I have put together a notebook on Multimodal RAG, where w... | I have put together a notebook on Multimodal RAG, where w...
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 ๐Ÿ“– it doesn't need indexing with image-text pairs but just images!
-
Qwen/Qwen2-VL-2B-Instruct
for generation ๐Ÿ’ฌ directly feed images as is to a vision language model with no processing to text!
I used ColPali implementation of the new ๐Ÿญ Byaldi library by @bclavie ๐Ÿค—
https://github.com/answerdotai/byaldi
Link to notebook: https://github.com/merveenoyan/smol-vision/blob/main/ColPali_%2B_Qwen2_VL.ipynb GitHub - AnswerDotAI/byaldi