Viewing profile — rawsh

You can actually get solid performance with pretrained chat models: https://raw.sh/posts/chess_puzzles On lichess puzzles gpt4o with the compiled prompt is around 70%, I think the …

Bit confused what the value add is over a framework like DSPy. This still requires you to create an eval dataset with ground truth, basically the only hard part of using DSPy. Easi…

I built a web version with WASM at https://pdfgrep.com a few years ago in case it’s helpful to anyone

https://github.com/VikParuchuri/marker is solid, but slow and needs gpu(s) to be practical

Is it possible to use this for hybrid search in combination with pg_embedding? My understanding is that hybrid search currently requires syncing with Postgres

Documents actually never get uploaded! PDF text extraction happens on the client using a web worker and MuPDF compiled to WASM. 1. PDF parsed and chunked on the client 2. Sparse ve…

Nope, it’s a serious project; I mostly made it for personal use during my last semester of college. I rewrote it a few times and packaged it up because I think it’s genuinely usefu…

Uses hybrid semantic search (combination of dense embeddings and sparse vectors) to retrieve high quality answers across your documents. Features - Significantly faster than compet…

pdfgrep.org is a CLI tool I use a lot to reference documents from classes. I’ve been playing around with Emscripten and I wanted to make a UI version of the tool. All documents sta…

DankGPT is able to draw context from a library of documents (textbook, papers, class slides) to explain any topic and answer complicated reasoning problems. It’s very similar to Ch…

pdfgrep.org is a CLI tool I use a lot to reference documents from classes. I’ve been playing around with Emscripten and I wanted to make a UI version of the tool. All documents sta…