docling-project / docling-project/docling
Why does VLM Pipeline Removes all the Enrichments From ConvertPipeline?
- 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
Assessment
This issue has not been assessed yet.