keywordx 1.0.4

A Python library for extracting and matching keywords with semantic and entity-based boosting.

KeywordX

KeywordX is a lightweight Python library for extracting and matching keywords from text using semantic similarity and entity-based boosting.
Perfect for NLP pipelines, chatbots, search systems, and event extraction.

---

Features

• Extract keywords with semantic similarity scoring
• Boost keyword matches using entities (dates, times, places, etc.)
• Supports custom IDF weighting for better relevance
• Easy-to-use API for integration into NLP pipelines

---

Installation

Install from PyPI:

pip install keywordx

The en_core_web_md spaCy model is required for the library to function. Install it using the following command:

python -m spacy download en_core_web_md

If the en_core_web_md model is not available, the library will attempt to fall back to the smaller en_core_web_sm model. However, this may result in reduced accuracy. You can install the fallback model using:

python -m spacy download en_core_web_sm

Or install from source:

git clone https://github.com/keikurono7/keywordx.git
cd keywordx
pip install -e .

Quick Start

Here is a quick example to get you started:

from keywordx import KeywordExtractor

ke = KeywordExtractor()
text = "Tomorrow I have a work meeting at 5pm in Bangalore."
keywords = ["meeting", "time", "place", "date"]

result = ke.extract(text, keywords)
print(result)

Example Output

The result will include extracted entities and semantic matches with scores:

{
  "entities": [
    {"span": [0, 8], "text": "Tomorrow", "type": "DATE"},
    {"span": [34, 37], "text": "5pm", "type": "TIME"},
    {"span": [41, 50], "text": "Bangalore", "type": "GPE"}
  ],
  "semantic_matches": [
    {"keyword": "meeting", "match": "meeting", "score": 0.99},
    {"keyword": "time", "match": "5pm", "score": 1.0},
    {"keyword": "place", "match": "Bangalore", "score": 1.0},
    {"keyword": "date", "match": "Tomorrow", "score": 1.0}
  ]
}

API Reference

• KeywordExtractor()
  Initializes the keyword extractor.

• .extract(text, keywords) → dict
  Extracts keywords and entities from text.

  • text: input string
  • keywords: list of keywords to match

• Returns:

  • entities: named entities (DATE, TIME, GPE, etc.)
  • semantic_matches: list of matched keywords with similarity scores

Use Cases

• Event and meeting extraction for calendar assistants
• Chatbot intent detection
• Automatic tagging of documents and notes
• Context-aware search and indexing

Contributing

Contributions are welcome. For significant changes, please open an issue first to discuss the proposal.

Contributors

• Madhusudan

  • Email: [e-mail]
  • GitHub: keikurono7
  • Role: Code implementation

• Saniya Naaz

  • Email: [e-mail]
  • GitHub: Saniyanaaz11
  • Role: Research work

• Dr. Nandeeswar S B

  • Email: [e-mail]
  • Role: Concept and idea generation

License

This project is licensed under the MIT License. See the LICENSE file for details.