nlmatics/llmsherpa issues and pull requests

#107 - can we parse csv or excel file ?

Issue - State: open - Opened by pulkitmehtaworkmetacube about 2 months ago

#107 - can we parse csv or excel file ?

Issue - State: open - Opened by pulkitmehtaworkmetacube about 2 months ago

#106 - Multi-column sections extending to to multiple pages fails

Issue - State: open - Opened by dilshans2k 3 months ago

#106 - Multi-column sections extending to to multiple pages fails

Issue - State: open - Opened by dilshans2k 3 months ago

#105 - LLMSHERPA API LOCAL HOSTING

Issue - State: open - Opened by Enaouram 3 months ago - 2 comments

#105 - LLMSHERPA API LOCAL HOSTING

Issue - State: open - Opened by Enaouram 3 months ago - 2 comments

#104 - Issue while accessing llmsherpa api url

Issue - State: open - Opened by Sneha-2113 3 months ago - 1 comment

#104 - Issue while accessing llmsherpa api url

Issue - State: open - Opened by Sneha-2113 3 months ago - 1 comment

#103 - Mismatch between pypi and repo version

Issue - State: open - Opened by ogencoglu 3 months ago - 1 comment

#103 - Mismatch between pypi and repo version

Issue - State: open - Opened by ogencoglu 3 months ago - 1 comment

#102 - pdf_reader.read_pdf(pdf_url) cannot read local pdf path

Issue - State: open - Opened by Tizzzzy 3 months ago - 3 comments

#102 - pdf_reader.read_pdf(pdf_url) cannot read local pdf path

Issue - State: open - Opened by Tizzzzy 3 months ago - 3 comments

#101 - Suggestions for Improvements (compiled)

Issue - State: open - Opened by SBhat2615 3 months ago

#101 - Suggestions for Improvements (compiled)

Issue - State: open - Opened by SBhat2615 3 months ago

#100 - Issue with Example Code

Issue - State: open - Opened by nickjtay 4 months ago - 3 comments

#100 - Issue with Example Code

Issue - State: open - Opened by nickjtay 4 months ago - 3 comments

#99 - colSpan should be colspan in TableCell class to_html method

Issue - State: open - Opened by Cerebex 4 months ago

#99 - colSpan should be colspan in TableCell class to_html method

Issue - State: open - Opened by Cerebex 4 months ago

#98 - Class TableHeader to_html method does not use correct table tags

Issue - State: open - Opened by Cerebex 4 months ago

#98 - Class TableHeader to_html method does not use correct table tags

Issue - State: open - Opened by Cerebex 4 months ago

#97 - Server not responsive

Issue - State: open - Opened by pierreoberholzer 4 months ago - 4 comments

#97 - Server not responsive

Issue - State: open - Opened by pierreoberholzer 4 months ago - 4 comments

#96 - Custom headers for reading pdf files

Pull Request - State: open - Opened by CodMonk 4 months ago

#96 - Custom headers for reading pdf files

Pull Request - State: open - Opened by CodMonk 4 months ago

#95 - Added github workflow to run unittests when a PR is created

Pull Request - State: open - Opened by aaryan200 4 months ago - 1 comment

#95 - Added github workflow to run unittests when a PR is created

Pull Request - State: open - Opened by aaryan200 4 months ago - 1 comment

#94 - local files parsing fixed

Pull Request - State: open - Opened by juanls1 4 months ago - 2 comments

#94 - local files parsing fixed

Pull Request - State: open - Opened by juanls1 4 months ago - 1 comment

#93 - KeyError: 'style' while running on local using docker image

Issue - State: open - Opened by abhishekJadhav 4 months ago - 2 comments

#93 - KeyError: 'style' while running on local using docker image

Issue - State: open - Opened by abhishekJadhav 4 months ago - 2 comments

#92 - Local files parsing Error

Issue - State: closed - Opened by juanls1 4 months ago - 2 comments

#92 - Local files parsing Error

Issue - State: closed - Opened by juanls1 4 months ago - 2 comments

#91 - llmsherpa is Missing Information

Issue - State: open - Opened by hasandot 4 months ago

#91 - llmsherpa is Missing Information

Issue - State: open - Opened by hasandot 4 months ago

#90 - Incorrect child assignment for 'header' blocks in LayoutReader.read

Pull Request - State: closed - Opened by IoanaDragan 5 months ago - 6 comments

#90 - Incorrect child assignment for 'header' blocks in LayoutReader.read

Pull Request - State: closed - Opened by IoanaDragan 5 months ago - 6 comments

#88 - absolute path Issue in read_pdf method

Issue - State: open - Opened by Nishant-Bansal-777 5 months ago - 2 comments

#88 - absolute path Issue in read_pdf method

Issue - State: open - Opened by Nishant-Bansal-777 5 months ago - 2 comments

#87 - Does the llm give sentence wise bbox or title wise bbox

Issue - State: open - Opened by shivani-cognologix 5 months ago

#87 - Does the llm give sentence wise bbox or title wise bbox

Issue - State: open - Opened by shivani-cognologix 5 months ago

#86 - LayoutReader.read handling levels incorrectly

Issue - State: open - Opened by solvingproblemswithtechnology 6 months ago

#86 - LayoutReader.read handling levels incorrectly

Issue - State: open - Opened by solvingproblemswithtechnology 6 months ago

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

Issue - State: open - Opened by anirudh-gapblue 6 months ago - 2 comments

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

Issue - State: open - Opened by anirudh-gapblue 6 months ago - 2 comments

#83 - Fixes Issue #79. Fixed repetition of text in to_text and to_html methods of the Document class

Pull Request - State: closed - Opened by AaryanTR 6 months ago - 5 comments

#83 - Fixes Issue #79. Fixed repetition of text in to_text and to_html methods of the Document class

Pull Request - State: closed - Opened by AaryanTR 6 months ago - 5 comments

#80 - Certificate issues

Issue - State: open - Opened by jimmytidey 6 months ago - 4 comments

#80 - Certificate issues

Issue - State: open - Opened by jimmytidey 6 months ago - 4 comments

#79 - [BUG] Duplicated nodes in output from `to_html()` and `to_text()`

Issue - State: closed - Opened by jinkjonks 6 months ago - 3 comments

#79 - [BUG] Duplicated nodes in output from `to_html()` and `to_text()`

Issue - State: closed - Opened by jinkjonks 6 months ago - 3 comments

#78 - Two column PDFs

Issue - State: open - Opened by diego898 7 months ago - 2 comments

#78 - Two column PDFs

Issue - State: open - Opened by diego898 7 months ago - 2 comments

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

Issue - State: open - Opened by AIMads 7 months ago - 1 comment

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

Issue - State: open - Opened by AIMads 7 months ago - 1 comment

#76 - feature request: is Chinese Text/PDF parsing Supported ?

Issue - State: open - Opened by ZJLi2013 7 months ago

#76 - feature request: is Chinese Text/PDF parsing Supported ?

Issue - State: open - Opened by ZJLi2013 7 months ago

#75 - Handling Right to Left languages

Issue - State: open - Opened by wolfassi123 7 months ago - 1 comment

#75 - Handling Right to Left languages

Issue - State: open - Opened by wolfassi123 7 months ago - 1 comment

#74 - Add status check before parsing the json string

Pull Request - State: closed - Opened by oreh 7 months ago - 1 comment

#74 - Add status check before parsing the json string

Pull Request - State: closed - Opened by oreh 7 months ago - 1 comment

#73 - `to_text()` returns emtpy text when the document doesn't have sections

Issue - State: open - Opened by livelxw 7 months ago - 1 comment

#73 - `to_text()` returns emtpy text when the document doesn't have sections

Issue - State: open - Opened by livelxw 7 months ago - 1 comment

#72 - Update README

Pull Request - State: closed - Opened by sonalshad 7 months ago

#72 - Update README

Pull Request - State: closed - Opened by sonalshad 7 months ago

#71 - Missing lines

Issue - State: open - Opened by mshibashish 7 months ago

#71 - Missing lines

Issue - State: open - Opened by mshibashish 7 months ago

#70 - Mathe Formulas

Issue - State: open - Opened by nise 7 months ago

#70 - Mathe Formulas

Issue - State: open - Opened by nise 7 months ago

#69 - Ingestion Failed

Issue - State: open - Opened by dkarthicks27 7 months ago - 2 comments

#69 - Ingestion Failed

Issue - State: open - Opened by dkarthicks27 7 months ago - 2 comments

#68 - Golang version of llmsherpa

Issue - State: open - Opened by pashpashpash 7 months ago

#68 - Golang version of llmsherpa

Issue - State: open - Opened by pashpashpash 7 months ago

#67 - MaxRetryError HTTPSConnectionPool

Issue - State: open - Opened by Higgy-debug 7 months ago - 4 comments

#67 - MaxRetryError HTTPSConnectionPool

Issue - State: open - Opened by Higgy-debug 7 months ago - 4 comments

#64 - JSONDecodeError

Issue - State: open - Opened by chengyjonathan 8 months ago - 1 comment

#64 - JSONDecodeError

Issue - State: open - Opened by chengyjonathan 8 months ago - 1 comment

#63 - read_pdf fails on specific pdf locally, not through hosted api

Issue - State: open - Opened by Ianpwest 8 months ago - 5 comments

#63 - read_pdf fails on specific pdf locally, not through hosted api

Issue - State: open - Opened by Ianpwest 8 months ago - 5 comments

#62 - Fixed two LlamaIndex imports

Pull Request - State: closed - Opened by lebigot 8 months ago

#62 - Fixed two LlamaIndex imports

Pull Request - State: closed - Opened by lebigot 8 months ago

#61 - Langchain integration

Issue - State: open - Opened by zishanahmed08 8 months ago

#61 - Langchain integration

Issue - State: open - Opened by zishanahmed08 8 months ago

#60 - Bug in load_data when using full path

Issue - State: open - Opened by yoeldk 8 months ago - 2 comments

#60 - Bug in load_data when using full path

Issue - State: open - Opened by yoeldk 8 months ago - 2 comments

#59 - LayoutPDFReader._parse_pdf returns error when pdf contains empty pages

Issue - State: open - Opened by aleksvercau 8 months ago - 9 comments

#57 - Skips first few lines in PDF.

Issue - State: open - Opened by samgriek 9 months ago - 3 comments

#57 - Skips first few lines in PDF.

Issue - State: open - Opened by samgriek 9 months ago - 3 comments

#56 - Bug in API function: Repeated content in HTML when trying to convert PDF to HTML.

Issue - State: open - Opened by PrashantK-DS 9 months ago

GitHub / nlmatics/llmsherpa issues and pull requests