Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
The state of NLP in production 🥽
Search
Abdur-Rahmaan Janhangeer
August 27, 2023
Programming
0
66
The state of NLP in production 🥽
NLP in production vs real life
Abdur-Rahmaan Janhangeer
August 27, 2023
Tweet
Share
More Decks by Abdur-Rahmaan Janhangeer
See All by Abdur-Rahmaan Janhangeer
Extending Flask using the Flask Plugins API
osdotsystem
0
22
PEPs that hit the front page
osdotsystem
0
24
libSQL: Taking Sqlite To The Moon
osdotsystem
0
110
Boosting Python With Rust 🚀
osdotsystem
0
120
Flet: Flutter in Python
osdotsystem
0
220
SQLite Internals: How The World's Most Used Database Works
osdotsystem
2
3.5k
Fast Flask Dev For Big Codebases
osdotsystem
0
150
Python Bytecode or How Python Operates
osdotsystem
0
210
How To OpenSource
osdotsystem
0
120
Other Decks in Programming
See All in Programming
Product Management LT会_クアンド新家
shinshin
0
210
DDDを志して3年経ったら「DDDの皮を被ったクリーンアーキテクチャ」になった話【デブサミ2024夏】
texmeijin
1
620
Google's Recipe for Scaling (Web) Security – LocoMocoSec 2024
lweichselbaum
0
170
【Go言語】golangci-lintの使い方
tomo1227
0
270
I/O Extended Android in Korea 2024 ~ Whats new in Android development tools
pluu
0
250
コード生成を伴うLLMエージェント - 2024.07.18 Tokyo AI
smiyawaki0820
11
4.1k
企業向け生成AIアプリの 開発から得られた知見
takaakikakei
0
310
The rollercoaster of releasing an Android, iOS, and macOS app with Kotlin Multiplatform | droidcon Berlin
prof18
0
110
CSC307 Lecture 07
javiergs
PRO
0
220
Polarsの成長: v0.14からv1.0までの変遷と今後の展望
zerebom
1
350
Harnessing Large Language Models for Training-free Video Anomaly Detection
tereka114
1
1.3k
Microservices rules (July 2024) : what good looks like
cer
PRO
0
1.6k
Featured
See All Featured
5 minutes of I Can Smell Your CMS
philhawksworth
200
19k
Building Effective Engineering Teams - LeadDev
addyosmani
47
2.2k
Clear Off the Table
cherdarchuk
89
320k
What's new in Ruby 2.0
geeforr
338
31k
Design by the Numbers
sachag
277
18k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
26
2.1k
Designing with Data
zakiwarfel
96
5k
Scaling GitHub
holman
458
140k
Rebuilding a faster, lazier Slack
samanthasiow
78
8.5k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
277
13k
How To Stay Up To Date on Web Technology
chriscoyier
784
250k
Art, The Web, and Tiny UX
lynnandtonic
291
20k
Transcript
The state of NLP in production
None
Python Mauritius Usergroup site fb linkedin mailing list 3
url pymug.com site 4
About me compileralchemy.com 5
slides 6
The state of NLP in production 7
Hardest part of a real-world project 8
? 9
Is it cooking up an awesome model? 10
No, the world is more complex than this 11
Elements of an NLP project 12
NLP project gather data clean store train use model retrain
model 13
gather data 14
Toy project use curated data set quick extraction 15
Real project a lot of data needed data corresponds to
business case. data probably does not exist speed of data gathering find ingenious / better ways of getting data automate collection 16
clean/preprocess data 17
Toy project use an existing parser / curator e.g. NLTK
existing options 18
Real project use a parser intended for it, several custom
steps parallel processing of data 19
store data 20
Toy project laptop 21
Real project cloud database hot / cold data TTL 22
training 23
Toy project use laptop / external GPU 24
Real project on cloud training on cloud knowledge cross-cloud skills
fault tolerance 25
use model 26
Toy project local website / code 27
Real project continuation of pipeline web service architecture devops /
deploy 28
retraining 29
Toy project euhh this even exists???? 30
Real project learn cloud offerings for continuous learning ways to
retrain / fine tune 31
It's more than serving a model 32
Operation model 33
[ pipeline ] data collection --- process --- train -<-
| | --------------------------- model ^ | | | | --->--- V web service [pod] [pod] --- happy user | -> users service [pod] [pod] | -> db service [pod] 34
skills chart 35
skills --------------- --------------- | | | | | backend |
| devops | | | | | --------------- --------------- --------------- --------------- | | | | | backend | | data eng | | | | | --------------- --------------- 36
skills --------------- --------------- | | | | | backend |
| devops | | | | | --------------- --------------- web service deploy --------------- --------------- | | | | | ml | | data eng | | | | | --------------- --------------- models pipelining 37
code blueprint [ architecture repos ] [ pipeline repos ]
[ ml repos ] [ backend repos ] 38
Tools 39
Pandas Good queries Much resources Read SQL 40
Dask Good for it's purpose: Parallelize tasks Poor docs 41
Polars Awesome parallelizations Great docs 42
NLTK use spacy if possible 43
Notebooks great for cloud used in production on the cloud
44
Advice to research / scientists folks keep everything clean people
will come after you always in hurry / messy / i'll clean it later mood good practices? is this phrase in the korean dictionary? 45
General advices have great docs good onboarding have great standards
46
Keep learning! 47