FreeGenius AI, an advanced AI assistant that is capable of engaging in conversation and performing multi-step actions. Supports numerous open-source LLMs via Llama.cpp or Ollama or Groq Cloud API, with optional integration with AutoGen agents, OpenAI API, Google Gemini Pro, fabric and unlimited plugins.
Project description
# FreeGenius AI
FreeGenius AI is an ambitious project sparked by the pioneering work of [LetMeDoIt AI](https://github.com/eliranwong/letmedoit). It’s designed with the primary objective of offering a comprehensive suite of AI solutions that mirror the capabilities of [LetMeDoIt AI](https://github.com/eliranwong/letmedoit). However, FreeGenius AI is remarkably different in that all core features are completely free, and it doesn’t require the use of an OpenAI key.
As with [LetMeDoIt AI](https://github.com/eliranwong/letmedoit), FreeGenius AI is designed to be capable of engaging in intuitive conversations, executing codes, providing up-to-date information, and performing a wide range of tasks. It’s designed to learn, adapt, and grow with the user, offering personalized experiences and interactions.
Our recent developments, for example, [the ability to run multiple tools in a single request](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Running%20Multiple%20Tools%20in%20One%20Go.md), demonstrate that FreeGenius AI is far more capable than LetMeDoIt AI, while we still maintain backward compatibility with [LetMeDoIt AI](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/LetMeDoIt%20Mode.md).
FreeGenius AI supports [a wide range of AI backends and models](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Supported%20Backends%20and%20Models.md): Ollama, Llama.cpp, Llama-cpp-python (default), Groq Cloud API, OpenAI API, Google Gemini via Vertex AI. Llama-cpp-python is selected as backend by default, only because it does not require an extra step for setup.
Our recommendations: * For backend selection, we consider [Ollama](https://ollama.com/) as the best friendly free offline option and [Groq Cloud API](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Groq%20API%20Setup.md) as the best freiendly and free online option. * With regard to AI models, we have found wizardlm2 and mixtral works well FreeGenius AI, though many other are well-supported.
# Latest changes
https://github.com/eliranwong/freegenius/blob/main/latest_changes.md
## Beyond LetMeDoIt AI
https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/LetMeDoIt%20Mode.md
# Distinctive Features
[Support Wide Range of Backends and Models](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Supported%20Backends%20and%20Models.md)
[Tool Calling for Any LLMs](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Function%20Call%20Approach%20with%20Any%20LLMs.md)
[Running Multiple Tools in One Go](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Running%20Multiple%20Tools%20in%20One%20Go.md)
[Highly Customisable Plugins](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/000_Home.md#plugins)
[Integration with Popular AI Tools](https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/000_Home.md#integration)
# Quick Tool Calling
Version 0.2.86+ supports use of @ to specify a tool. Available tools:
@chat @paste_from_clipboard @improve_writing @convert_relative_datetime @copy_to_clipboard @append_prompt @command @append_command @fabric @append_fabric @list_current_directory_contents @extract_python_code @run_python_code @integrate_google_searches @add_google_calendar_event @add_outlook_calendar_event @analyze_audio @analyze_files @analyze_images @analyze_web_content @ask_chatgpt @ask_codey @ask_gemini @ask_groq @ask_llama3_1 @ask_llamacpp @ask_llamacppserver @ask_ollama @ask_palm2 @correct_python @build_agents @create_image @create_map @create_qrcode @create_statistical_graphics @datetimes @download_web_content @download_youtube_audio @download_youtube_video @edit_text @execute_computing_task @install_package @save_memory @retrieve_memory @modify_images @open_browser @pronunce_words @remove_image_background @search_chats @load_chats @search_finance @search_latest_news @search_sqlite @search_weather_info @send_gamil @send_outlook @send_tweet
![tools](https://github.com/user-attachments/assets/d3a301ee-a228-4d0c-882e-0dd06141be2f)
Remarks:
@chat is regarded as a single tool. If you just want a direct response generated by LLM, simply use @chat.
@execute_computing_task is like a magic tool designed to execute computing tasks on demand.
Tips: Enter @ to get input suggestions of available tools
# Selective Features
# Multiple Tools in One Go
From version 0.2.87+, FreeGenius AI supports use of multiple tools in a single request. It enables individual tools to work on results, generated by running previous tools.
![multiple_tools_in_single_prompt](https://github.com/user-attachments/assets/7bdc63cd-beca-44c9-bfb0-27596a5e0632)
Read more at: https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Running%20Multiple%20Tools%20in%20One%20Go.md
# Customizable Plugins
![plugins](https://github.com/eliranwong/freegenius/assets/25262722/6bb4b2f6-5684-42c1-95e3-7b12c3a38db6)
# System Command and Fabric Integration
System Command Integration: https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/System%20Command%20Integration.md
Fabric Integration: https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Fabric%20Integration.md
# Support GPU Offloading
![llamacpp_with_gpu_offloading_compressed](https://github.com/eliranwong/freegenius/assets/25262722/2d607fc1-e6b5-4c62-be14-325d73866fce)
# Access to Real-time Data
![realtime_information](https://github.com/eliranwong/freegenius/assets/25262722/d94fd9c3-f242-4c8c-8564-308f866e9adb)
# Access to Device Information
![access_device_information](https://github.com/eliranwong/freegenius/assets/25262722/6e3386a4-7314-4ce5-a64f-fffe35dff92e)
# Task Execution
![freegenius_ai_screenshot](https://github.com/eliranwong/freegenius/assets/25262722/1e9dd18e-aa4b-4e2c-8d76-386af7ba00ea)
# Content Creation
![content_creation](https://github.com/eliranwong/freegenius/assets/25262722/5582d519-b925-4e1b-8fd8-ecaa8422d391)
# Supported Platforms
Windows, macOS, Linux
Upcoming: Android
# Installation - an example
Install FreeGenius AI, by running:
To set up virtual environment (recommended):
> mkdir -p ~/apps/freegenius
> cd ~/apps/freegenius
> python3 -m venv freegenius
> source freegenius/bin/activate
To install:
> pip install –upgrade freegenius
Remarks: Auto-upgrade is supported in macOS and Linux versions, but not in Windows version. Windows users need to manually upgrade to get the latest features.
To run:
> freegenius
To start up with a particular backend, you may use parameter -b, e.g.:
> freegenius -b groq
Read more at https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/000_Home.md#installation
# Quick Guide
https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/Quick%20Guide.md
# More
Documentation https://github.com/eliranwong/freegenius/blob/main/package/freegenius/docs/000_Home.md
# Welcome Contributions
You are welcome to make contributions to this project by:
joining the development collaboratively
donations to show support and invest for the future
Support link: https://www.paypal.me/letmedoitai
Please kindly report of any issues at https://github.com/eliranwong/freegenius/issues
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
File details
Details for the file freegenius-0.3.12.tar.gz
.
File metadata
- Download URL: freegenius-0.3.12.tar.gz
- Upload date:
- Size: 5.5 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 35670ee50670e41d87914aa520d199cd4df74dd15f5256b0ce41832c37874fe7 |
|
MD5 | 3ad9d314aeed89e5823b8df234a9f02c |
|
BLAKE2b-256 | 0b7c388f747e5d6fe9a9093c14bc2cbf56da843b0d721e02c12120ab3e9d42da |
File details
Details for the file freegenius-0.3.12-py3-none-any.whl
.
File metadata
- Download URL: freegenius-0.3.12-py3-none-any.whl
- Upload date:
- Size: 5.7 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 47bc3e9d1ad11f5c5237c0f72b81fdb3209f3689b2c0197a01ea888befcdb72f |
|
MD5 | a0d74e88ffeed6dc4f44dfad4ae205a3 |
|
BLAKE2b-256 | ff6dfa4ce2fbb30a031826a763034f64905bc60c925528e6df36077f011b53c3 |