Collection of this group's data for a LLM-powered weekly report #351

Open
opened 2026-09-15 15:30:06 +00:00 by abompard · 8 comments

Hi folks,

I'm generating a weekly report of activity in the Fedora project centered on teams and SIGs, it's called This Week in Fedora. This generation uses an LLM. The goal is to make it easier to catch up with everything that's going on in the project, and to give visibility to each group's work and requests for help or testing. I think that from a newcomer's point of view, having an insight on what a group is working on at a point in time is helpful to decide whether it's interesting and worth contributing to.
I can collect activity from:

  • the fedora-join mailing-list
  • discourse posts with the #join-sig tag
  • this tracker
  • meetings in Matrix meeting channels if you have any (but it doesn't look like you do)
  • messages in the #join channel in Matrix

I currently don't collect any of this, but I would like to know whether this group is OK with my program collecting and submitting info to an LLM from the following sources:

  1. mailing-lists, discourse posts and meetings (if any)
  2. this tracker
  3. the matrix channel

Right now the Matrix channel seems to be mostly ticket notifications, but if you sometimes do work there, I think it could be a valuable source for the report.
That said, I recognize that the form of the tool influences its use, chat messages are usually less thought-through than emails or forum posts, and members could be indimidated that something they write there and regret end up in a visible summary (the program respects message edits, but anyway).
Since my goal is to foster participation, the one thing I don't want to do is to hinder it in another way.

Please decide which collected sources, if any, you are OK with (and if you work in other places that you would like to have collected, of course (I can do RSS feeds!)). If the group is OK with Matrix channel collection but some individuals aren't, I can also exclude certain Matrix usernames from collection throughout the Matrix channels that are not meetings.

I'm happy to answer questions if you have any. Thanks!

Hi folks, I'm generating a weekly report of activity in the Fedora project centered on teams and SIGs, it's called [This Week in Fedora](https://abompard.fedorapeople.org/twif/). This generation uses an LLM. The goal is to make it easier to catch up with everything that's going on in the project, and to give visibility to each group's work and requests for help or testing. I think that from a newcomer's point of view, having an insight on what a group is working on at a point in time is helpful to decide whether it's interesting and worth contributing to. I can collect activity from: - the `fedora-join` mailing-list - discourse posts with the `#join-sig` tag - this tracker - meetings in Matrix meeting channels if you have any (but it doesn't look like you do) - messages in the `#join` channel in Matrix I currently don't collect any of this, but I would like to know whether this group is OK with my program collecting and submitting info to an LLM from the following sources: 1. mailing-lists, discourse posts and meetings (if any) 2. this tracker 3. the matrix channel Right now the Matrix channel seems to be mostly ticket notifications, but if you sometimes do work there, I think it could be a valuable source for the report. That said, I recognize that the form of the tool influences its use, chat messages are usually less thought-through than emails or forum posts, and members could be indimidated that something they write there and regret end up in a visible summary (the program respects message edits, but anyway). Since my goal is to foster participation, the one thing I don't want to do is to hinder it in another way. Please decide which collected sources, if any, you are OK with (and if you work in other places that you would like to have collected, of course (I can do RSS feeds!)). If the group is OK with Matrix channel collection but some individuals aren't, I can also exclude certain Matrix usernames from collection throughout the Matrix channels that are not meetings. I'm happy to answer questions if you have any. Thanks!
Owner

+1 from me. As far as I'm concerned, all the data is already public information, so please free to use it to generate summaries to help us all keep up with everything that goes on in Fedora.

+1 from me. As far as I'm concerned, all the data is already public information, so please free to use it to generate summaries to help us all keep up with everything that goes on in Fedora.
Owner

@join/Members : please comment here folks, (does that send notifications to the whole team? I'm still unsure of whether people get notifications from tickets on forge..)

@join/Members : please comment here folks, (does that send notifications to the whole team? I'm still unsure of whether people get notifications from tickets on forge..)
Owner

I dont think we need this, we have a lot of introductions and unofficial chats on the Matrix.

I cant see who would benefit, and it would dissuade people like me from being friendly and saying things not relevant to direct fedora issues - but making friends is super important to new joiners...
So I am a big -1

I dont think we need this, we have a lot of introductions and unofficial chats on the Matrix. I cant see who would benefit, and it would dissuade people like me from being friendly and saying things not relevant to direct fedora issues - but making friends is super important to new joiners... So I am a big -1
Member

-1 from me based on the above
(Also this does send emails and thus notifications to members of the join team, unsure if the owners get the email too)

-1 from me based on the above (Also this does send emails and thus notifications to members of the join team, unsure if the owners get the email too)
Author

I've noted that you don't want the Matrix channel summarized, thanks for the reply. Are you OK with the other sources being summarized?

I've noted that you don't want the Matrix channel summarized, thanks for the reply. Are you OK with the other sources being summarized?
Owner

I think that summarising the issue tracker is okay.

I mean, I'm personally against it, someone could simply come here and read it, but if Red Hat is paying you to do it I won't block it.

But note that I won't review it for accuracy.

I think that summarising the issue tracker is okay. I mean, I'm personally against it, someone could simply come here and read it, but if Red Hat is paying you to do it I won't block it. But note that I won't review it for accuracy.
Owner

It's more about having all the info in one place because it's a nightmare to keep up with all the channels/forges/lists/tags/categories/platforms that we're spread out on 😓. We've tried to do that for ages and failed (there was a grand "hubs" idea at one point which got shelved, for example). So while correctness cannot be guaranteed in the summaries, the way it's being done with enough links etc. to send people to the authoritative information source is sort of the "next best thing".

TLDR: i'm trying to follow "Don't let the perfect be the enemy of the good" in this case.


So yeh, i think we're saying: OK with everything apart from the matrix channel.

It's more about having all the info in one place because it's a nightmare to keep up with all the channels/forges/lists/tags/categories/platforms that we're spread out on 😓. We've tried to do that for ages and failed (there was a grand "[hubs](https://forge.fedoraproject.org/apps/fedora-hubs)" idea at one point which got shelved, for example). So while correctness cannot be guaranteed in the summaries, the way it's being done with enough links etc. to send people to the authoritative information source is sort of the "next best thing". TLDR: i'm trying to follow "Don't let the perfect be the enemy of the good" in this case. ---- So yeh, i think we're saying: OK with everything apart from the matrix channel.
Member

I'm +1 on the same conditions @ankursinha wrote.

I'm +1 on the same conditions @ankursinha wrote.
Sign in to join this conversation.
No milestone
No project
No assignees
5 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
join/Fedora-Join#351
No description provided.