Kalliope assistant + MM

E3V3A

@sispheor said in Kalliope assistant + MM:

We have added a single line command install for Kalliope.

Is it for the MMM-kalliope?

Fantastic! Sound like music to our ears!

sispheor

No it’s for Kalliope core. MMM-Kalliope need to be installed via only a clone of the module as usual.

And the kalliope neuron can be installed via the kalliope CLI. It’s in the doc of each community neuron.

NoNameRo

@sispheor when trying to install Kalliope on a freshly installed system, I have 2 errors

Searching for SpeechRecognition>=3.7.1
Reading https://pypi.python.org/simple/SpeechRecognition/
No local packages or working download links found for SpeechRecognition>=3.7.1
error: Could not find suitable distribution for Requirement.parse('SpeechRecognition>=3.7.1')

Searching for apscheduler>=3.3.1
Reading https://pypi.python.org/simple/apscheduler/
Downloading https://pypi.python.org/packages/c4/16/8be21944c787ef13cd7581c62d446053d079f36aa54ef20b5b45b378944d/APScheduler-3.5.1.tar.gz#md5=18c2050f24bad3dd82e17dd4b5f182df
Best match: APScheduler 3.5.1
Processing APScheduler-3.5.1.tar.gz
Writing /tmp/easy_install-NmMSMf/APScheduler-3.5.1/setup.cfg
Running APScheduler-3.5.1/setup.py -q bdist_egg --dist-dir /tmp/easy_install-NmMSMf/APScheduler-3.5.1/egg-dist-tmp-px4K5B
  File "build/bdist.linux-armv7l/egg/apscheduler/executors/base_py3.py", line 12
    async def run_coroutine_job(job, jobstore_alias, run_times, logger_name):
            ^
SyntaxError: invalid syntax

creating /usr/local/lib/python2.7/dist-packages/APScheduler-3.5.1-py2.7.egg
Extracting APScheduler-3.5.1-py2.7.egg to /usr/local/lib/python2.7/dist-packages
  File "/usr/local/lib/python2.7/dist-packages/APScheduler-3.5.1-py2.7.egg/apscheduler/executors/base_py3.py", line 12
    async def run_coroutine_job(job, jobstore_alias, run_times, logger_name):
            ^
SyntaxError: invalid syntax

then a little excitement, add the starter configuration to rpi_install_kalliope.sh, and let the user during the installation choose which language he wants to install

sispheor

@NoNameRo said in Kalliope assistant + MM:

SpeechRecognition

Hi,

I had this one time.
Can you try to install the lib manually?

sudo pip install SpeechRecognition

Then run the install again from the kalliope folder (in /home/pi)

sudo python setup.py

It’s weird, sometime pip doesn’t find this lib.

E3V3A

You should not have the pip installation in that script without:

checking if it is already installed
make sure what python version your using. pip2 or pip3?
allow user to cancel that installation, if they know they already have it

Most of the time, if you have both Py2 and Py3 installed, pip would apply to Py2 and pip3 to Py3.

NoNameRo

@sispheor SpeechRecognition was successfully installed, but sudo python setup.py has another error

pi@MagicMirror:~/kalliope $ sudo python setup.py
usage: setup.py [global_opts] cmd1 [cmd1_opts] [cmd2 [cmd2_opts] ...]
   or: setup.py --help [cmd1 cmd2 ...]
   or: setup.py --help-commands
   or: setup.py cmd --help

error: no commands supplied

sispheor

@E3V3A
Actually, we consider here that the user start the installation from a fresh install raspbian.
So he is using Python 2 and pip2.

sispheor

@NoNameRo sorry, forgot one word

sudo python setup.py install

sispheor

@E3V3A but yes you are right, a good script should be idempotent.
I’ll enhance it.

E3V3A

Does MMM-kalliope allow or have any Google Assistant or Alexa functionality?
If, yes, how to install it. I didn’t see anything in the neuron list…

Although Kalliope look very nice and surely better documented now, it will be hard to sell without these features. People wanna talk to AI, not only ask to turn your lights on or off, which you can do by your self. Perhaps a phone plugin so you can call it up and talk?

In addition it is a huge obstacle that you have to make plugins (or neurons or synapses or whatever you call it) for just about everything you want to talk to Kalliope about. This learning should be automated by ML, and integrated to the productivity tools you already have, including future Alexa and GA compatibility.

sispheor

Kalliope is not an IA but a framework to make an assistant. Kalliope is like Ansible actually by design.
From neuron you can cover almost all features provided by current assistant like Google or Alexa.

There is a Android app to control kalliope from your phone and a “Tasker” neuron to control your phone from kalliope.

Users have to make their brain in the language they want by using neuron. We provide “starter kit” to give a basic config and new user to understand the concept.

I Understand that is not what you are looking for. You should give a try to another app.

E3V3A

@sispheor Cool! Thanks a lot for clarifying.

marcnlx

Hi,

I really love the Kalliope Virtual Assistant. I used the Manual Install (Method #2) option, since the one-liner command failed on my RPi.

I managed to install Kalliope (“Kalliope version”: “0.5.1b”), but I have some issues having all the messages show in MMM-Kalliope module (in upper_third) on the mirror.

I have added this to my ~/MagicMirror/config/config.js file:

{
    module: "MMM-kalliope",
    position: "upper_third",
                        config: {
                                max: "5",
                                keep_seconds: "8",
                                title: "Kalliope",
                                notification: "KALLIOPE",
                                payload: "my message"
                                }

}

I have added this to my ~/kalliope_starter_en/brain.yml file:

- name: "mm-say"
  signals: []
  neurons:
    - magic_mirror:
        mm_url: "http://127.0.0.1:8080/kalliope"
        notification: "KALLIOPE"
        payload: "{{ kalliope_memory['kalliope_last_tts_message'] }}"

- name: "mm-alert"
  signals:
    - order: "send an alert to magic mirror"
  neurons:
    - magic_mirror:
        mm_url: "http://127.0.0.1:8080/kalliope"
        notification: "SHOW_ALERT"
        payload:
          title: "my alert title"
          message: "the message"
          timer: 5000

And I have added this to the hooks in my ~/kalliope_starter_en/settings.yml file:

#  on_start_speaking:
  on_start_speaking: "mm-say"

I’m not sure what I am missing here…would anybody be able to help me out?

I also sometimes have an issue after Kalliope gets triggered by the WakeUp word related to the microphone/audio (but this might also be caused by the mic on the usb webcam I am using…):

what can i do for you?
Threshold set to: 4000
Say something!
Google Speech Recognition could not understand audio
I don't recognize that order
Waiting for trigger detection
yes sir?
Threshold set to: 4000
Say something!
Google Speech Recognition could not understand audio
I don't know this order
Exception in thread Thread-2:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()
  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/signals/order/order.py", line 84, in run
    self.start_trigger()
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 382, in trigger
    return self.machine._process(func)
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 1020, in _process
    self._transition_queue[0]()
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 398, in _trigger
    return self._process(event_data)
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 408, in _process
    if trans.execute(event_data):
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 262, in execute
    self._change_state(event_data)
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 273, in _change_state
    event_data.machine.get_state(self.dest).enter(event_data)
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 119, in enter
    event_data.machine.callback(handle, event_data)
  File "/usr/local/lib/python2.7/dist-packages/transitions-0.6.4-py2.7.egg/transitions/core.py", line 990, in callback
    func(*event_data.args, **event_data.kwargs)
  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/signals/order/order.py", line 92, in start_trigger_process
    self.trigger_instance = TriggerLauncher.get_trigger(settings=self.settings, callback=self.trigger_callback)
  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/core/TriggerLauncher.py", line 32, in get_trigger
    parameters=trigger.parameters)
  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/core/Utils/Utils.py", line 140, in get_dynamic_class_instantiation
    return klass(**parameters)
  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/trigger/snowboy/snowboy.py", line 51, in __init__
    sleep_time=0.03)
  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/trigger/snowboy/snowboydecoder.py", line 98, in __init__
    stream_callback=audio_callback)
  File "build/bdist.linux-armv7l/egg/pyaudio.py", line 750, in open
    stream = Stream(self, *args, **kwargs)
  File "build/bdist.linux-armv7l/egg/pyaudio.py", line 441, in __init__
    self._stream = pa.open(**arguments)
IOError: [Errno -9985] Device unavailable

When starting kalliope with the –debug option, I see lines like this in the debug log:

2018-03-17 13:55:30 :: kalliope-0.5.1b :: Magic_mirror call Magic Mirror MMM-kalliope-API: http://127.0.0.1:8080/kalliope
2018-03-17 13:55:31 :: kalliope-0.5.1b :: Magic_mirrorcannot get a valid json from returned content

2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronLauncher] replacing brackets from {'notification': 'KALLIOPE', 'mm_url': 'http://127.0.0.1:8080/kalliope', 'is_api_call': True, 'payload': "{{kalliope_memory['kalliope_last_tts_message']}}", 'no_voice': False}, using {}
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronLauncher] replacing brackets from KALLIOPE, using {'kalliope_memory': {'kalliope_last_tts_message': 'what can i do for you?'}}
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronLauncher] replacing brackets from http://127.0.0.1:8080/kalliope, using {'kalliope_memory': {'kalliope_last_tts_message': 'what can i do for you?'}}
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronLauncher] replacing brackets from True, using {'kalliope_memory': {'kalliope_last_tts_message': 'what can i do for you?'}}
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronLauncher] replacing brackets from {{kalliope_memory['kalliope_last_tts_message']}}, using {'kalliope_memory': {'kalliope_last_tts_message': 'what can i do for you?'}}
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronLauncher] replacing brackets from False, using {'kalliope_memory': {'kalliope_last_tts_message': 'what can i do for you?'}, 'name': 'sir'}
2018-03-17 13:55:09 :: kalliope-0.5.1b :: Run neuron: "{'name': 'magic_mirror', 'parameters': {'notification': 'KALLIOPE', 'mm_url': 'http://127.0.0.1:8080/kalliope', 'is_api_call': True, 'payload': 'what can i do for you?', 'no_voice': False}}"
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [Utils]-> get_dynamic_class_instantiation : package path : kalliope.neurons.magic_mirror.magic_mirror
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [Utils]-> get_dynamic_class_instantiation : loading path : resources/neurons/magic_mirror/magic_mirror.py, as package Magic_mirror
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronModule] TTS args: {'name': 'pico2wave', 'parameters': {'cache': True, 'language': 'en-US'}}
2018-03-17 13:55:09 :: kalliope-0.5.1b :: Magic_mirror call Magic Mirror MMM-kalliope-API: http://127.0.0.1:8080/kalliope
2018-03-17 13:55:09 :: kalliope-0.5.1b :: Magic_mirrorcannot get a valid json from returned content
2018-03-17 13:55:09 :: kalliope-0.5.1b :: [NeuronModule] Say() called with message: {'content': '<!DOCTYPE html>\n<html lang="en">\n<head>\n<meta charset="utf-8">\n<title>Error</title>\n</head>\n<body>\n<pre>Cannot POST /kalliope</pre>\n</body>\n</html>\n', 'status_code': 404, 'response_header': {'Content-Length': '148', 'X-XSS-Protection': '1; mode=block', 'X-Download-Options': 'noopen', 'X-Content-Type-Options': 'nosniff', 'Content-Type': 'text/html; charset=utf-8', 'Strict-Transport-Security': 'max-age=15552000; includeSubDomains', 'Connection': 'keep-alive', 'Content-Security-Policy': "default-src 'self'", 'Date': 'Sat, 17 Mar 2018 12:55:09 GMT', 'X-Frame-Options': 'SAMEORIGIN', 'X-DNS-Prefetch-Control': 'off'}}

Accessing the URL http://192.168.1.16:8080/kalliope, gives me this:

Cannot GET /kalliope

I also see the following error using the CURL example (removed the “<” from the beginning on the output of each line):

pi@mirror:~ $ curl -H "Content-Type: application/json" -X POST -d '{"notification":"KALLIOPE", "payload": "my message"}' http://127.0.0.1:8080/kalliope      
!DOCTYPE html>
html lang="en">
head>
meta charset="utf-8">
title>Error</title>
/head>
body>
pre>Cannot POST /kalliope</pre>
/body>
/html>
pi@mirror:~ $

sispheor

@marcnlx why are you trying to reach the URL from your browser? It’s an API. It should be accessed from a script only.

marcnlx

@sispheor said in Kalliope assistant + MM:

@marcnlx why are you trying to reach the URL from your browser? It’s an API. It should be accessed from a script only.

The CURL example gave me this output on the CLI. I was only using my browser to make sure I was able to reach the API.

Any idea what configuration mistake I could have made?

sispheor

@marcnlx @marcnlx you’ve set http://127.0.0.1:8080/kalliope for the neuron but the mirror up is 192.168.1.16. doesn’t it?

Also, notification and payload are not needed in the config of the module.

marcnlx

@sispheor said in Kalliope assistant + MM:

@marcnlx @marcnlx you’ve set http://127.0.0.1:8080/kalliope for the neuron but the mirror up is 192.168.1.16. doesn’t it?

Also, notification and payload are not needed in the config of the module.

@sispheor 127.0.0.1 is the localhost IP, 192.168.1.16 is the external IP…the Magic Mirror is available on every IP in use on the RPi (listening address is set to 0.0.0.0).

I just commented out the notification and payload and thing are now showing on the Mirror! This is really cool! :)

Okay…now I need to figure out how to build the whole virtual assistant…on to “phase #2”.
In your demo video I saw a basically complete brain…is there any place where I can find that one? ;)

sispheor

@marcnlx take a look to starter kits. It contains example. Also there is an example of usage of each neuron on the website.
Have fun !

marcnlx

@sispheor said in Kalliope assistant + MM:

@marcnlx take a look to starter kits. It contains example. Also there is an example of usage of each neuron on the website.
Have fun !

I will! I’m going to check everything out later today, thanks!

marcnlx

I tested Kalliope yesterday night and once you know how it works, it’s pretty sweet! ;)

Unfortunately I noticed some bugs/issues which are discussed multiple times on Github, so for now I think I will wait until a later release since I need to restart Kalliope multiple times after 2-3 phrases because of pulseaudio issues which I can’t seem to fix:

2018-03-18 12:42:27 :: kalliope-0.5.1b :: File found in /home/pi/kalliope_starter_en/trigger/kalliope-EN-12samples.pmdl
Exception in thread Thread-2:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()

  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/trigger/snowboy/snowboydecoder.py", line 98, in __init__
    stream_callback=audio_callback)
  File "build/bdist.linux-armv7l/egg/pyaudio.py", line 750, in open
    stream = Stream(self, *args, **kwargs)
  File "build/bdist.linux-armv7l/egg/pyaudio.py", line 441, in __init__
    self._stream = pa.open(**arguments)
IOError: [Errno -9985] Device unavailable