nlmatics/llmsherpa

Issues

• [BUG] Duplicated nodes in output from `to_html()` and `to_text()`

  #79 opened 7 months ago by jinkjonks
  4

• absolute path Issue in read_pdf method

  #88 opened 7 months ago by Nishant-Bansal-777
  2

• can we parse csv or excel file ?

  #107 opened 4 months ago by pulkitmehtaworkmetacube
  0

• pdf_reader.read_pdf(pdf_url) cannot read local pdf path

  #102 opened 5 months ago by Tizzzzy
  3

• Mismatch between pypi and repo version

  #103 opened 5 months ago by ogencoglu
  1

• LLMSHERPA API LOCAL HOSTING

  #105 opened 5 months ago by Enaouram
  2

• Local files parsing Error

  #92 opened 5 months ago by juanls1
  2

• Issue while accessing llmsherpa api url

  #104 opened 5 months ago by Sneha-2113
  1

• Multi-column sections extending to to multiple pages fails

  #106 opened 5 months ago by dilshans2k
  0

• Issue with Example Code

  #100 opened 5 months ago by nickjtay
  3

• Suggestions for Improvements (compiled)

  #101 opened 5 months ago by SBhat2615
  0

• colSpan should be colspan in TableCell class to_html method

  #99 opened 5 months ago by Cerebex
  0

• Class TableHeader to_html method does not use correct table tags

  #98 opened 5 months ago by Cerebex
  0

• Certificate issues

  #80 opened 8 months ago by jimmytidey
  4

• Bug in load_data when using full path

  #60 opened 10 months ago by yoeldk
  2

• read_pdf fails on specific pdf locally, not through hosted api

  #63 opened 9 months ago by Ianpwest
  5

• LayoutPDFReader._parse_pdf returns error when pdf contains empty pages

  #59 opened 10 months ago by aleksvercau
  9

• Server not responsive

  #97 opened 6 months ago by pierreoberholzer
  4

• JSONDecodeError

  #64 opened 9 months ago by chengyjonathan
  1

• KeyError: 'style' while running on local using docker image

  #93 opened 6 months ago by abhishekJadhav
  2

• MaxRetryError HTTPSConnectionPool

  #67 opened 9 months ago by Higgy-debug
  4

• Ingestion Failed

  #69 opened 9 months ago by dkarthicks27
  2

• Receiving 'urllib3.exceptions.LocationValueError: No host specified.' even though I have a local server up and running

  #84 opened 8 months ago by anirudh-gapblue
  2

• llmsherpa is Missing Information

  #91 opened 6 months ago by hasandot
  0

• Handling Right to Left languages

  #75 opened 9 months ago by wolfassi123
  1

• Two column PDFs

  #78 opened 8 months ago by diego898
  2

• Does the llm give sentence wise bbox or title wise bbox

  #87 opened 7 months ago by shivani-cognologix
  0

• LayoutReader.read handling levels incorrectly

  #86 opened 8 months ago by solvingproblemswithtechnology
  0

• Failed to establish a new connection: [Errno 111] Connection refused'))

  #51 opened a year ago by promaprogga
  1

• Bug in API function: Incorrect behavior with repeated sections.

  #49 opened a year ago by gshreya5
  8

• Parse nodes on a para-point level

  #55 opened a year ago by irash03
  1

• Is it possible to run this fully local, so sensitive PII PDFs dont leave the network?

  #77 opened 9 months ago by AIMads
  1

• `to_text()` returns emtpy text when the document doesn't have sections

  #73 opened 9 months ago by livelxw
  1

• feature request: is Chinese Text/PDF parsing Supported ?

  #76 opened 9 months ago by ZJLi2013
  0

• [Question]: what is block_class parameter in block json representation?

  #54 opened a year ago by jjubric
  1

• Connection Error

  #46 opened a year ago by JackOfAllSkills
  3

• Missing lines

  #71 opened 9 months ago by mshibashish
  0

• Mathe Formulas

  #70 opened 9 months ago by nise
  0

• Golang version of llmsherpa

  #68 opened 9 months ago by pashpashpash
  0

• Skips first few lines in PDF.

  #57 opened a year ago by samgriek
  3

• KeyError: result

  #45 opened a year ago by PranavGupta98
  3

• Ingest failed

  #53 opened a year ago by mrenlivex
  2

• Langchain integration

  #61 opened 10 months ago by zishanahmed08
  0

• Bug in API function: Repeated content in HTML when trying to convert PDF to HTML.

  #56 opened a year ago by PrashantK-DS
  0

• Feature Request - Splitting Bounding Boxes Across Pages

  #52 opened a year ago by amn-max
  1

• Nodes and llama idnex

  #50 opened a year ago by drewskidang
  1

• Get repeated headers and footers

  #48 opened a year ago by simon-cerda
  1

• Add async API

  #44 opened a year ago by ianschmitz
  0

• PDF size limit - apologies if I caused problems

  #43 opened a year ago by WindyOrgUK
  0

• InternalServerError: Error code: 503

  #42 opened a year ago by Fly-betterme
  0