Skip to content

Sub-Issue 1: Connect IPCC Documents to the Ingestion Pipeline #34

Description

@aleenaharoldpeter

Description

IPCC HTML files have already been added to the repository under input/ipcc, but they are not currently processed by the chatbot backend.

This task focuses on ensuring that IPCC documents are discovered and included during document ingestion.

Tasks

  • Review the existing document ingestion workflow.
  • Identify where CABook documents are loaded and processed.
  • Extend the ingestion workflow to include files from input/ipcc.
  • Verify that IPCC documents are successfully detected and processed.
  • Add logging to confirm successful ingestion.

Acceptance Criteria

  • IPCC files are automatically discovered during ingestion.
  • No ingestion errors occur.
  • Logs confirm that IPCC documents are being processed.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions