# 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.
# Beyond LetMeDoIt AI
https://github.com/eliranwong/freegenius/wiki/Beyond-LetMeDoIt-AI
# Goals
The author aims to equip FreeGenius AI, as an AI suite that is able to:
- run offline
- support local LLM servers
- support open-source large language models
- support optional, but not required, OpenAI ChatGPT and Google Gemini Pro API keys
- support current LetMeDoIt AI equivalent features
- devlops strategies plugin framework to execute multi-step generation or task execution
- run with common computer hardwares with reasonable and affordable cost
# Supported LLM Interface / Models
FreeGenius AI supports four interfaces: llamcpp, ollama, gemini, and chatgpt. It also maintains backward compatibility with LetMeDoIt AI in LetMeDoIt Mode. The configuration of the LLM Interface is determined by the value of config.llmInterface, which defaults to 'llamacpp'.
* llamacpp - [Llama.cpp](https://github.com/ggerganov/llama.cpp) / [Hugging Face models](https://huggingface.co/) + [Ollama Hosted models](https://ollama.com/library)
* ollama - [Ollama](https://ollama.com/) / [Ollama Hosted models](https://ollama.com/library)
* gemini - [Google Vertex AI](https://cloud.google.com/vertex-ai) / [Gemini Pro & Gemini Pro Vision](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models)
* chatgpt - [OpenAI API](https://platform.openai.com/) / [ChatGPT models](https://platform.openai.com/docs/models)
* letmedoit - [LetMeDoIt mode](https://github.com/eliranwong/freegenius/wiki/LetMeDoIt-Mode) / [ChatGPT models](https://platform.openai.com/docs/models)
Note: You can use Ollama models with either "llamacpp" or "ollama" set as interface.
FreeGenius AI also integrates the following models to enhance its abilities.
## Vision
llamacpp & ollama: Llava
gemini: Gemini Pro Vision
chatgpt & letmedoit: ChatGPT-4 Vision
## Audio Analysis
llamacpp & ollama: OpenAI Whisper (offline)
gemini: Google Cloud Speech-to-Text Service
chatgpt & letmedoit: Whisper (online API)
## Image Creation and Modification
llamacpp, ollama & gemini: stable-diffusion
gemini: plan for imagen when imagen is open to public access
chatgpt: dall-e-3
## Voice Typing Options
1. Google Speech-to-Text (Generic)
2. Google Speech-to-Text (API)
3. OpenAI Whisper (offline)
## Speech-to-Text Options
1. Google Text-to-Speech (Generic)
2. Google Text-to-Speech (API)
3. Elevenlabs (API)
4. Custom system commands
# Highly Customizable
# Installation
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 freegenius
To run:
> freegenius
## What to Expect During the Initial Launch?
https://github.com/eliranwong/freegenius/wiki/Initial-Launch
## Download for Offline Use
FreeGenius AI can work with downloaded LLMs without internet. Upon the initial launch of FreeGenius AI, it will automatically download all necessary LLMs for core features and configure them for your convenience.
Additional featured models are automatically downloaded based on specific feature requests. For instance, the Whisper model is automatically downloaded for offline use when users request the transcription of an audio file.
https://github.com/eliranwong/freegenius/wiki/Change-Model
## Install Ollama
This is optional. Install [Ollama](https://ollama.com/) to use [Ollama models](https://ollama.com/library) with either Llama.cpp or Ollama.
# Guick Guide
https://github.com/eliranwong/freegenius/wiki/Quick-Guide
# How to Change LLM Platform?
https://github.com/eliranwong/freegenius/wiki/Change-LLM-Platform
# How to Change Models?
https://github.com/eliranwong/freegenius/wiki/Change-Model
# How to Set up Google or OpenAI Credentials?
This is optional. Read https://github.com/eliranwong/freegenius/wiki/Set-up-Optional-Credentials
# Function Calling Approach with Any LLM
https://github.com/eliranwong/freegenius/wiki/Function-Calling-Approach-with-Any-LLMs
# Tool Dependence Configurations
https://github.com/eliranwong/freegenius/wiki/Tool-Selection-Configurations
# Documentation
In progress at: https://github.com/eliranwong/freegenius/wiki
Most current features follow https://github.com/eliranwong/letmedoit/wiki
Particularly, plugin structure follows https://github.com/eliranwong/letmedoit/wiki/Plugins-%E2%80%90-Overview
# TODO
https://github.com/eliranwong/freegenius/issues/4
# Examples (selective only):
FreeGenius AI Plugins allow you to acheive variety of tasks with simple words:
* generate tweets
> Post a short tweet about LetMeDoIt AI
* analyze audio
> transcribe "meeting_records.mp3"
* search / analyze financial data
> What was the average stock price of Apple Inc. in 2023?
> Analyze Apple Inc's stock price over last 5 years.
* search weather information
> what is the current weather in New York?
* search latest news
> tell me the latest news about ChatGPT
* search old conversations
> search for "joke" in chat records
* load old conversations
> load chat records with this ID: 2024-01-20_19_21_04
* connect a sqlite file and fetch data or make changes
> connect /temp/my_database.sqlite and tell me about the tables that it contains
* integrated Google PaLM 2 multiturn chat, e.g.
> ask PaLM 2 to write an article about Google
* integrated Google Codey multiturn chat, e.g.
> ask Codey how to use decorators in python
* execute python codes with auto-healing feature and risk assessment, e.g.
> join "01.mp3" and "02.mp3" into a single file
* execute system commands to achieve specific tasks, e.g.
> Launch VLC player and play music in folder "music_folder"
* manipulate files, e.g.
> remove all desktop files with names starting with "Screenshot"
> zip "folder1"
* save memory, e.g.
> Remember, my birthday is January 1st.
* send Whatsapp messages, e.g.
> send Whatsapp message "come to office 9am tomorrow" to "staff" group
* retrieve memory, e.g.
> When is my birthday?
* search for online information when ChatGPT lacks information, e.g.
> Tell me somtheing about LetMeDoIt AI?
* add google or outlook calendar events, e.g.
> I am going to London on Friday. Add it to my outlook calendar
* send google or outlook emails, e.g.
> Email an appreciation letter to someone@someone.com
* analyze files, e.g.
> Summarize 'Hello_World.docx'
* analyze web content, e.g.
> Give me a summary on https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/1171397/CC3_feb20.pdf
* analyze images, e.g.
> Describe the image 'Hello.png' in detail
> Compare images insider folder 'images'
* remove image background, e.g.
> Remove image background of "my_photo.png"
* create qrcode, e.g.
> Create a QR code for the website: https://letmedoit.ai
* create maps, e.g.
> Show me a map with Hype Park Corner and Victoria stations pinned
* create statistical graphics, e.g.
> Create a bar chart that illustrates the correlation between each of the 12 months and their respective number of days
> Create a pie chart: Mary £10, Peter £8, John £15
* solve queries about dates and times, e.g.
> What is the current time in Hong Kong?
* solve math problem, e.g.
> You have a standard deck of 52 playing cards, which is composed of 4 suits: hearts, diamonds, clubs, and spades. Each suit has 13 cards: Ace through 10, and the face cards Jack, Queen, and King. If you draw 5 cards from the deck, in how many ways can you draw exactly 3 cards of one suit and exactly 2 cards of another suit?
* pronounce words in different dialects, e.g.
> read tomato in American English
> read tomato in British English
> read 中文 in Mandarin
> read 中文 in Cantonese
* download Youtube video files, e.g.
> Download https://www.youtube.com/watch?v=CDdvReNKKuk
* download Youtube audio files and convert them into mp3 format, e.g.
> Download https://www.youtube.com/watch?v=CDdvReNKKuk and convert it into mp3
* edit text with built-in or custom text editors, e.g.
> Edit README.md
* improve language skills, e.g. British English trainer, e.g.
> Improve my writing according to British English style
* convert text display, e.g. from simplified Chinese to traditional Chinese, e.g.
> Translate your last response into Chinese
## Fetures with OpenAI API key ONLY
Currently, the following features work only with a valid OpenAI API key
* create ai assistants based on the requested task, e.g.
> create a team of AI assistants to write a Christmas drama
> create a team of AI assistants to build a scalable and customisable python application to remove image noise
* create images, e.g.
> Create an app icon for "LetMeDoIt AI"
* modify images, e.g.
> Make a cartoon verion of image "my_photo.png"
You can modify plugins or create your own ones. Read more about Plugins at https://github.com/eliranwong/letmedoit/wiki/Plugins-%E2%80%90-Overview
# 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
Raw data
{
"_id": null,
"home_page": "https://letmedoit.ai",
"name": "freegenius",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.12,>=3.8",
"maintainer_email": null,
"keywords": "ai assistant ollama llama llamacpp openai chatgpt gemini autogen rag agent stable-diffusion",
"author": "Eliran Wong",
"author_email": "support@letmedoit.ai",
"download_url": "https://files.pythonhosted.org/packages/71/1f/4e7f72777c44cdb7c32886f3769095c35f06cf583b3547c7a34ab0fc37b3/freegenius-0.1.0.tar.gz",
"platform": null,
"description": "# FreeGenius AI\n\nFreeGenius 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.\n\nAs 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.\n\n\n\n# Beyond LetMeDoIt AI\n\nhttps://github.com/eliranwong/freegenius/wiki/Beyond-LetMeDoIt-AI\n\n# Goals\n\nThe author aims to equip FreeGenius AI, as an AI suite that is able to:\n\n- run offline\n- support local LLM servers\n- support open-source large language models\n- support optional, but not required, OpenAI ChatGPT and Google Gemini Pro API keys\n- support current LetMeDoIt AI equivalent features\n- devlops strategies plugin framework to execute multi-step generation or task execution\n- run with common computer hardwares with reasonable and affordable cost\n\n# Supported LLM Interface / Models\n\nFreeGenius AI supports four interfaces: llamcpp, ollama, gemini, and chatgpt. It also maintains backward compatibility with LetMeDoIt AI in LetMeDoIt Mode. The configuration of the LLM Interface is determined by the value of config.llmInterface, which defaults to 'llamacpp'.\n\n* llamacpp - [Llama.cpp](https://github.com/ggerganov/llama.cpp) / [Hugging Face models](https://huggingface.co/) + [Ollama Hosted models](https://ollama.com/library)\n\n* ollama - [Ollama](https://ollama.com/) / [Ollama Hosted models](https://ollama.com/library)\n\n* gemini - [Google Vertex AI](https://cloud.google.com/vertex-ai) / [Gemini Pro & Gemini Pro Vision](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models)\n\n* chatgpt - [OpenAI API](https://platform.openai.com/) / [ChatGPT models](https://platform.openai.com/docs/models)\n\n* letmedoit - [LetMeDoIt mode](https://github.com/eliranwong/freegenius/wiki/LetMeDoIt-Mode) / [ChatGPT models](https://platform.openai.com/docs/models)\n\nNote: You can use Ollama models with either \"llamacpp\" or \"ollama\" set as interface.\n\nFreeGenius AI also integrates the following models to enhance its abilities.\n\n## Vision\n\nllamacpp & ollama: Llava\n\ngemini: Gemini Pro Vision\n\nchatgpt & letmedoit: ChatGPT-4 Vision\n\n## Audio Analysis\n\nllamacpp & ollama: OpenAI Whisper (offline)\n\ngemini: Google Cloud Speech-to-Text Service\n\nchatgpt & letmedoit: Whisper (online API)\n\n## Image Creation and Modification\n\nllamacpp, ollama & gemini: stable-diffusion\n\ngemini: plan for imagen when imagen is open to public access\n\nchatgpt: dall-e-3\n\n## Voice Typing Options\n\n1. Google Speech-to-Text (Generic)\n2. Google Speech-to-Text (API)\n3. OpenAI Whisper (offline)\n\n## Speech-to-Text Options\n\n1. Google Text-to-Speech (Generic)\n2. Google Text-to-Speech (API)\n3. Elevenlabs (API)\n4. Custom system commands\n\n# Highly Customizable\n\n\n\n# Installation\n\nInstall FreeGenius AI, by running:\n\nTo set up virtual environment (recommended):\n\n> mkdir -p ~/apps/freegenius\n\n> cd ~/apps/freegenius\n\n> python3 -m venv freegenius\n\n> source freegenius/bin/activate\n\nTo install:\n\n> pip install freegenius\n\nTo run:\n\n> freegenius\n\n## What to Expect During the Initial Launch?\n\nhttps://github.com/eliranwong/freegenius/wiki/Initial-Launch\n\n## Download for Offline Use\n\nFreeGenius AI can work with downloaded LLMs without internet. Upon the initial launch of FreeGenius AI, it will automatically download all necessary LLMs for core features and configure them for your convenience.\n\nAdditional featured models are automatically downloaded based on specific feature requests. For instance, the Whisper model is automatically downloaded for offline use when users request the transcription of an audio file.\n\nhttps://github.com/eliranwong/freegenius/wiki/Change-Model\n\n## Install Ollama\n\nThis is optional. Install [Ollama](https://ollama.com/) to use [Ollama models](https://ollama.com/library) with either Llama.cpp or Ollama.\n\n# Guick Guide\n\nhttps://github.com/eliranwong/freegenius/wiki/Quick-Guide\n\n# How to Change LLM Platform?\n\nhttps://github.com/eliranwong/freegenius/wiki/Change-LLM-Platform\n\n# How to Change Models?\n\nhttps://github.com/eliranwong/freegenius/wiki/Change-Model\n\n# How to Set up Google or OpenAI Credentials?\n\nThis is optional. Read https://github.com/eliranwong/freegenius/wiki/Set-up-Optional-Credentials\n\n# Function Calling Approach with Any LLM\n\nhttps://github.com/eliranwong/freegenius/wiki/Function-Calling-Approach-with-Any-LLMs\n\n# Tool Dependence Configurations\n\nhttps://github.com/eliranwong/freegenius/wiki/Tool-Selection-Configurations\n\n# Documentation\n\nIn progress at: https://github.com/eliranwong/freegenius/wiki\n\nMost current features follow https://github.com/eliranwong/letmedoit/wiki\n\nParticularly, plugin structure follows https://github.com/eliranwong/letmedoit/wiki/Plugins-%E2%80%90-Overview\n\n# TODO\n\nhttps://github.com/eliranwong/freegenius/issues/4\n\n# Examples (selective only):\n\nFreeGenius AI Plugins allow you to acheive variety of tasks with simple words:\n\n* generate tweets\n\n> Post a short tweet about LetMeDoIt AI\n\n* analyze audio\n\n> transcribe \"meeting_records.mp3\"\n\n* search / analyze financial data\n\n> What was the average stock price of Apple Inc. in 2023?\n\n> Analyze Apple Inc's stock price over last 5 years.\n\n* search weather information\n\n> what is the current weather in New York?\n\n* search latest news\n\n> tell me the latest news about ChatGPT\n\n* search old conversations\n\n> search for \"joke\" in chat records\n\n* load old conversations\n\n> load chat records with this ID: 2024-01-20_19_21_04\n\n* connect a sqlite file and fetch data or make changes\n\n> connect /temp/my_database.sqlite and tell me about the tables that it contains\n\n* integrated Google PaLM 2 multiturn chat, e.g.\n\n> ask PaLM 2 to write an article about Google\n\n* integrated Google Codey multiturn chat, e.g.\n\n> ask Codey how to use decorators in python\n\n* execute python codes with auto-healing feature and risk assessment, e.g.\n\n> join \"01.mp3\" and \"02.mp3\" into a single file\n\n* execute system commands to achieve specific tasks, e.g.\n\n> Launch VLC player and play music in folder \"music_folder\"\n\n* manipulate files, e.g.\n\n> remove all desktop files with names starting with \"Screenshot\"\n\n> zip \"folder1\"\n\n* save memory, e.g.\n\n> Remember, my birthday is January 1st.\n\n* send Whatsapp messages, e.g.\n\n> send Whatsapp message \"come to office 9am tomorrow\" to \"staff\" group\n\n* retrieve memory, e.g.\n\n> When is my birthday?\n\n* search for online information when ChatGPT lacks information, e.g.\n\n> Tell me somtheing about LetMeDoIt AI?\n\n* add google or outlook calendar events, e.g.\n\n> I am going to London on Friday. Add it to my outlook calendar\n\n* send google or outlook emails, e.g.\n\n> Email an appreciation letter to someone@someone.com\n\n* analyze files, e.g.\n\n> Summarize 'Hello_World.docx'\n\n* analyze web content, e.g.\n\n> Give me a summary on https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/1171397/CC3_feb20.pdf \n\n* analyze images, e.g.\n\n> Describe the image 'Hello.png' in detail\n\n> Compare images insider folder 'images'\n\n* remove image background, e.g.\n\n> Remove image background of \"my_photo.png\"\n\n* create qrcode, e.g.\n\n> Create a QR code for the website: https://letmedoit.ai\n\n* create maps, e.g.\n\n> Show me a map with Hype Park Corner and Victoria stations pinned\n\n* create statistical graphics, e.g.\n\n> Create a bar chart that illustrates the correlation between each of the 12 months and their respective number of days\n\n> Create a pie chart: Mary \u00a310, Peter \u00a38, John \u00a315\n\n* solve queries about dates and times, e.g.\n\n> What is the current time in Hong Kong?\n\n* solve math problem, e.g.\n\n> You have a standard deck of 52 playing cards, which is composed of 4 suits: hearts, diamonds, clubs, and spades. Each suit has 13 cards: Ace through 10, and the face cards Jack, Queen, and King. If you draw 5 cards from the deck, in how many ways can you draw exactly 3 cards of one suit and exactly 2 cards of another suit? \n\n* pronounce words in different dialects, e.g.\n\n> read tomato in American English\n\n> read tomato in British English\n\n> read \u4e2d\u6587 in Mandarin\n\n> read \u4e2d\u6587 in Cantonese\n\n* download Youtube video files, e.g.\n\n> Download https://www.youtube.com/watch?v=CDdvReNKKuk\n\n* download Youtube audio files and convert them into mp3 format, e.g.\n\n> Download https://www.youtube.com/watch?v=CDdvReNKKuk and convert it into mp3\n\n* edit text with built-in or custom text editors, e.g.\n\n> Edit README.md\n\n* improve language skills, e.g. British English trainer, e.g.\n\n> Improve my writing according to British English style\n\n* convert text display, e.g. from simplified Chinese to traditional Chinese, e.g.\n\n> Translate your last response into Chinese\n\n\n## Fetures with OpenAI API key ONLY\n\nCurrently, the following features work only with a valid OpenAI API key\n\n* create ai assistants based on the requested task, e.g.\n\n> create a team of AI assistants to write a Christmas drama\n\n> create a team of AI assistants to build a scalable and customisable python application to remove image noise\n\n* create images, e.g.\n\n> Create an app icon for \"LetMeDoIt AI\"\n\n* modify images, e.g.\n\n> Make a cartoon verion of image \"my_photo.png\"\n\nYou can modify plugins or create your own ones. Read more about Plugins at https://github.com/eliranwong/letmedoit/wiki/Plugins-%E2%80%90-Overview\n\n# Welcome Contributions\n\nYou are welcome to make contributions to this project by:\n\n* joining the development collaboratively\n\n* donations to show support and invest for the future\n\nSupport link: https://www.paypal.me/letmedoitai\n\nPlease kindly report of any issues at https://github.com/eliranwong/freegenius/issues\n",
"bugtrack_url": null,
"license": "GNU General Public License (GPL)",
"summary": "FreeGenius AI, an advanced AI assistant that can talk and take multi-step actions. Supports numerous open-source LLMs via Llama.cpp or Ollama, with optional integration with AutoGen agents, OpenAI API, Google Gemini Pro and unlimited plugins.",
"version": "0.1.0",
"project_urls": {
"Documentation": "https://github.com/eliranwong/letmedoit/wiki",
"Funding": "https://www.paypal.me/letmedoitai",
"Homepage": "https://letmedoit.ai",
"Source": "https://github.com/eliranwong/letmedoit",
"Tracker": "https://github.com/eliranwong/letmedoit/issues"
},
"split_keywords": [
"ai",
"assistant",
"ollama",
"llama",
"llamacpp",
"openai",
"chatgpt",
"gemini",
"autogen",
"rag",
"agent",
"stable-diffusion"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9603953e6d8c9a8ac6df859fcc69a10d3fbca1fd7f1f82733de90219ac2d7be2",
"md5": "74e495872177082f236c7d68b372eccb",
"sha256": "27e3d186d99de4887b6dcbb204bd7534b79d5abfb5ea4500d62afb0c5538b0d0"
},
"downloads": -1,
"filename": "freegenius-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "74e495872177082f236c7d68b372eccb",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.12,>=3.8",
"size": 5611295,
"upload_time": "2024-04-25T21:19:53",
"upload_time_iso_8601": "2024-04-25T21:19:53.981126Z",
"url": "https://files.pythonhosted.org/packages/96/03/953e6d8c9a8ac6df859fcc69a10d3fbca1fd7f1f82733de90219ac2d7be2/freegenius-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "711f4e7f72777c44cdb7c32886f3769095c35f06cf583b3547c7a34ab0fc37b3",
"md5": "4b936b2b11675241a601523737487b12",
"sha256": "79d176ee2cc185b9ded5bdcc5b97b08a02d9b8722dd2fc11b04ee7edfaab2bd1"
},
"downloads": -1,
"filename": "freegenius-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "4b936b2b11675241a601523737487b12",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.12,>=3.8",
"size": 5436702,
"upload_time": "2024-04-25T21:20:01",
"upload_time_iso_8601": "2024-04-25T21:20:01.799584Z",
"url": "https://files.pythonhosted.org/packages/71/1f/4e7f72777c44cdb7c32886f3769095c35f06cf583b3547c7a34ab0fc37b3/freegenius-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-25 21:20:01",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "eliranwong",
"github_project": "letmedoit",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "freegenius"
}
JSON
