Post
3808
If you have documents that do not only have text and you're doing retrieval or RAG (using OCR and LLMs), give it up and give ColPali and vision language models a try ๐ค
Why? Documents consist of multiple modalities: layout, table, text, chart, images. Document processing pipelines often consist of multiple models and they're immensely brittle and slow. ๐ฅฒ
How? ColPali is a ColBERT-like document retrieval model built on PaliGemma, it operates over image patches directly, and indexing takes far less time with more accuracy. You can use it for retrieval, and if you want to do retrieval augmented generation, find the closest document, and do not process it, give it directly to a VLM like Qwen2-VL (as image input) and give your text query. ๐ค
This is much faster + you do not lose out on any information + much easier to maintain too! ๐ฅณ
Multimodal RAG merve/multimodal-rag-66d97602e781122aae0a5139 ๐ฌ
Document AI (made it way before, for folks who want structured input/output and can fine-tune a model) merve/awesome-document-ai-65ef1cdc2e97ef9cc85c898e ๐
Why? Documents consist of multiple modalities: layout, table, text, chart, images. Document processing pipelines often consist of multiple models and they're immensely brittle and slow. ๐ฅฒ
How? ColPali is a ColBERT-like document retrieval model built on PaliGemma, it operates over image patches directly, and indexing takes far less time with more accuracy. You can use it for retrieval, and if you want to do retrieval augmented generation, find the closest document, and do not process it, give it directly to a VLM like Qwen2-VL (as image input) and give your text query. ๐ค
This is much faster + you do not lose out on any information + much easier to maintain too! ๐ฅณ
Multimodal RAG merve/multimodal-rag-66d97602e781122aae0a5139 ๐ฌ
Document AI (made it way before, for folks who want structured input/output and can fine-tune a model) merve/awesome-document-ai-65ef1cdc2e97ef9cc85c898e ๐
- 2 replies
