https://github.com/noob-no-1/irregular_capitalization_websearch

This is developed as a part of an agent for standardising and correcting the spelling of English words e.g. (iPhone, HelloKitty T恤) in data sets passed to the agent.
https://github.com/noob-no-1/irregular_capitalization_websearch

googlesearchapi langchain webscraping

Last synced: 6 days ago
JSON representation

This is developed as a part of an agent for standardising and correcting the spelling of English words e.g. (iPhone, HelloKitty T恤) in data sets passed to the agent.

• Host: GitHub
• URL: https://github.com/noob-no-1/irregular_capitalization_websearch
• Owner: Noob-No-1
• Created: 2024-12-20T02:28:06.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-12-30T03:35:39.000Z (5 months ago)
• Last Synced: 2025-02-17T21:46:27.517Z (3 months ago)
• Topics: googlesearchapi, langchain, webscraping
• Language: Python
• Homepage:
• Size: 255 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
This tool is developed as a part of an agent which is designed to enhance the llm model (StarFire (星火) developed by IFLYTEK) 

This part of the agent aims to develop a frequency table for the capitalization spelling for each of the keyword extracted.

Sample output:

"Pdf": [

    ["PDF", 675],

    ["pdf", 11],

    ["Pdf", 0],

],

"ar": [

    ["ar", 1],

    ["AR", 254],

    ["Ar", 0],

    ["aR", 0],

],

"WiFi": [

    ["WiFi", 167],

    ["wifi", 3],

    ["WIFI", 25],

    ["Wifi", 72],

    ["WIfi", 0],

],

"Acc线": [

    ["acc线", 0],

    ["ACC线", 2],

    ["Acc线", 0],

],

"hellokittyT恤": [

    ["hellokittyt恤", 0],

    ["HELLOKITTYT恤", 0],

    ["HellokittyT恤", 0],

    ["hellokittyT恤", 0],

],

"pnc": [

    ["PNC", 262],

    ["PnC", 0],

    ["pnc", 12],

]

'''