GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — Add Docling to Feast · Issue #5037 · feast-dev/feast

Add Docling to Feast #5037

New issue
Copy link
New issue
Copy link
Closed
Closed
Add Docling to Feast#5037
Copy link
Labels
kind/featureNew feature or requestNew feature or request

Description

@franciscojavierarceo
franciscojavierarceo
opened on Feb 10, 2025
Issue body actions

Is your feature request related to a problem? Please describe.
Feast should support a docling extra to allow easy usage of docling in the Feature Server so that a user can run docling as a transformation.

Describe the solution you'd like
An ODFV on write can use docling to chunk the data.

Describe alternatives you've considered
N/A

Additional context
N/A

Activity

  1. franciscojavierarceo
    added
    kind/featureNew feature or requestNew feature or request
    on Feb 10, 2025
  2. franciscojavierarceo
    added a parent issue on Feb 10, 2025
    • Introduce Feast NLP/LLM Add-On #4964
  3. franciscojavierarceo commented on Feb 21, 2025

    @franciscojavierarceo
    franciscojavierarceo
    on Feb 21, 2025
    MemberAuthor
    More actions

    @ntkathole this would be a good one to add as an extra Nikhil if you have bandwidth.

    Reacted by Nikhil Kathole
  4. ntkathole commented on Feb 24, 2025

    @ntkathole
    ntkathole
    on Feb 24, 2025
    Member
    More actions

    @ntkathole this would be a good one to add as an extra Nikhil if you have bandwidth.

    @franciscojavierarceo Just trying to understand the scope here, You mean "add as an extra" as a natively support document chunking or NLP transformations OR simply adding dependency and continue the efforts from #5065 ?

    Reacted by Francisco Javier Arceo
  5. franciscojavierarceo commented on Feb 24, 2025

    @franciscojavierarceo
    franciscojavierarceo
    on Feb 24, 2025
    MemberAuthor
    More actions

    I think you can take that one over, the bandwidth is really the challenge that we have to get the CICD to work with pytorch. I started looking into it but it looks like it's going to take a bit and I have to prioritize some other items. :/

    Reacted by Nikhil Kathole
  6. ntkathole commented on Feb 25, 2025

    @ntkathole
    ntkathole
    on Feb 25, 2025
    Member
    More actions

    We need to update uv version to fix dependencies. Old version of uv is no longer providing correct dependency resolution for us. Raised #5086 to fix existing dependencies, once merged will add docling and torch.

  7. franciscojavierarceo
    closed this as completedon Mar 4, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    kind/featureNew feature or requestNew feature or request

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      You are visitor 01402503 — GeezerVison does not store the pages you look up.
      Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.