Text Processing API

A fast API for sentiment analysis, lemmatization, POS tagging, chunking, and named entity recognition using FastAPI, spaCy, and TextBlob.

Setup

1. Install dependencies:

   pip install -r requirements.txt
   python -m textblob.download_corpora
   python -m spacy download en_core_web_sm

2. Run the API server:

   uvicorn main:app --reload

Endpoints

• POST /sentiment — Sentiment analysis
• POST /lemmatize — Lemmatization (stemming)
• POST /pos_chunk — POS tagging and chunking
• POST /phrase_ner — Phrase extraction and NER

Request body:

{
  "text": "Your text here."
}

Example: Language Detection

Request:

{
  "text": "Bonjour tout le monde!"
}

Response:

{
  "language": "fr"
}

Example: Tokenization

Request:

{
  "text": "Hello, world!"
}

Response:

{
  "tokens": ["Hello", ",", "world", "!"]
}