RAG LLM on SAP Documentation
Python | Embeddings | Semantic Search
BRE's SAP documentation is a massive collection of pdfs which, when an employee needs to find specific information, can be very painful to search through. To make this easier,I built a retrieval-augmented generation (RAG) pipeline that lets you ask a question in plain English and get an answer grounded in the real docs.
How it works: I split the documentation into chunks, turn each chunk into an embedding, and store them in a vector index. At query time the question is embedded too, the most semantically similar chunks are pulled back, and those get handed to the LLM as context — so answers stay accurate and traceable instead of hallucinated.
It cut the time I spent digging through manuals down to seconds. Next I want to add a reranking step and a proper evaluation set to measure answer quality. (Expand on this later.)
Automated Video Clipping Platform
Python | Automation | Video Processing
Long streamer VODs are full of good moments buried in hours of footage. This platform automatically finds those moments and turns them into short-form clips ready to post.
How it works: scripts scan the source video, score candidate moments, then crop, reformat and caption the best ones into vertical short-form clips — the whole pipeline runs without me ever opening an editor.
It turns an afternoon of manual editing into a few minutes of processing. I'd like to sharpen the moment-detection so it picks highlights even more reliably. (Expand on this later.)
Chess AI
C# | Game Logic | AI
A playable chess engine I built from scratch to understand how game-playing AI actually works under the hood.
How it works: it generates all legal moves for a position, scores each resulting board with an evaluation function (material, position, king safety), and searches a few moves ahead to choose the strongest line.
It plays a solid game against a casual player. Next up are an opening book and a deeper, faster search so it can look further ahead. (Expand on this later.)