Hacker News new | past | comments | ask | show | jobs | submit login
Show HN: Panza: A personal email assistant, trained and running on-device (github.com/ist-daslab)
49 points by eldar_ciki on May 2, 2024 | hide | past | favorite | 5 comments
Tired of crafting well-polished emails and wish you had an assistant to take over the hard work while mimicking your writing style? Introducing Panza, a personalized LLM email assistant that runs entirely on your device! Choose between Llama-3 or Mistral, tailor it to your unique style, and let it write the emails for you. Take a look at our demo and give it a try on your emails at: https://github.com/IST-DASLab/PanzaMail

Some technical details about Panza:

- Panza is an automated email assistant customized to your writing style and past email history.

- Panza produces a fine-tuned LLM that matches your writing style, pairing it with a Retrieval-Augmented Generation (RAG) component which helps it produce relevant emails.

- Panza *can be trained and run entirely locally*. Currently, it requires a single GPU with 16-24 GiB of memory, but we also plan to release a CPU-only version.

- Training and execution are also quick - for a dataset on the order of 1000 emails, training Panza takes well under an hour, and generating a new email takes a few seconds at most.




I've been waiting for something like this. I've got most of my emails, text messages and social media posts since 1997. One day I'm going to load it all up on something like this.


Same here. Looking forward to trying this out.


I will try this on my M2 with 24gb. Got all my email since the 1998.

Edit: oof spoke to soon. Need to spend some time with this to adapt it for the M2. Only linux+nvidia out of the box


you might want to open an issue in our git repo, and if there is interest we would be more than happy to add a solution for Apple silicon


This is so cool!




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: