Skip to content

Extracting BibTeX from textual PDF ? #913

@Snikch63200

Description

@Snikch63200

Hi,

Is there a way (simple tool) to extract BibTeX informations from a pdf document using a llm and embedding model.

I know my question isn't 'directly' related to paperQA but I saw PaperQA seems doing it very well in indexing process (with Llama3+graphite3) and I wonder how to do it independantly.

I tried to reproduce this process with Open-WebUI but answers are very random (sometime excellent, sometime awful) with same prompt and parameters...

Best regards.

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions