Skip to main content

Search and summarize the web with ease!

Project description

Summer Search

summer-search is a Python package that provides a simple interface for searching the web, extracting relevant content, and generating a summary based on the extracted information. The package leverages popular libraries such as requests, BeautifulSoup, and transformers to achieve its functionality.

Installation

You can install the package using pip:

pip install summer-search

Requirements:

  • bs4 (Beautiful Soup 4):

  • requests:

  • transformers:

  • sentencepiece:

  • tensorflow:

  • torch:

checkout the requirements.txt

 pip install -r requirements.txt

Make sure to install these dependencies before using the summer-search package to ensure all the required libraries are available.

Usage

from SummerSearch import summerSearch



# Create an instance

searcher = summerSearch()

print("Ready to search and summarize!")



# Perform a search

while True:



    # query to search 

    search_query = input("Enter a search query: ")

    raw_paragraph = searcher.search(search_query=search_query,filter="fixed_index",filter_value=1)

    print("Generating summary...")



    #specifying the model

    model = "t5-small"



    #summerization

    result = searcher.summarize(raw_paragraph, model)



    # Print the results

    print("\nSearch Query:", result["search_query"])

    print("\nSummary:", result["summary"])

    print("\nReference Link:", result["reference"])

    print("\nLearn More Links:", result["learn_more"])

    print("\nAdditional Links:", result["all_links"])

Documentation

  • summerSearch Class

Methods

  • search(search_query, filter="accuracy", filter_value=2): Performs a search and returns the raw paragraph.

    • search_query: The user's search query.

    • filter: Filtering option ("accuracy" or "fixed_index").

    • filter_value: Value based on the selected filter (default is 2).

  • summarize(raw_paragraph, model): Summarizes the raw paragraph using a specified model.

    • raw_paragraph: The raw text to be summarized.

    • model: The summarization model to use.

Summarization Models

The summerSearch class supports the following summarization models:

  • t5-small: A small variant of the T5 (Text-to-Text Transfer Transformer) model for general and basic summaries.

  • facebook/bart-large-cnn: The BART (BART: Denoising Sequence-to-Sequence Pre-training) model, specifically the large CNN variant, for general and more proper summaries.

  • kabita-choudhary/finetuned-bart-for-conversation-summary: A fine-tuned BART model for conversation summaries.

Feel free to choose the model that best fits your requirements and experiment with different models to observe variations in summarization results.

Notes

Feel free to explore and experiment with the package

  • You can always contribute to the package!

  • The package uses a combination of web scraping and summarization techniques to provide relevant information based on the user's search query.

  • The filter and filter_value parameters in the search method allow users to customize the search process based on accuracy or a fixed index.

  • The summarize method utilizes the Hugging Face Transformers library for text summarization.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

summer-search-0.0.4.tar.gz (4.7 kB view details)

Uploaded Source

Built Distribution

summer_search-0.0.4-py3-none-any.whl (4.7 kB view details)

Uploaded Python 3

File details

Details for the file summer-search-0.0.4.tar.gz.

File metadata

  • Download URL: summer-search-0.0.4.tar.gz
  • Upload date:
  • Size: 4.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.2

File hashes

Hashes for summer-search-0.0.4.tar.gz
Algorithm Hash digest
SHA256 ff022ed9ab4d822c794ae0a344be2b74f06c10ce54b2c65712416b68072d3c12
MD5 4e118737e98ca5e219cc977489f58577
BLAKE2b-256 bc1c051e83fcdef9ae98c9a228693d018bb42ba4467ea9ff8bdcd76edc4350cf

See more details on using hashes here.

File details

Details for the file summer_search-0.0.4-py3-none-any.whl.

File metadata

File hashes

Hashes for summer_search-0.0.4-py3-none-any.whl
Algorithm Hash digest
SHA256 f4bb518d8b1ea61f2d6d90fd0e5642cf1aa18f0cfc5e7d56de048b633e7e2386
MD5 acb037ee22b81ccfe777f8cac410bcca
BLAKE2b-256 053cee2a5ea52a3e75daa9db601e0dc4269edaac90b876c82ec62e2757748cc2

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page