Home

Nlphose enables creation of complex NLP pipelines in seconds using a set of simple command line tools. You can 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. It works on static files or as well as stream of text.

Introduction

Installing

QuickStart

Using GUI Pipeline Builder

Architecture

Sources

• Kafka Source
• File Source
• Twitter Source

Processors

• Sentiment Analysis (AFINN)
• NER (Spacy)
• Language Identification (FastText)
• Chunking (NLTK)
• Sentiment Analysis (Transformers)
• Question Answering (Transformers)
• Zero shot Classification (Transformers)
• Filtering and Transforming JSON streams (jq)

Sinks

• Kafka Sink
• File Sink
• WebSocket Sink
• Writing Custom Sinks

Handling BigData

• Scaling Nlphose pipelines using Kafka and Kubernetes
• Executing Nlphose pipelines in PySpark

Stopping the Pipeline

Monitoring Performance