v0.2.16 - intregration failed to configure bug

[pbn42]

Describe the bug

Using v0.2.146, installation works fine, but when i finished to create the integration, i got a "failed to configure" message.

Expected behavior
Integration shall start and should appear as a conversation agent

Logs
If applicable, please upload any error or debug logs output by Home Assistant.

`Enregistreur: homeassistant.config_entries
Source: config_entries.py:575
S'est produit pour la première fois: 22:11:11 (1 occurrences)
Dernier enregistrement: 22:11:11

Error setting up entry LLM Model 'acon96/Home-3B-v3-GGUF' (llama.cpp) for llama_conversation
Traceback (most recent call last):
  File "/usr/src/homeassistant/homeassistant/config_entries.py", line 575, in async_setup
    result = await component.async_setup_entry(hass, self)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/config/custom_components/llama_conversation/__init__.py", line 67, in async_setup_entry
    agent = await hass.async_add_executor_job(create_agent, backend_type)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/config/custom_components/llama_conversation/__init__.py", line 63, in create_agent
    return agent_cls(hass, entry)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/config/custom_components/llama_conversation/agent.py", line 139, in __init__
    self._load_model(entry)
  File "/config/custom_components/llama_conversation/agent.py", line 542, in _load_model
    validate_llama_cpp_python_installation()
  File "/config/custom_components/llama_conversation/utils.py", line 97, in validate_llama_cpp_python_installation
    raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)`

Thanks a lot

[acon96]

Can you post the contents of /proc/cpuinfo for the system this is running on? The error is that the integration is trying to execute an illegal instruction because it is installing the wrong variant of llama-cpp-python. See #99 for more info.

[pbn42]

Sure :

`processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 156
model name : Intel(R) Celeron(R) N5095A @ 2.00GHz
stepping : 0
microcode : 0x1b
cpu MHz : 1996.800
cache size : 16384 KB
physical id : 0
siblings : 2
core id : 0
cpu cores : 2
apicid : 0
initial apicid : 0
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx rdtscp lm constant_tsc arch _perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 cx 16 pdcm sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave rdrand hy pervisor lahf_lm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced tp r_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust smep erms rdseed smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves arat vnmi umip waitpkg gfn i rdpid movdiri movdir64b md_clear flush_l1d arch_capabilities
vmx flags : vnmi preemption_timer posted_intr invvpid ept_x_only ept_ad ep t_1gb flexpriority apicv tsc_offset vtpr mtf vapic ept vpid unrestricted_guest v apic_reg vid shadow_vmcs pml tsc_scaling
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs srbds mmio_stal e_data rfds
bogomips : 3993.60
clflush size : 64
cache_alignment : 64
address sizes : 39 bits physical, 48 bits virtual
power management:

processor : 1
vendor_id : GenuineIntel
cpu family : 6
model : 156
model name : Intel(R) Celeron(R) N5095A @ 2.00GHz
stepping : 0
microcode : 0x1b
cpu MHz : 1996.800
cache size : 16384 KB
physical id : 0
siblings : 2
core id : 1
cpu cores : 2
apicid : 1
initial apicid : 1
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx rdtscp lm constant_tsc arch _perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 cx 16 pdcm sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave rdrand hy pervisor lahf_lm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced tp r_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust smep erms rdseed smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves arat vnmi umip waitpkg gfn i rdpid movdiri movdir64b md_clear flush_l1d arch_capabilities
vmx flags : vnmi preemption_timer posted_intr invvpid ept_x_only ept_ad ep t_1gb flexpriority apicv tsc_offset vtpr mtf vapic ept vpid unrestricted_guest v apic_reg vid shadow_vmcs pml tsc_scaling
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs srbds mmio_stal e_data rfds
bogomips : 3993.60
clflush size : 64
cache_alignment : 64
address sizes : 39 bits physical, 48 bits virtual
power management:`

[mikaelheidrich]

For what it's worth I am having the exact same issue using v0.2.17:

`Logger: homeassistant.config_entries
Source: config_entries.py:575
First occurred: 10:26:19 (1 occurrences)
Last logged: 10:26:19

Error setting up entry LLM Model 'acon96/Home-3B-v3-GGUF' (llama.cpp) for llama_conversation
Traceback (most recent call last):
File "/usr/src/homeassistant/homeassistant/config_entries.py", line 575, in async_setup
result = await component.async_setup_entry(hass, self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 67, in async_setup_entry
agent = await hass.async_add_executor_job(create_agent, backend_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 63, in create_agent
return agent_cls(hass, entry)
^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/agent.py", line 139, in init
self._load_model(entry)
File "/config/custom_components/llama_conversation/agent.py", line 542, in _load_model
validate_llama_cpp_python_installation()
File "/config/custom_components/llama_conversation/utils.py", line 97, in validate_llama_cpp_python_installation
raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)
`
Logger: homeassistant.config_entries
Source: config_entries.py:575
First occurred: 10:26:19 (1 occurrences)
Last logged: 10:26:19

Error setting up entry LLM Model 'acon96/Home-3B-v3-GGUF' (llama.cpp) for llama_conversation
Traceback (most recent call last):
File "/usr/src/homeassistant/homeassistant/config_entries.py", line 575, in async_setup
result = await component.async_setup_entry(hass, self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 67, in async_setup_entry
agent = await hass.async_add_executor_job(create_agent, backend_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 63, in create_agent
return agent_cls(hass, entry)
^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/agent.py", line 139, in init
self._load_model(entry)
File "/config/custom_components/llama_conversation/agent.py", line 542, in _load_model
validate_llama_cpp_python_installation()
File "/config/custom_components/llama_conversation/utils.py", line 97, in validate_llama_cpp_python_installation
raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)

Logger: homeassistant.config_entries
Source: config_entries.py:575
First occurred: 10:26:19 (1 occurrences)
Last logged: 10:26:19

Error setting up entry LLM Model 'acon96/Home-3B-v3-GGUF' (llama.cpp) for llama_conversation
Traceback (most recent call last):
File "/usr/src/homeassistant/homeassistant/config_entries.py", line 575, in async_setup
result = await component.async_setup_entry(hass, self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 67, in async_setup_entry
agent = await hass.async_add_executor_job(create_agent, backend_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 63, in create_agent
return agent_cls(hass, entry)
^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/agent.py", line 139, in init
self._load_model(entry)
File "/config/custom_components/llama_conversation/agent.py", line 542, in _load_model
validate_llama_cpp_python_installation()
File "/config/custom_components/llama_conversation/utils.py", line 97, in validate_llama_cpp_python_installation
raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)

Logger: homeassistant.config_entries
Source: config_entries.py:575
First occurred: 10:26:19 (1 occurrences)
Last logged: 10:26:19

Error setting up entry LLM Model 'acon96/Home-3B-v3-GGUF' (llama.cpp) for llama_conversation
Traceback (most recent call last):
File "/usr/src/homeassistant/homeassistant/config_entries.py", line 575, in async_setup
result = await component.async_setup_entry(hass, self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 67, in async_setup_entry
agent = await hass.async_add_executor_job(create_agent, backend_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 63, in create_agent
return agent_cls(hass, entry)
^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/agent.py", line 139, in init
self._load_model(entry)
File "/config/custom_components/llama_conversation/agent.py", line 542, in _load_model
validate_llama_cpp_python_installation()
File "/config/custom_components/llama_conversation/utils.py", line 97, in validate_llama_cpp_python_installation
raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)

CPU is Genuine intel celeron 2955u

[mikaelheidrich]

To follow up, tried the new release and still have this error. I have tried manually adding various whl to the custom_components/llama_conversation/ directory and continuing the installation. All result with the same error:

Logger: homeassistant.config_entries
Source: config_entries.py:594
First occurred: 12:40:25 (6 occurrences)
Last logged: 14:11:04

Error setting up entry LLM Model 'acon96/Home-3B-v3-GGUF' (llama.cpp) for llama_conversation
Error setting up entry LLM Model 'llama_cpp_python-0.2.77-cp312-cp312-musllinux_1_2_x86_64-noavx.whl' (llama.cpp) for llama_conversation
Error setting up entry LLM Model 'llama_cpp_python-0.2.77-cp312-cp312-musllinux_1_2_x86_64-avx512.whl' (llama.cpp) for llama_conversation
Error setting up entry LLM Model 'llama_cpp_python-0.2.77-cp312-cp312-musllinux_1_2_x86_64.whl' (llama.cpp) for llama_conversation
Traceback (most recent call last):
File "/usr/src/homeassistant/homeassistant/config_entries.py", line 594, in async_setup
result = await component.async_setup_entry(hass, self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 80, in async_setup_entry
agent = await hass.async_add_executor_job(create_agent, backend_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/init.py", line 76, in create_agent
return agent_cls(hass, entry)
^^^^^^^^^^^^^^^^^^^^^^
File "/config/custom_components/llama_conversation/agent.py", line 152, in init
self._load_model(entry)
File "/config/custom_components/llama_conversation/agent.py", line 776, in _load_model
validate_llama_cpp_python_installation()
File "/config/custom_components/llama_conversation/utils.py", line 132, in validate_llama_cpp_python_installation
raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)

CPU is Genuine intel celeron 2955u

[acon96]

Your CPU says that it supports all of the required instructions but keeps crashing because of a missing instruction.

The solution to get around this is to follow the directions here to build wheels that are compatible with the machine you are using: https://github.com/acon96/home-llm/blob/develop/docs/Backend%20Configuration.md#build-your-own

[mikaelheidrich]

Hey! Thanks for the reply. I’m running Home Assistant OS supervised and the command line won’t let me execute docker or git commands. Guess I’ll have to find a different route. Thanks again!

[pbn42]

Your CPU says that it supports all of the required instructions but keeps crashing because of a missing instruction.

The solution to get around this is to follow the directions here to build wheels that are compatible with the machine you are using: https://github.com/acon96/home-llm/blob/develop/docs/Backend%20Configuration.md#build-your-own

Thanks a lot. I just generated it for my Intel(R) Celeron(R) N5095A @ 2.00GHz (see attachment below)

Can you just tell us where to store it in HA please ?

llama_cpp_python-0.2.77-cp312-cp312-musllinux_1_2_x86_64.zip

[benbender]

@pbn42 "Take the appropriate wheel and copy it to the custom_components/llama_conversation/ directory." (See https://github.com/acon96/home-llm/blob/develop/docs/Backend%20Configuration.md#wheels)

[benbender]

I followed the given instructions and placed the newly created wheel inside of the custom_components/llama_conversation/-folder.

I'm still getting:

2024-06-10 13:10:45.828 ERROR (MainThread) [homeassistant.config_entries] Error setting up entry LLM Model 'acon96/Home-3B-v3-GGUF' (llama.cpp) for llama_conversation
Traceback (most recent call last):
  File "/usr/src/homeassistant/homeassistant/config_entries.py", line 594, in async_setup
    result = await component.async_setup_entry(hass, self)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/config/custom_components/llama_conversation/__init__.py", line 80, in async_setup_entry
    agent = await hass.async_add_executor_job(create_agent, backend_type)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/config/custom_components/llama_conversation/__init__.py", line 76, in create_agent
    return agent_cls(hass, entry)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/config/custom_components/llama_conversation/agent.py", line 152, in __init__
    self._load_model(entry)
  File "/config/custom_components/llama_conversation/agent.py", line 776, in _load_model
    validate_llama_cpp_python_installation()
  File "/config/custom_components/llama_conversation/utils.py", line 132, in validate_llama_cpp_python_installation
    raise Exception(f"Failed to properly initialize llama-cpp-python. (Exit code {process.exitcode}.)")

Latest home-llm, latest home-assistant on a Intel(R) Celeron(R) N5105 @ 2.00GHz-CPU.

[bigboo3000]

I have exactly the same problem with an Intel Celeron J4105, I first use a "noavx" prebuilt wheel >not working

then I built a custom wheel on my machine and placed in correct folder, but I still have:
Exception: Failed to properly initialize llama-cpp-python. (Exit code -4.)