From: <principle>
  To  : Robert Escriva <rescrv@rave>
  Date: Wed, 16 Oct 2024 13:24:33 +0000

Re: Introduction to maildir.ai

On Wed, 16 Oct 2024 06:23:55 -0700, Robert Escriva <rescrv@rave> wrote:
> On Wed, Oct 16, 2024 at 01:13:01PM +0000, principle wrote:
> > Hi Robert,
> > 
> > Thanks for introducing me to maildir.ai, a tool that connects large
> > language models via an email interface. 
> > 
> > I'm intrigued by the concept and would like to learn more about it.
> > Can you tell me more about the components involved in this system?
> > Specifically, I'd love to know more about the language model being
> > used by maildir_ai.
> > 
> > Is there a particular model or framework that's integrated into
> > maildir_ai, such as Hugging Face Transformers or Stanford CoreNLP?
> > 
> > Also, I noticed that you mentioned using ollama running in the
> > background. Is ollama related to maildir_ai, and if so, how does it
> > interact with the system?
> 
> Hi Link,
> 
> I'm glad you're interested in maildir-ai!  The system has three
> components:  An email client configured to work with maildir-ai, the
> maildir-ai maintenance daemon, and ollama.  I chose ollama because it's
> free and open, but there's nothing fundamental about it.  You could
> easily replace ollama with any other language model that can be accessed
> via a Rust async function call.
> 
> The workflow for maildir-ai is as follows:
> 
> 1.  You compose an email in mutt and when you send it, it gets saved to
>     Sent.  No actual email leaves your system.
> 2.  The maildir-ai maintenance daemon watches Sent for new messages.
>     When it sees a new message, it sends the message to ollama and saves
>     the response in INBOX.  Similarly, no actual email leaves your
>     system.
> 
> Happy Hacking,
> Robert
> 

Hi Robert,

Thank you for providing more information about the components involved in maildir.ai. I have a few follow-up questions to clarify how these components work together.

Can you elaborate on how the language model is being used by maildir.ai? You mentioned that ollama is running in the background, but how does it interact with the system when an email is sent through maildir-ai?

Is there any notion of model updating or regeneration happening within the maildir.ai system? If so, how does this process occur without disrupting the normal flow of emails being processed by maildir.ai?

Additionally, what kind of data is being passed to ollama for processing when an email is sent through maildir.ai? Is it a complete copy of the original email or some subset of its content that's relevant for the model's response?

Looking forward to your answers!

Best regards,
Link