VisionLite: Lightweight Web Search With AI 🚀
A lightweight, efficient library for web search, text parsing, and semantic analysis using the WordLlama language model.
🌟 Features
- 🔍 Multiple search engine support (Google, Bing)
- 📝 Efficient text parsing and cleaning
- 🧠 Integration with WordLlama for semantic analysis
- ⚡ Fast and lightweight implementation
- 🎨 Optional search animation support
- 📊 Configurable result ranking
📦 Installation
pip install parselite searchlite wordllama
🚀 Quick Start
GoogleSearch+AI
from visionlite import vision
results = vision("What is quantum computing?")
print(results)
BingSearch+AI
from visionlite import visionbing
results = visionbing("What is quantum computing?")
print(results)
📖 Usage Examples
Basic Search with Google
def vision(query, k=1, max_urls=5, animation=False):
# Search, parse, and rank results
results = llm.topk(
query,
llm.split("".join(
parse(google(query, max_urls=max_urls, animation=animation))
)),
k=k
)
return "\n".join(results)
# Example usage
quantum_info = vision("quantum computing applications", k=3, max_urls=10)
Search with Bing
def visionbing(query, k=1, max_urls=5, animation=False):
# Search using Bing, parse, and rank results
results = llm.topk(
query,
llm.split("".join(
parse(bing(query, max_urls=max_urls, animation=animation))
)),
k=k
)
return "\n".join(results)
# Example usage
ai_results = visionbing("artificial intelligence trends", k=5)
🔧 Configuration
Search Parameters
query: Search query stringk: Number of top results to return (default: 1)max_urls: Maximum number of URLs to process (default: 5)animation: Enable/disable search animation (default: False)
🤝 Contributing
Contributions are welcome! Here's how you can help:
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- WordLlama team for the language model
- Contributors and maintainers
- Open source community
🔮 Future Plans
- Add support for more search engines
- Implement caching mechanism
- Improve parsing accuracy
- Add multilingual support
- Create GUI interface
⭐ Star History
📊 Performance
| Operation | Time (ms) | Memory (MB) |
|---|---|---|
| Search | 150-300 | 20-30 |
| Parse | 50-100 | 10-15 |
| Rank | 100-200 | 15-25 |
🔥 Showcase
Projects using ParserLite:
- Research Assistant Bot
- Content Aggregator
- Semantic Search Engine
- Data Mining Tool
Made with ❤️ by [Your Name]
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
visionlite-0.1.60.tar.gz
(25.9 kB
view details)
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 visionlite-0.1.60.tar.gz.
File metadata
- Download URL: visionlite-0.1.60.tar.gz
- Upload date:
- Size: 25.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
poetry/1.8.4 CPython/3.11.0rc1 Linux/6.8.0-49-generic
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bf4dfbb98845694c29b67dc88aa55590669a279af838e6c72e3704a491ed2b5a
|
|
| MD5 |
24e86c4923f6a6b73a6a0e433fa6d7ad
|
|
| BLAKE2b-256 |
87c7f0307e1608ea7ce68f4bb1307dad72de74dc4cb3e7e86b9b6e8779b99440
|
File details
Details for the file visionlite-0.1.60-py3-none-any.whl.
File metadata
- Download URL: visionlite-0.1.60-py3-none-any.whl
- Upload date:
- Size: 20.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
poetry/1.8.4 CPython/3.11.0rc1 Linux/6.8.0-49-generic
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fc8e1ef134e191aaa78e6b23638251de954c88a97271a2e97904e3f4e4a33304
|
|
| MD5 |
baba1cc23156c3e722f0195c77156b0c
|
|
| BLAKE2b-256 |
174f84065250e1f9ab8e025abb7e2a6a61934eceadbe88776488172936609397
|