Embeddings and Retrieval for LLMs: Techniques and Challenges // Anton Troynikov // LLMs in Prod Con
HTML-код
- Опубликовано: 4 июл 2023
- This portion is sponsored by Chroma.
Website: docs.trychroma.com/
Chroma is the open-source embedding database. Chroma makes it easy to build LLM apps by making knowledge, facts, and skills pluggable for LLMs.
//Abstract
Retrieval augmented generation with embeddings and LLMs has become an important workflow for AI applications.
While embedding-based retrieval is very powerful for applications like 'chat with my documents', users and developers should be aware of key limitations, and techniques to mitigate them.
//Bio
Anton Troynikov is the cofounder of Chroma, an open source embedding store built for AI applications. Previously, Anton worked on robotics with a focus on 3D computer vision. He does not believe AI is going to kill us all. Наука
Loved the talk and details on vector dbs.
Also, love the hat.
Loving the presentation, but hate the border. The border occupy most part of the screen and it is hard to see the presentation slides.
Also hate the placement adz
nobody forcing you to watch free content