Skip to content

Adding support for AI based document intelligence #7

Description

@sankalpsrv

Considering that after building with hard coded parsing there are still the following problems:

  1. Tables are not being read.
  2. Regex hard coded is not able to accurately parse the sections boundaries at all times.
  3. Some earlier enactments are not in the format we require from IndiaCode

We can explore the use of LLM's for the above, each of which is a sub-issue in and of itself.

Activity

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

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions