harinisri2001

Issue with Heading Extraction

5

Hi, Currently, all headings, including subheadings and child headings, are marked with ##, making them indistinguishable from one another. There is no clear differentiation between parent and nested headings. Anyone...

Issue with reading downloading model

3

@dolfim-ibm I am downloading a model in the Dockerfile using the following command: RUN python -c "from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline; \ StandardPdfPipeline.download_models_hf(force=True, local_dir='/app/python/rag/resources/artifacts/')" The model is successfully downloaded to the...

@Nimrod007 @jverre Hi I would like to know the architecture of Opik. What is the purpose of all three databases in the stack? What is the purpose of MySQL, Redis,...

Extraction is not in markdown

5

I tried to extract the contents of pdf. But it is extracting as plain text, not as markdown. Am I missing any parameter? from markitdown import MarkItDown md = MarkItDown()...

Customizing dpi value for ocr

4

@dolfim-ibm How can I pass the customized dpi value for ocr?

Generic pdf annotators

1

Hi @davidmezzetti , I checked out your annotateai project, but it involves multiple LLM calls. So i started alternates which doesnt involves llm calls. Is it possible to achieve what...

Issue with inconsistent extraction in CPU vs GPU

1

@dolfim-ibm @PeterStaar-IBM @cau-git I am trying to extract tables in images with smoldocling. When I run the three page PDF in cpu it is extracting the first page properly but...