Skip to main content

No project description provided

Project description

NeuralNet

Overview

NeuralNet is a high-performance, Rust-based library designed for fast retrieval and generation (RAG) tasks. Leveraging Rust's efficiency, NeuralNet delivers rapid, reliable, and intelligent contextual processing capabilities, making it ideal for applications requiring quick information retrieval and seamless response generation.

Features

  • Superfast Performance: Built using Rust for optimal speed and efficiency.
  • Flexible Contextual Processing: Supports complex RAG operations with minimal latency.
  • Easy Integration: Simple Python bindings for seamless use in Python projects.
  • Open Source: Licensed under the MIT License, allowing you to use, modify, and distribute freely.

Installation

To use NeuralNet in your Python projects, follow these steps:

  1. Install the Python Package

    First, install the package from PyPI:

    pip install NeuralNet
    

Usage

Here’s the simple code to utilize in your Python code:

    import neuralnet as net
    
    def test_rust_functions():
        urls = ["https://botpress.com/blog/what-is-an-ai-agent"]
        texts = net.extract_texts(urls)
        print("Extracted texts:", texts)
    
        query = "how scaling support works"
        response = net.generate_response(query, texts)
        print("Generated response:", response)
    
    if __name__ == "__main__":
        test_rust_functions()

Available Functions

`retrieve(query: str, documents: List[str]) -> str: Takes a query and a list of documents, returning the most relevant document based on contextual similarity.

Contributing

We welcome contributions to NeuralNet! If you have suggestions, bug reports, or would like to contribute code, please follow these steps:

  • **Fork the repository on GitHub.
  • **Create a new branch for your changes.
  • **Submit a pull request with a clear description of your changes.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

For questions or support, please contact Dhruv Kumar.

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

neuralnetrag-0.1.0.tar.gz (18.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

neuralnetrag-0.1.0-cp311-none-win_amd64.whl (1.6 MB view details)

Uploaded CPython 3.11Windows x86-64

File details

Details for the file neuralnetrag-0.1.0.tar.gz.

File metadata

  • Download URL: neuralnetrag-0.1.0.tar.gz
  • Upload date:
  • Size: 18.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: maturin/1.7.0

File hashes

Hashes for neuralnetrag-0.1.0.tar.gz
Algorithm Hash digest
SHA256 ced1e50c5af35984bae087b7393b83e431c187fe8987ba1ab514e4afcdff8104
MD5 88df7d01efdad034c73cc72e1456b123
BLAKE2b-256 8032c484e375d1960be3ff7966726e738ec5f60cd1c3258287e0f0f752a592bf

See more details on using hashes here.

File details

Details for the file neuralnetrag-0.1.0-cp311-none-win_amd64.whl.

File metadata

File hashes

Hashes for neuralnetrag-0.1.0-cp311-none-win_amd64.whl
Algorithm Hash digest
SHA256 7eac1f8498a6b600b65fb70a371895110d120191a2e6ad9b8f0fb5dad613b53e
MD5 7a40f343ed409685dbbe4cec58c138cd
BLAKE2b-256 4f42e60ffa72ac1728627b12576c8b21ebad98b2a3bee76fa00548710a310c3c

See more details on using hashes here.

Supported by

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