Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/code2k13/nlphose

Enables creation of complex NLP pipelines in seconds, for processing static files or streaming text, using a set of simple command line tools. Perform multiple operation on text like NER, Sentiment Analysis, Chunking, Language Identification, Q&A, 0-shot Classification and more by executing a single command in the terminal. Can be used as a low code or no code Natural Language Processing solution. Also works with Kubernetes and PySpark !
https://github.com/code2k13/nlphose

ai artifical-intelligense data-science language-detection low-code machine-learning named-entity-recognition natural-language-processing nlp no-code sentiment-analysis text-mining twitter-sentiment-analysis

Last synced: about 1 month ago
JSON representation

Enables creation of complex NLP pipelines in seconds, for processing static files or streaming text, using a set of simple command line tools. Perform multiple operation on text like NER, Sentiment Analysis, Chunking, Language Identification, Q&A, 0-shot Classification and more by executing a single command in the terminal. Can be used as a low code or no code Natural Language Processing solution. Also works with Kubernetes and PySpark !

Awesome Lists containing this project

README

        

![nlphose](logo.png)
Nlphose is a set of command-line tools that enables creation of complex NLP pipelines within seconds.
It currently supports following operation on static files and streaming data:

* Sentiment Analysis (AFINN)
* NER (Spacy)
* Language Identification (FastText)
* Chunking (NLTK)
* Sentiment Analysis (Transformers)
* Question Answering (Transformers)
* Zero shot Classification (Transformers)

๐Ÿ‘‡๐ŸปBelow is a sample pipeline that streams in ๐Ÿ—จ๏ธ tweets containing the term โ›ˆ๏ธ'rainfall' and tries to guess the ๐Ÿ™๏ธ place it rained using extractive question answering.

```shell
twint -s 'rainfall' |\
./twint2json.py |\
./xformer.py --pipeline question-answering --param 'where did it rain' |\
jq '{"text":.text,"answer":.xfrmr_question_answering.answer}'
```
Nlphose pipelines can run on your laptop or on a cluster of computers using [Kubernetes](https://ashishware.com/2021/12/12/scalablenlp/) or [Pyspark](https://ashishware.com/2022/01/23/PysparkNlphose/).

## ๐Ÿ˜ฒ๐Ÿ˜ฒ๐Ÿ˜ฒ Looks interesting ??

Checkout the ๐Ÿ”—[installation guide ](https://github.com/code2k13/nlphose/wiki/Installing) and ๐Ÿ”Ž[some usage examples](https://github.com/code2k13/nlphose/wiki/Quickstart). Please refer to the wiki for ๐Ÿ“–[detailed documentation](https://github.com/code2k13/nlphose/wiki)

## GUI Pipeline Builder (WIP)
I am also working on a GUI Pipeline buider tool which allows users to create a pipeline by simply drag-and-drop

![](https://github.com/code2k13/nlphoseGUI/blob/main/images/drag_drop_nlphose.gif?raw=true)

For more details visit it's repository : [https://github.com/code2k13/nlphoseGUI](https://github.com/code2k13/nlphoseGUI)