adding the llm-gpt4all models breaks the python app.

[jwhowa]

I installed llm no problem, assigning my openai key, and am able to speak to gpt4 without problem, see the output of my llm models command:

OpenAI Chat: gpt-3.5-turbo (aliases: 3.5, chatgpt)
OpenAI Chat: gpt-3.5-turbo-16k (aliases: chatgpt-16k, 3.5-16k)
OpenAI Chat: gpt-4 (aliases: 4, gpt4)
OpenAI Chat: gpt-4-32k (aliases: 4-32k)
OpenAI Chat: gpt-4-1106-preview
OpenAI Chat: gpt-4-0125-preview
OpenAI Chat: gpt-4-turbo-preview (aliases: gpt-4-turbo, 4-turbo, 4t)
OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instruct)

But when I attempt "llm install llm-gpt4all", it appears to work, but llm is now broken. "llm models" gives the following error:

`(bob) [pazgsai01|~/bob:$] llm models list
Traceback (most recent call last):
  File "/home/myuser/bob/bob/bin/llm", line 8, in <module>
    sys.exit(cli())
<snip>
FileNotFoundError: Model file does not exist: PosixPath('/home/myuser/.cache/gpt4all/mistral-7b-openorca.gguf2.Q4_0.gguf')

Whether I try this on Windows or Linux, I get the exact error message.

If I uninstall llm-gpt4all, LLM works just fine talking to OpenAI, it's just like the integration to iterate and download the models is broken?

Any help appreciated! -Jim

[slhck]

Same here, also under macOS.

➜ llm models list
Traceback (most recent call last):
  File "/opt/homebrew/bin/llm", line 8, in <module>
    sys.exit(cli())
             ^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/click/core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/click/core.py", line 1078, in main
    rv = self.invoke(ctx)
         ^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/click/core.py", line 1688, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/click/core.py", line 1688, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/click/core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/click/core.py", line 783, in invoke
    return __callback(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/llm/cli.py", line 799, in models_list
    for model_with_aliases in get_models_with_aliases():
                              ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/llm/__init__.py", line 80, in get_models_with_aliases
    pm.hook.register_models(register=register)
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/pluggy/_hooks.py", line 501, in __call__
    return self._hookexec(self.name, self._hookimpls.copy(), kwargs, firstresult)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/pluggy/_manager.py", line 119, in _hookexec
    return self._inner_hookexec(hook_name, methods, kwargs, firstresult)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/pluggy/_callers.py", line 138, in _multicall
    raise exception.with_traceback(exception.__traceback__)
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/pluggy/_callers.py", line 102, in _multicall
    res = hook_impl.function(*args)
          ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/llm_gpt4all.py", line 57, in register_models
    models.sort(
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/llm_gpt4all.py", line 59, in <lambda>
    not model.is_installed(),
        ^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/llm_gpt4all.py", line 179, in is_installed
    GPT4All.retrieve_model(
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/llm_gpt4all.py", line 38, in retrieve_model
    return _GPT4All.retrieve_model(model_name, model_path, allow_download, verbose)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/llm/0.13.1_1/libexec/lib/python3.12/site-packages/gpt4all/gpt4all.py", line 309, in retrieve_model
    raise FileNotFoundError(f"Model file does not exist: {model_dest!r}")
FileNotFoundError: Model file does not exist: PosixPath('/Users/werner/.cache/gpt4all/mistral-7b-openorca.gguf2.Q4_0.gguf')

[slhck]

This is fixed in #27 actually …