A Python library for loading websites and asking questions using Hugging Face AI. Developed by Fardin Ibrahimi, Bachelor of Science in Computer Science and CEO of Humanoid Company. Humanoid Company specializes in developing AI applications and models that closely emulate human actions and decision-making approaches, with the mission statement 'Not Human, Beyond Human'. This library enables more accessible and innovative web interaction capabilities.
Project description
WebNexa
A simple Python library for loading websites and asking questions about them using Hugging Face AI models.
About
This library was developed by Fardin Ibrahimi, Bachelor of Science in Computer Science and CEO of Humanoid Company. Humanoid Company specializes in developing AI applications and models that closely emulate human actions and decision-making approaches, with the mission statement "Not Human, Beyond Human". This library enables more accessible and innovative web interaction capabilities.
Installation
pip install webnexa
Quick Start
from webnexa import WebNexa
# Initialize (API key from environment variable HUGGINGFACE_API_KEY)
chat = WebNexa()
# Or pass API key directly
chat = WebNexa(hf_token="your-api-key-here")
# Load a website
chat.load_website("https://example.com")
# Ask questions
answer = chat.ask("What is this website about?")
print(answer)
# Get streaming responses
for chunk in chat.ask("Tell me more", use_streaming=True):
print(chunk, end="", flush=True)
# Summarize the website
summary = chat.summarize(max_lines=5)
print(summary)
Setup
Set your Hugging Face API key as an environment variable:
export HUGGINGFACE_API_KEY="your-api-key-here"
Or pass it directly when creating the WebNexa instance:
chat = WebNexa(hf_token="your-api-key-here")
Features
- Load websites: Extract content from any website URL
- Ask questions: Get AI-powered answers based on the website content
- Streaming support: Get real-time streaming responses
- Summarization: Generate concise summaries of website content
Requirements
- Python 3.8+
- Hugging Face API key
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file webnexa-0.1.0.tar.gz.
File metadata
- Download URL: webnexa-0.1.0.tar.gz
- Upload date:
- Size: 11.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7105592b5c623268ac256ea6cf9d24ac47ec32be922e7255d52b41f333e8aa86
|
|
| MD5 |
6d8e804ffe732167157ab15788f09943
|
|
| BLAKE2b-256 |
012f1bc6fd903bfb93417bae7f813020722426c1f924d980f37f552b111bd6ed
|
File details
Details for the file webnexa-0.1.0-py3-none-any.whl.
File metadata
- Download URL: webnexa-0.1.0-py3-none-any.whl
- Upload date:
- Size: 7.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
983b251d2435ac5dbb443f553f2b38d7fb3dc690acefda715301e91b61bf4ff7
|
|
| MD5 |
2ab919dfc41bf2f4bee5ec9537fce0d6
|
|
| BLAKE2b-256 |
8a261d1f343145240ad099f1a19bd3c7646f7582d97b5e156d08b94a48447f54
|