Apache OpenNLP · Capability
Apache OpenNLP NLP Pipeline Workflow
End-to-end NLP processing workflow combining language detection, sentence detection, tokenization, POS tagging, NER, chunking, and parsing for comprehensive text analysis.
What You Can Do
POST
Detect language
— Detect document language
/v1/language
POST
Detect sentences
— Split text into sentences
/v1/sentences
POST
Tokenize
— Tokenize text
/v1/tokens
POST
Find entities
— Find named entities
/v1/entities
POST
Tag pos
— Tag parts of speech
/v1/pos
POST
Chunk
— Chunk text into phrases
/v1/chunks
POST
Parse
— Parse sentence structure
/v1/parse
POST
Categorize
— Categorize document
/v1/categories
GET
List models
— List available models
/v1/models
MCP Tools
detect-language
Detect the language of input text
read-only
detect-sentences
Split text into individual sentences
read-only
tokenize
Tokenize text into words and punctuation
read-only
find-named-entities
Find named entities (persons, locations, organizations) in text
read-only
tag-parts-of-speech
Assign POS tags to each token in tokenized text
read-only
lemmatize
Reduce tokens to their base/lemma forms
read-only
chunk-phrases
Identify noun phrases, verb phrases, and other chunks
read-only
parse-sentence
Build a full parse tree for a sentence
read-only
categorize-document
Classify a document into predefined categories
read-only
list-models
List all available NLP models
read-only
APIs Used
opennlp