Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
March 14, 2024
·
Seattle
OutlookLLM
Learn how to integrate a local LLM into Outlook on Windows, enabling private email composition, thread summarization, and inbox Q&A via TensorRT-LLM.
Overview
Outlook Add-in to use Generative AI features (Email composition, Email Thread Summarization (WIP), Inbox Q&A(WIP) securely and privately. It uses a local LLM (e.g. Mistral 7B IT, Gemma 7B IT) served via Nvidia TensorRT-LLM. on windows.
Links
Outlook add-in integrates local LLM inference via Nvidia TensorRT-LLM.
Secure Outlook Add-in integrates Generative AI for email drafting and thread summarization.
Tech stack