Skip to content

Ahmetemintek/ner_with_fastapi

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Named Entity Recognition with FastAPI

This project implements a Named Entity Recognition (NER) over an example text using FastAPI.
In the named entity recognition pipeline, following components were used:

  • Document assembler
  • Tokenizer
  • Pretrained spell checker spellcheck_dl
  • Pretrained word embeddings glove_100d
  • Pretrained NER model onto_100
  • NER converter to create NER chunks.

The pipeline created in this project is able to detect following entity types from given text:

CARDINAL, EVENT, WORK_OF_ART, ORG, DATE, GPE, PERSON, PRODUCT, NORP, ORDINAL, MONEY, LOC, FAC, LAW, TIME, PERCENT, QUANTITY, LANGUAGE

Files

  • extraction_model/:
    • config/
      • config.py: Configuration settings for the NER model.
    • pretrained_models/: A folder containing pre-trained sparknlp models.
      • glove_100d_en_2.4.0_2.4_1579690104032: Pretrained word embeddings model
      • onto_100_en_2.4.0_2.4_1579729071672: Pretrained NER model
      • spellcheck_dl_en_3.4.1_3.0_1648457196011: Pretrained spell checker model
    • saved_ner_pipeline/: A folder containing saved NER pipeline.
      • ner_pipeline: Named Entity Recognition pipeline that is created with this project.
    • saprknlp_jar/
      • spark-nlp-assembly-5.3.2.jar: Jar file for the sparknlp library.
    • extraction.py: FastAPI application code containing the endpoints for NER.
    • log_manager.py: Module for initializing the logger.
    • pipeline_manager.py: Module for managing the Spark NLP pipeline.
  • requirements.txt: List of Python dependencies required to run the project.
  • README.md: This README file providing information about the project.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages