$ cat /etc/cookies.conf
We use cookies to understand how people use this site.
Analytics cookies help us improve your experience.
They are off by default. Nothing tracks you until you say so.
$ select cookie_preferences
Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Demonstrates a proof‑of‑concept using modern retrieval methods—late interaction, OCR‑free pipelines, reasoning retrievers, and hypothetical embeddings—to improve agentic systems in real‑world scenarios.
There are some amazing innovative tools available for agents nowadays, while most AI chatbots are still using naive RAG. There have been advances such as late interaction (Modern ColBERT) which outperform naive RAG and BM25. The Colpali Gemma pipeline allows OCR less retrieval. Retrievers such as Promptrievers and Rank one have reasoning capabilities built into them. And, hypothetical document embeddings offer a representation of the data fitting the user’s thinking and intent.
Loading recent emails...