Skip to content

Feature: Google Drive - Presentation to Markdown / Audio|Video Transcribed (10MB Limit)#3075

Closed
that-dom wants to merge 34 commits intoelastic:mainfrom
that-dom:that-dom-google-drive-custom
Closed

Feature: Google Drive - Presentation to Markdown / Audio|Video Transcribed (10MB Limit)#3075
that-dom wants to merge 34 commits intoelastic:mainfrom
that-dom:that-dom-google-drive-custom

Conversation

@that-dom
Copy link
Copy Markdown

@that-dom that-dom commented Jan 6, 2025

Closes #3073 & #3074

In the Google Drive source this adds the functionality to convert Presentation to Markdown using Azure's OpenAI models and using Whisper service to transcribe audio or video to text with the limit of 10MB.

Checklists

Pre-Review Checklist

  • this PR does NOT contain credentials of any kind, such as API keys or username/passwords (double check config.yml.example)
  • this PR has a meaningful title
  • this PR links to all relevant github issues that it fixes or partially addresses
  • if there is no GH issue, please create it. Each PR should have a link to an issue
  • this PR has a thorough description
  • Covered the changes with automated tests
  • Tested the changes locally
  • Added a label for each target release version (example: v7.13.2, v7.14.0, v8.0.0)
  • Considered corresponding documentation changes
  • Contributed any configuration settings changes to the configuration reference
  • if you added or changed Rich Configurable Fields for a Native Connector, you made a corresponding PR in Kibana

Changes Requiring Extra Attention

  • Security-related changes (encryption, TLS, SSRF, etc)
  • New external service dependencies added.

This adds external services for Azure hosted OpenAI GPT4-mini and Whisper API's

Related Pull Requests

Release Note

github-actions Bot and others added 30 commits July 9, 2024 09:58
…e id and adding support for views (elastic#2681) (elastic#2688)

Co-authored-by: parthpuri-elastic <150776158+parthpuri-elastic@users.noreply.github.com>
…tic#2699) (elastic#2700)

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
elastic#2713)

Co-authored-by: Liam Thompson <32779855+leemthompo@users.noreply.github.com>
…elastic#2715)

Co-authored-by: Artem Shelkovnikov <artem.shelkovnikov@elastic.co>
…tic#2721) (elastic#2724)

Co-authored-by: elastic-renovate-prod[bot] <174716857+elastic-renovate-prod[bot]@users.noreply.github.com>
Co-authored-by: Giannicola Olivadoti <giannicola.olivadoti@elastic.co>
Co-authored-by: Artem Shelkovnikov <artem.shelkovnikov@elastic.co>
Co-authored-by: Artem Shelkovnikov <artem.shelkovnikov@elastic.co>
…lastic#2737)

Co-authored-by: parthpuri-elastic <150776158+parthpuri-elastic@users.noreply.github.com>
Co-authored-by: Sean Story <sean.j.story@gmail.com>
)

Co-authored-by: Artem Shelkovnikov <artem.shelkovnikov@elastic.co>
…elastic#2881) (elastic#2900)

Co-authored-by: Artem Shelkovnikov <artem.shelkovnikov@elastic.co>
…) (elastic#2973)

Co-authored-by: Sean Story <sean.j.story@gmail.com>
Co-authored-by: Artem Shelkovnikov <artem.shelkovnikov@elastic.co>
Added the ability to send presentations to azure openai gpt-4o-mini for conversation to markdown
Added the ability for audio/video files under 25MB to be sent to azure open whisper model for output to text.
Copy link
Copy Markdown
Member

@seanstory seanstory left a comment

Choose a reason for hiding this comment

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

Looks like you may need to rebase and force-push - you're pulling in a lot of diff that is not yours.

Also, it looks like you're tightly coupling the Google Drive connector to an Azure AI tool. Which doesn't make a lot of sense to me.

I don't see this being mergable. If you'd like to have a chat with the team in #connectors-feedback, we can discuss how we can work to better integrate with LLM tools, but this diff as I understand it does not align with our vision for the architecture.

Copy link
Copy Markdown
Member

@artem-shelkovnikov artem-shelkovnikov left a comment

Choose a reason for hiding this comment

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

+1 to Sean's points.

If we want similar functionallity, specific connectors are not the place to do it. Should be either supported framework-wise, or on later stages such as ingest pipelines.

@that-dom
Copy link
Copy Markdown
Author

that-dom commented Jan 8, 2025

Thanks for the review, and I agree with all points. I am glad to see that this is kicking a more considerable discussion because markdown and text are the future for any GenAI use cases. 😄

@that-dom that-dom closed this Jan 8, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Google Drive - Presentation to Markdown

10 participants