Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Integrate Docling library into Langflow #5802

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

vishwamartur
Copy link

Related to #5665

Integrate the Docling library into the Langflow project to enhance document parsing and exporting capabilities.

  • Backend Changes:

    • Add import statement for Docling library in src/backend/base/langflow/components/unstructured/unstructured.py.
    • Add a new input for Docling configuration in src/backend/base/langflow/components/unstructured/unstructured.py.
    • Update the process_files method to use Docling for document parsing in src/backend/base/langflow/components/unstructured/unstructured.py.
    • Create a new component for Docling document loader in src/backend/base/langflow/components/documentloaders/docling_loader.py.
  • Documentation Updates:

    • Add a new section for Docling workflows in docs/docs/Components/components-processing.md.
    • Include examples of document conversion and AI integration using Docling in docs/docs/Components/components-processing.md.
    • Add a new section for Docling-related tools in docs/docs/Components/components-tools.md.
    • Include examples of using Docling tools in Langflow in docs/docs/Components/components-tools.md.
    • Add a mention of Docling integration in the overview in docs/docs/Concepts/concepts-overview.md.
    • Highlight the benefits of using Docling in Langflow in docs/docs/Concepts/concepts-overview.md.

Related to langflow-ai#5665

Integrate the Docling library into the Langflow project to enhance document parsing and exporting capabilities.

* **Backend Changes:**
  - Add import statement for Docling library in `src/backend/base/langflow/components/unstructured/unstructured.py`.
  - Add a new input for Docling configuration in `src/backend/base/langflow/components/unstructured/unstructured.py`.
  - Update the `process_files` method to use Docling for document parsing in `src/backend/base/langflow/components/unstructured/unstructured.py`.
  - Create a new component for Docling document loader in `src/backend/base/langflow/components/documentloaders/docling_loader.py`.

* **Documentation Updates:**
  - Add a new section for Docling workflows in `docs/docs/Components/components-processing.md`.
  - Include examples of document conversion and AI integration using Docling in `docs/docs/Components/components-processing.md`.
  - Add a new section for Docling-related tools in `docs/docs/Components/components-tools.md`.
  - Include examples of using Docling tools in Langflow in `docs/docs/Components/components-tools.md`.
  - Add a mention of Docling integration in the overview in `docs/docs/Concepts/concepts-overview.md`.
  - Highlight the benefits of using Docling in Langflow in `docs/docs/Concepts/concepts-overview.md`.
@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. documentation Improvements or additions to documentation labels Jan 20, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant