judahpaul16 / gpt-home Goto Github PK

I was able to build everything without any errors! I had to run an "apt --fix-broken" though as libflac12 had a number of dependencies to correct and install.

Now, I am getting these messages in the log (assuming that the wake word is "computer" - I don't get a response):

INFO:functions:Timed out, waiting for phrase to start...
ERROR:functions:Listening timed out: Traceback (most recent call last):
ERROR:functions:Listening timed out: Traceback (most recent call last):
ERROR:functions:Listening timed out: Traceback (most recent call last):
ERROR:functions:Listening timed out: Traceback (most recent call last):
ERROR:functions:Listening timed out: Traceback (most recent call last):
ERROR:functions:Listening timed out: Traceback (most recent call last):
ERROR:functions:Listening timed out: Traceback (most recent call last):

Originally posted by @brainhig in #12 (comment)

I have my openweather api key in the web console but when I try to use it, it shows the following error:

When I run "./setup.sh" I get the following error:

Building Docker image 'gpt-home' for ARMhf...
ERROR: "docker buildx build" requires exactly 1 argument.
See 'docker buildx build --help'.

Usage:  docker buildx build [OPTIONS] PATH | URL | -

Start a build
Docker build failed. Exiting...
cosmo@cosmo:~ $ 

https://docs.litellm.ai/docs/proxy/quick_start

System kept reporting "Network not connected. Retrying..." while connected to wifi. Turns out my Google wifi blocks ICMP and there is no way to enable it.

As a workaround I changed the following in common.py from this:

def network_connected():
return os.system("ping -c 1 google.com") == 0

to this:

def network_connected():
return 1

--samd

Fwiw I also




got a new display and resoldered. Looks cleaner and more intact but still no sign of life.

Originally posted by @ashepp in #12 (comment)

root@almalinux:/app# apt show dbus-daemon
Package: dbus-daemon
Version: 1.14.4-1ubuntu1
Priority: important
Section: admin
Source: dbus
Origin: Ubuntu
Maintainer: Ubuntu Developers <[email protected]>
Original-Maintainer: Utopia Maintenance Team <[email protected]>
Bugs: https://bugs.launchpad.net/ubuntu/+filebug
Installed-Size: 457 kB
Depends: dbus-bin (= 1.14.4-1ubuntu1), dbus-session-bus-common (>= 1.14.4-1ubuntu1), libapparmor1 (>= 2.8.94), libaudit1 (>= 1:2.2.1), libc6 (>= 2.34), libcap-ng0 (>= 0.7.9), libdbus-1-3 (= 1.14.4-1ubuntu1), libexpat1 (>= 2.1~beta3), libselinux1 (>= 3.1~), libsystemd0
Breaks: dbus (<< 1.13.18-2~)
Replaces: dbus (<< 1.13.18-2~)
Homepage: https://dbus.freedesktop.org/
Task: minimal, server-minimal
Download-Size: 114 kB
APT-Manual-Installed: no
APT-Sources: http://ports.ubuntu.com/ubuntu-ports lunar/main arm64 Packages
Description: simple interprocess messaging system (reference message bus)

System information:

[almalinux@almalinux ~]$ cat /etc/os-release
NAME="AlmaLinux"
VERSION="9.4 (Seafoam Ocelot)"
ID="almalinux"
ID_LIKE="rhel centos fedora"
VERSION_ID="9.4"
PLATFORM_ID="platform:el9"
PRETTY_NAME="AlmaLinux 9.4 (Seafoam Ocelot)"
ANSI_COLOR="0;34"
LOGO="fedora-logo-icon"
CPE_NAME="cpe:/o:almalinux:almalinux:9::baseos"
HOME_URL="https://almalinux.org/"
DOCUMENTATION_URL="https://wiki.almalinux.org/"
BUG_REPORT_URL="https://bugs.almalinux.org/"

ALMALINUX_MANTISBT_PROJECT="AlmaLinux-9"
ALMALINUX_MANTISBT_PROJECT_VERSION="9.4"
REDHAT_SUPPORT_PRODUCT="AlmaLinux"
REDHAT_SUPPORT_PRODUCT_VERSION="9.4"
SUPPORT_END=2032-06-01
[almalinux@almalinux ~]$ uname -a
Linux almalinux.local 6.1.31-v8.1.el9 #1 SMP PREEMPT Wed Jun 14 12:18:16 UTC 2023 aarch64 aarch64 aarch64 GNU/Linux
[almalinux@almalinux ~]$

Spotify API response:

Spotifyd logs:

I thought I'd try a fresh install to see if it made any difference. Before I was using Ubuntu Server LTS - whatever the newest one is on the Raspberry Pi Imager.

So I did a fresh install (using RPi Imager) and selected Ubuntu Server 23.10 64bit. I added settings for Wifi and SSH into RPi Imager so that the install would contain them already.

Then I booted up, SSH'd in, and all I did was:

• Ran sudo apt get update
• Installed raspi-config
• Ran raspi-config, and changed audio output to Phono
• Tested audio output successfully with speaker-test

Ran:

echo "export OPENAI_API_KEY='my api key'" >> ~/.bashrc
source ~/.bashrc
curl -s https://raw.githubusercontent.com/judahpaul16/gpt-home/main/contrib/setup.sh |
bash -s -- --no-build

At some point this failed with the error: "Got permission denied while trying to connect to the Docker daemon socket at unix:///var/run/docker.sock: Get http://%2Fvar%2Frun%2Fdocker.sock/v1.32/containers/json: dial unix /var/run/docker.sock: connect: permission denied"

• So I ran the command "sudo usermod -aG docker myusername" then rebooted the Pi

Then I ran this again:

echo "export OPENAI_API_KEY='my api key'" >> ~/.bashrc
source ~/.bashrc
curl -s https://raw.githubusercontent.com/judahpaul16/gpt-home/main/contrib/setup.sh |
bash -s -- --no-build

And this time it finished with no problems.

I connected to http://192.168.0.215 from a web browser on another machine, and the web interface comes up fine and lets me change options etc.

I tested by speaking to it, and all the same issues are still happening - no audio, and I can only give one command each time I restart the service, and I get the response when I click the service restart button.

Originally posted by @buffeh in #38 (reply in thread)

Hi, i installed everything as explained but the command gpt-start keeps failing with result 'exit-code'

The web interfacce Is working, except for the settings Tab which Is not loading.

Thanks in Advance, you had a Greta idea!

Updates, so after a few reboots I am able to get the mic to work (not sure how).
When I call it (wake word Cosmo), and ask for anything, it always says the same feedback on the speaker and on the OLED:

Heard <the question I asked>. Something went wrong. Name "handle_error" is not defined.

Please help?
Thanks!

Error connecting to Spotify: Command '['sudo', 'systemctl', 'restart', 'spotifyd']' returned non-zero exit status 1.

I ordered the full set of parts but spent longer than I'd anticipated on assembly and still not quite sure I have it right. Could you possibly post some additional photos from other angles? Possibly an assembly video?

Hi, I'm getting an error in the logs as below. The device says "Listening..." on the OLED but doesn't seem to be responsive otherwise.
I also tested the mic and speaker when putting the hardware together and both were fine. They now fail when I test them online (no mic) and the speaker only plays when issued in sudo mode. Not sure if this is related.

Error from web-interface event logs (it hangs and crashes so I'm unable to copy paste) but something along the line of:

ERROR:common:Listening timed out: Traceback (most recent call last)...

Any ideas please?
Thanks!

I've got it working for the basic functionality, Thank you SO much for your help and quick response!

Now I'm having issues with Open Weather API. Sorry, I'm testing one thing at a time. Please let me know if you want me to start new issues for anything new.

SUCCESS:functions:Heard: "whats the weather in santa fe new mexico"
ERROR:functions:Error: Traceback (most recent call last):
File "/home/ubuntu/gpt-home/functions.py", line 323, in open_weather_action
response = await session.get(f"https://api.openweathermap.org/data/3.0/onecall?lat={coords.get('lat')}&lon={coords.get('lon')}&appid={api_key}&units=imperial")
AttributeError: 'NoneType' object has no attribute 'get'

SUCCESS:functions:Something went wrong. 'NoneType' object has no attribute 'get'

Originally posted by @brainhig in #12 (comment)

I'm using a USB sound device to connect a couple small speakers (https://a.co/d/05CPIVYZ) and a USB microphone, mostly due to the long cord (https://a.co/d/00JrdQhD) and for the life of me I can't get the microphone to pick up.

I'm able to hear sound with aplay on both the host and in the container, and can record using arecord. I've had to modify my /etc/asound.conf to get to this point. This is currently what I have:

# Output device (hw:1)
pcm.!default {
    type plug
    slave.pcm {
        type hw
        card 1
    }
}

ctl.!default {
    type hw
    card 1
}

# Input device (hw:2)
pcm.input {
    type plug
    slave.pcm {
        type hw
        card 2
    }
}

ctl.input {
    type hw
    card 2
}

Here's the output of aplay -l

**** List of PLAYBACK Hardware Devices ****
card 0: Headphones [bcm2835 Headphones], device 0: bcm2835 Headphones [bcm2835 Headphones]
  Subdevices: 8/8
  Subdevice #0: subdevice #0
  Subdevice #1: subdevice #1
  Subdevice #2: subdevice #2
  Subdevice #3: subdevice #3
  Subdevice #4: subdevice #4
  Subdevice #5: subdevice #5
  Subdevice #6: subdevice #6
  Subdevice #7: subdevice #7
card 1: Device [USB PnP Audio Device], device 0: USB Audio [USB Audio]
  Subdevices: 1/1
  Subdevice #0: subdevice #0

And the output of arecord -l

**** List of CAPTURE Hardware Devices ****
card 1: Device [USB PnP Audio Device], device 0: USB Audio [USB Audio]
  Subdevices: 0/1
  Subdevice #0: subdevice #0
card 2: Microphone [USB Lavalier Microphone], device 0: USB Audio [USB Audio]
  Subdevices: 1/1
  Subdevice #0: subdevice #0

I've tried modifying common.py line:
engine.setProperty('alsa_device', 'hw:Headphones,0')
to a few different things. I'ved tried hw:Microphone,0 and plughw:2,0. Neither have worked.
The logs repeat over and over

INFO:common:Could not understand audio, waiting for a new phrase...

I'm hitting up against a brick wall at this point. I'm not sure what to try next. Any ideas?

Can you make the i2c display optional? It's a nice to have feature at best, and requiring a specific i2c device is rather limiting.
Great project! Looking forward to using this once I get it set up once I disable the display code.