Skip to content

The fragmentation issue when extracting documents containing HTML tables #308

Description

@anranshens

When using langextract to extract the information contained in documents with HTML tables,suppose the content of my table is very long, will the chunking logic cut the table, causing the subsequent chunks to lack the table header and preventing the LLM from understanding, ultimately resulting in the loss of the extracted result data? is there a better solution to this problem?

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