docling-project / docling-project/docling

Why does VLM Pipeline Removes all the Enrichments From ConvertPipeline?

Open
#2,439 5 comments 0 reactions 0 assignees View on GitHub
question
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Question

I can see that `VlmPipeline` is setting `enrichment_pipe` to empty list. [here](https://github.com/docling-project/docling/blob/f7244a433378327576e3554d41d80928ee38e2a7/docling/pipeline/base_pipeline.py#L152).

As I can understand `VlmPipeline` is a subclass of [`ConvertPipeline`](https://github.com/docling-project/docling/blob/f7244a433378327576e3554d41d80928ee38e2a7/docling/pipeline/base_pipeline.py#L135C7-L135C22), so why does `VlmPipeline` resets the `enrichment_pipe` to `empty` when it was set with [`document classification` and `picture description`](https://github.com/docling-project/docling/blob/f7244a433378327576e3554d41d80928ee38e2a7/docling/pipeline/base_pipeline.py#L152) in [`ConvertPipeline`](https://github.com/docling-project/docling/blob/f7244a433378327576e3554d41d80928ee38e2a7/docling/pipeline/base_pipeline.py#L135C7-L135C22)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.