒ 
posted an update Sep 5
Post
5452
I have put together a notebook on Multimodal RAG, where we do not process the documents with hefty pipelines but natively use:
- vidore/colpali for retrieval πŸ“– it doesn't need indexing with image-text pairs but just images!
- Qwen/Qwen2-VL-2B-Instruct for generation πŸ’¬ directly feed images as is to a vision language model with no processing to text!
I used ColPali implementation of the new 🐭 Byaldi library by @bclavie πŸ€—
https://github.com/answerdotai/byaldi
Link to notebook: https://github.com/merveenoyan/smol-vision/blob/main/ColPali_%2B_Qwen2_VL.ipynb
In this post