Unstructured-IO / Unstructured-IO/unstructured

bug/partition_pdf() with stategy = "fast" is not extracting any elements

Open
#4,260 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
HTML
Stars
15.5k
Forks
1.3k
Avg merge
4d 2h
Merged PRs (30d)
13

Description

/partition_pdf() with stategy = "fast" is not extracting any elements

To Reproduce
We are trying to use partition_pdf with strategy = "fast" using below code.
elements = partition_pdf(
filename=temp_file_path,
strategy="fast"

elements are always empty list.

Any help would be appreciated as its a priority for us.
PDF text is extractable. Is there any scenarios where strategy = 'fast' will fail. We have tried with PDF which does not have any images and also with PDF that contains contains text and images(almost 90% and images 10% ).
In both the cases its returning an empty list

Regards
Remya.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing partition_pdf(filename=temp_file_path, strategy="fast") with the text-only and mixed text/image PDFs described in the report, and inspect why the result is empty. Done means the fast strategy either returns the expected extracted elements for supported PDFs or clearly documents the scenarios in which it cannot do so.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.