Skip to content

A new package that takes a text description of an image and returns a structured summary of the blurring tool's features and use cases. It processes user-provided text input about the tool, such as it

Notifications You must be signed in to change notification settings

chigwell/textblur-summary

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 

Repository files navigation

textblur_summary

PyPI version License: MIT Downloads LinkedIn

A Python package that extracts and structures key features and use cases from text descriptions of blurring tools, providing a clean, formatted summary without sensitive or technical details.


📌 Overview

textblur_summary processes user-provided text about a blurring tool (e.g., its purpose, benefits, and limitations) and returns a structured summary of its features. It highlights non-sensitive aspects like being free, instant, and watermark-free, while omitting technical or proprietary details.


🚀 Installation

Install via pip:

pip install textblur_summary

🔧 Usage

Basic Usage (Default LLM: ChatLLM7)

from textblur_summary import textblur_summary

# Example input: A user-provided description of a blurring tool
user_input = """
TextBlur is a free, instant image blurring tool. It allows users to blur faces or sensitive details in photos without watermarks.
"""

# Call the function (LLM7 API key is fetched from environment variable LLM7_API_KEY)
response = textblur_summary(user_input)
print(response)

Custom LLM Integration

You can pass your own LLM instance (e.g., OpenAI, Anthropic, or Google) for flexibility:

Using OpenAI:

from langchain_openai import ChatOpenAI
from textblur_summary import textblur_summary

llm = ChatOpenAI()
response = textblur_summary(user_input, llm=llm)
print(response)

Using Anthropic:

from langchain_anthropic import ChatAnthropic
from textblur_summary import textblur_summary

llm = ChatAnthropic()
response = textblur_summary(user_input, llm=llm)
print(response)

Using Google Generative AI:

from langchain_google_genai import ChatGoogleGenerativeAI
from textblur_summary import textblur_summary

llm = ChatGoogleGenerativeAI()
response = textblur_summary(user_input, llm=llm)
print(response)

🔑 API Key Configuration

  • Default LLM: Uses ChatLLM7 (from langchain_llm7) with the API key fetched from:
    • Environment variable: LLM7_API_KEY
    • Fallback: Hardcoded default (if no key is provided).
  • Custom API Key: Pass it directly:
    response = textblur_summary(user_input, api_key="your_llm7_api_key")
  • Get a Free API Key: Register at LLM7 Token.

📊 Function Parameters

Parameter Type Description
user_input str The text description of the blurring tool to analyze.
api_key Optional[str] LLM7 API key (optional if using environment variable).
llm Optional[BaseChatModel] Custom LLM instance (e.g., ChatOpenAI, ChatAnthropic). Defaults to ChatLLM7.

📝 Notes

  • Rate Limits: The default LLM7 free tier is sufficient for most use cases.
  • Output Format: Returns a list of structured key points (e.g., features, benefits).
  • Safety: Avoid sharing sensitive or proprietary details in user_input.

📢 Issues & Support

Report bugs or feature requests at: GitHub Issues


👤 Author