Search code, repositories, users, issues, pull requests...
submited by
Style Pass
The V-RAG architecture utilizes a vision language model (VLM) to embed pages of PDF files (or any other document) as vectors directly, without the tedious chunking process.
Check out the background blog post: https://softlandia.fi/en/blog/building-a-rag-tired-of-chunking-maybe-vision-is-all-you-need
This will index the PDF file in to in-memory vector database. This will take some time depending on the size of the PDF file and the GPU you are using in Modal. The current demo is using a A10G GPU.
Read more github.com/S...
