Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Schedule polling for new meetings #12

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Schedule polling for new meetings #12

wants to merge 4 commits into from

Conversation

jdungan
Copy link
Member

@jdungan jdungan commented Mar 17, 2025

clean up meeting data, add action to save meetings

Experimenting with github action to get new meetings and write summaries

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
@jdungan jdungan changed the title DRAFT: Schedule polling for new meetings Schedule polling for new meetings Mar 19, 2025
Copy link
Member

@groovecoder groovecoder left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It took quite a while to get used to this style of code.

It looks like the summaries are generated from the agenda PDF? I thought we should generate summaries from the transcripts instead? Or we could have an agenda summary AND a transcript summary.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

change (blocking): don't check the *.jsonl file into the repo or we'll have to git commit them into the repo to update them. They should be put into the storage destination like S3 or something.

SUMMARY_FILE = Path("data/summaries.jsonl")


async def load_meetings() -> List[Meeting]:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

question (blocking): why is this async?

)

# Generate the AI summary
ai_summary = await summarize_with_llama(summary)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggestion (non-blocking): If we're using aiohttp to do these concurrently, shouldn't we remove the await from this call? So the process can do all the summaries concurrently? Or am I forgetting how async http and concurrency works?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, a gather() does make sense here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants