Jarvis AI is a Python Module which is able to perform task like Chatbot, Assistant etc. It provides base functionality for any assistant application. This JarvisAI is built using Tensorflow, Pytorch, Transformers and other opensource libraries and frameworks.
This project is created only for those who are interested in building a Virtual Assistant. Generally, it took lots of time to write code from scratch to build a Virtual Assistant. So, I have built a Library called "JarvisAI", which gives you easy functionality to build your own Virtual Assistant.
Click on the image below to watch the tutorial on YouTube-
Tutorial 1-
Tutorial 2-
Jarvis AI is a Python Module that is able to perform tasks like Chatbot, Assistant, etc. It provides base functionality for any assistant application. This JarvisAI is built using Tensorflow, Pytorch, Transformers, and other open-source libraries and frameworks. Well, you can contribute to this project to make it more powerful.
Official Website: Click Here
Official Instagram Page: Click Here
Get your Free API key from https://jarvisai.in
To use it only Python (> 3.6) is required.
To contribute to the project: Python is the only prerequisite for basic scripting, Machine Learning, and Deep Learning knowledge will help this model to do tasks like AI-ML. Read the How to Contribute section of this page.
The JarvisAI’s architecture is divided into two parts.
User End- It is basically responsible for getting input from the user and after preprocessing input it sends input to JarvisAI’s server. And once the server sends its response back, it produces output on the user screen/system.
Server Side- The server is responsible to handle various kinds of AI-ML, and NLP tasks. It mainly identifies user intent by analyzing user input and interacting with other external APIs and handling user input.
Install the latest version-
ip install JarvisAI
[Optional Step] If Pyaudio is not working or not installed you might need to install it separately-
In the case of Mac OSX do the following:
rew install portaudio
ip install pyaudio
In the case of Windows or Linux do the following:
Download pyaudio from: lfd.uci.edu/~gohlke/pythonlibs/#pyaudio
pip install PyAudio-0.2.11-cp310-cp310-win_amd64.whl
[Optional Step] If pycountry is not working or not installed then Install "python3-pycountry" Package on Ubuntu/Linux-
udo apt-get update -y
udo apt-get install -y python3-pycountry
[Optional Step] You might need to Install Microsoft Visual C++ Redistributable for Visual Studio 2022
You need only this piece of code-
def custom_function(*args, **kwargs):
command = kwargs.get('query')
entities = kwargs.get('entities')
print(entities)
# write your code here to do something with the command
# perform some tasks # return is optional
return command + ' Executed'
jarvis = JarvisAI.Jarvis(input_mechanism='voice', output_mechanism='both',
google_speech_api_key=None, backend_tts_api='pyttsx3',
use_whisper_asr=False, display_logs=False,
api_key='527557f2-0b67-4500-8ca0-03766ade589a')
# add_action("general", custom_function) # OPTIONAL
jarvis.start()
It will start your AI, it will ask you to give input and accordingly it will produce output.
You can configure input_mechanism
and output_mechanism
parameter for voice input/output or text input/output.
READ MORE: Google Speech API (Pricing and Key) at: https://cloud.google.com/speech-to-text
These are below supported intent that AI can handle, you can ask in natural language.
Example- "What is the time now", "make me laugh", "click a photo", etc.
Note: Some features / command might not work. WIP. Tell me bugs.
You can set below parameter while creating object of JarvisAI-
jarvis = JarvisAI.Jarvis(input_mechanism='voice', output_mechanism='both',
google_speech_api_key=None, backend_tts_api='pyttsx3',
use_whisper_asr=False, display_logs=False,
api_key='527557f2-0b67-4500-8ca0-03766ade589a')
For text input-'
input_mechanism='text'
For voice input-
input_mechanism='voice'
For text output-
output_mechanism='text'
For voice output-
output_mechanism='text'
For voice and text output-
output_mechanism='both'
WIP
You tell me
Instructions Coming Soon
Donate and Contribute to run me this project, and buy a domain
Feel free to use my code, don't forget to mention credit. All the contributors will get credits in this repo.
Mention below line for credits-
Credits-
Follow me on Instagram: https://www.instagram.com/dipesh_pal17
Subscribe me on YouTube: https://www.youtube.com/dipeshpal17