Skip to main content

NeoGPT 🚀

GitHub license GitHub issues GitHub stars GitHub forks Google Collab

pip install https://github.com/neokd/NeoGPT/releases/download/v0.1.0/neogpt-0.1.0-py3-none-any.whl

Not working? Read our setup guide here

$ neogpt

Introduction

NeoGPT is an AI assistant that transforms your local workspace into a powerhouse of productivity from your CLI. With features like code interpretation, multi-RAG support, vision models, and LLM integration, NeoGPT redefines how you work and create. Join the revolution and experience a new era of efficiency with NeoGPT.

NeoGPT is continuously evolving, and your feedback shapes its future. Join our Discord community to stay up to date with the latest developments.

Table of Contents

Getting Started

  1. Installation: Clone this repository and install the necessary dependencies.

      git clone https://github.com/neokd/NeoGPT.git
      cd NeoGPT/neogpt
      pip install -r requirements.txt
    
  2. Building Database Currently NeoGPT supports local files and Youtube videos. To build the database add your local files to the documents directory and URL in the builder.url file. Then run the builder script.

       python main.py --build
    

    This will create a database file in the neogpt/db folder. You can also specify the database to use by using --db flag. Supported databases are:

    • Chroma (default)
    • FAISS

    Currently the database is built using 2 papers as reference:

  3. Run NeoGPT: Run the CLI to start using NeoGPT. Requires Python v3.10. You can use the --help flag to view the available commands and options.

    python main.py
    

    You can also use --ui flag to run the Streamlit UI.

    python main.py --ui
    
  4. Project Documentation: To view the project documentation, run the following command in your terminal or command prompt (Development ⚠️)

    cd docs
    npm i mintlify
    mintlify dev
    

Features

  • Code Interpreter: Execute code seamlessly in your local environment with our Code Interpreter. Enjoy the convenience of real-time code execution, all within your personal workspace.

  • Multi RAG Support: NeoGPT supports multiple RAG techniques, enabling you to choose the most suitable model for your needs. It includes local RAG, ensemble RAG, web RAG, and more. 🧠📚

  • Vision: Explore a new dimension as NeoGPT supports vision models like bakllava and llava, enabling you to chat with images using Ollama. 🖼️👁️🧠

  • LLM 🤖: NeoGPT supports multiple LLM models, allowing users to interact with a variety of language models. We support LlamaCpp, Ollama, LM Studio, OpenAI, and Togerther Ai. 🤖🧠📚

Quick Start

pip install https://github.com/neokd/NeoGPT/releases/download/v0.1.0/neogpt-0.1.0-py3-none-any.whl

Terminal

After installing the package, you can run the CLI by typing the following command in your terminal.

$ neogpt

Python

from neogpt import db_retriever

chain = db_retriever()

chain.invoke("What operating system are we on?")

Commands

Code Interpreter

To use the Interpreter, type the following command in your terminal.

$ neogpt --interpreter

Build Vector Database

To build the vector database, type the following command in your terminal.

$ neogpt --build

Run Streamlit UI

To run the Streamlit UI, type the following command in your terminal.

$ neogpt --ui

Change Your LLM

Offline LLM

To change your LLM, type the following command in your terminal.

$ neogpt --model ollama/bakllava

Online LLM

To change your LLM, type the following command in your terminal.

Warning: Add your API key to the .env file before running the command.

$ neogpt --model together/mistralai/Mistral-7B-Instruct-v0.2

Magic Commands

  • 🔄 /reset - Reset the chat session
  • 🚪 /exit - Exit the chat session
  • 📜 /history - Print the chat history
  • 💾 /save - Save the chat history to a neogpt/conversations
  • 📋 /copy - Copy the last response from NeoGPT to the clipboard
  • ⏪ /undo - Remove the last response from the chat history
  • 🔁 /redo - Resend the last human input to the model
  • 📂 /load [path] - Load the saved chat history from the specified file
  • 🔖 /tokens [prompt] - Calculate the number of tokens for a given prompt
  • 📄 /export - Export the current settings to the settings/settings.yaml file
  • 📜 /conversations - List available previously saved conversations.
  • 📚 /source - Prints the source directory
  • 🔍 /search [keyword] - Search the chat history for the keyword
  • 📋 /copycode or /cc - Copy the last code block to the clipboard

Contributing

We welcome contributions to NeoGPT! If you have ideas for new features or improvements, please open an issue or submit a pull request. For more information, see our contributing guide.

License

This project is licensed under the MIT License - see the LICENSE file for details. Let's innovate together! 🤖✨

Metadata

Release files for neogpt 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for neogpt 0.1.0
File Size Uploaded Provenance
neogpt-0.1.0.tar.gz 4.5 MB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for neogpt 0.1.0
File Interpreter ABI Platform
neogpt-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 9.0 MB

Release files / neogpt-0.1.0.tar.gz

Download URL neogpt-0.1.0.tar.gz
Size 4.5 MB
Tags Source
SHA-256 checksum
How to use checksums
2714e5adcd766f93860a7cebeca4a7f753f67800ee1662b34f922a2812847b4d
BLAKE2b-256 checksum
How to use checksums
f3d45aef917dc9b516a091ab1b4fbc5a0d131c5f212d24dd3f05bbd7c1f73c72
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.8.2 CPython/3.11.8 Darwin/23.4.0

Release files / neogpt-0.1.0-py3-none-any.whl

Download URL neogpt-0.1.0-py3-none-any.whl
Size 4.5 MB
Tags Python 3
SHA-256 checksum
How to use checksums
cc90f1c7d666491fa4dd898d8c5846164995d6e9b37dc52d4dd21609d5e4bbb2
BLAKE2b-256 checksum
How to use checksums
4fabb97470142b198331c039780d67c7a41b5fcca2bf05a38a6d3b557176b38d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.8.2 CPython/3.11.8 Darwin/23.4.0

Security for neogpt 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page