nlmatics nlm-ingestor issues

nlmatics / nlm-ingestor

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

https://www.nlmatics.com

Apache License 2.0

912 stars 111 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

llm sherpa deployed in eks cluster with 4vcpu and 16gb ram not working properly

#74 gireesh99 opened 2 days ago
1
Update version in setup.py, and enable unpinning version of pandas.

#73 michaelfeil opened 2 weeks ago
0
KeyError: 'style'

#72 RaphSte opened 3 weeks ago
13
Update docker-publish.yml

#71 ansukla closed 3 weeks ago
0
Update to nlm 2.9.2 v2

#70 jamesvillarrubia opened 3 weeks ago
1
Docker expose port needs to be corrected

#69 kjoth opened 3 weeks ago
0
Updates tika jar to 2.9.2

#68 jamesvillarrubia closed 3 weeks ago
2
Connection error with Docker run

#67 kjoth opened 3 weeks ago
0
BBOX information

#66 TheMrguiller opened 1 month ago
0
Latest docker image not working locally

#65 mvennela opened 1 month ago
1
Download encodings during build to run Docker image offline

#64 mgl closed 3 weeks ago
0
Missing Tests?

#63 ramarnat opened 1 month ago
0
Add the default config file for tika

#62 kiran-nlmatics closed 1 month ago
0
Receiving an error 'urllib3.exceptions.LocationValueError: No host specified.'

#61 anirudh-gapblue opened 1 month ago
0
Expose port

#60 jinkjonks closed 3 weeks ago
0
Health checks fail because port 5001 not exposed by default

#59 jinkjonks closed 3 weeks ago
0
How to deploy this thing in production building image with the docker file giving error.

#58 aman-vink closed 2 months ago
1
Is it possible to run this fully local, so sensitive PII PDFs dont leave the network?

#57 AIMads opened 2 months ago
1
For anyone hoping to deploy this as a lambda

#56 dgonier opened 2 months ago
1
Lost pages

#55 sailxjx opened 2 months ago
0
Correct the BBOX for table blocks

#54 kiran-nlmatics closed 2 months ago
0
fix: bbox error in block renderer

#53 livelxw closed 2 months ago
0
bbox error in BlockRender

#52 livelxw closed 2 months ago
2
Trivially small chunks returned

#51 thelazydogsback opened 2 months ago
0
&applyOcr=yes - no OCR taking place (skipping image pages)

#50 thelazydogsback opened 2 months ago
3
docker image is not producing any result

#49 craldaz opened 2 months ago
1
Bug

#48 aman-vink opened 2 months ago
4
Update __main__.py

#47 moveyor closed 2 months ago
0
Dependency versions too strict

#46 choyuansu opened 2 months ago
0
Issue with finding tables and sections

#45 Aviral-tech opened 3 months ago
0
Error when parsing a PDF

#44 kaulshashank opened 3 months ago
2
Fix table left KeyError

#43 jinhy-sequoiacap closed 3 months ago
1
Question: Is it possible to retrieve the pdf position (bbox) for table rows

#42 janwbouma opened 3 months ago
0
box_style not being taken into account

#41 mikecook69 opened 3 months ago
2
made changes to integrate with indexer

#40 ansukla closed 3 months ago
0
nlm-ingestor is SUPER SLOW

#39 pashpashpash opened 3 months ago
4
Disable rules/paranthesized header

#38 mikecook69 opened 3 months ago
0
Suggestions for Fast Production Server

#37 yashpatel21 opened 3 months ago
5
[PDF Ingestor] make sure key idx within the range of sorted freq keys

#36 baobo5625 closed 3 months ago
0
Can you provide guidance on when page_idx wouldn't be available?

#35 chrismaresca opened 3 months ago
0
Unable to finish setup of nlm-ingestor due to missing distutils module

#34 lukenas opened 3 months ago
0
Encoding error with non-ASCII character.

#33 jamesvillarrubia opened 3 months ago
2
PDF extraction

#32 Amy-raj opened 3 months ago
1
Docker file available for hosting into lambda as container?

#31 akayalEC opened 4 months ago
0
Not able to install nlm_ingestor

#30 sli701 opened 4 months ago
3
memory leaks

#29 ZengJin123 closed 2 months ago
1
.pages files are chunked correctly but page_idx is always 0

#28 pashpashpash opened 4 months ago
0
.pptx files are correctly chunks, but page_idx is always 0

#27 pashpashpash opened 4 months ago
0
.doc files are correctly chunked, but page_idx is always 0

#26 pashpashpash opened 4 months ago
0
HTLM AND XML INGESTOR

#25 drewskidang opened 4 months ago
1