Does this require chat gpt-4 access in order to work?

[codyvb]

I'm getting this error when I attempt.

Python: Traceback (most recent call last): File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/__init__.py", line 91, in generate_blender_code response = openai.ChatCompletion.create( File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_resources/chat_completion.py", line 25, in create return super().create(*args, **kwargs) File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_resources/abstract/engine_api_resource.py", line 153, in create response, _, api_key = requestor.request( File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_requestor.py", line 226, in request resp, got_stream = self._interpret_response(result, stream) File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_requestor.py", line 619, in _interpret_response self._interpret_response_line( File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_requestor.py", line 682, in _interpret_response_line raise self.handle_error_response( openai.error.InvalidRequestError: The model:gpt-4` does not exist

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/init.py", line 236, in execute blender_code = generate_blender_code(context.scene.gpt4_chat_input, context.scene.gpt4_chat_history) File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/init.py", line 98, in generate_blender_code response = openai.ChatCompletion.create( File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_resources/chat_completion.py", line 25, in create return super().create(*args, **kwargs) File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_resources/abstract/engine_apiresource.py", line 153, in create response, , api_key = requestor.request( File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_requestor.py", line 226, in request resp, got_stream = self._interpret_response(result, stream) File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_requestor.py", line 619, in _interpret_response self._interpret_response_line( File "/Users/codybrown/Library/Application Support/Blender/3.4/scripts/addons/BlenderGPT-main/lib/openai/api_requestor.py", line 682, in _interpret_response_line raise self.handle_error_response( openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details. `

[AKhilRaghav0]

It's recommended to install the necessary requirements before proceeding to avoid any potential issues. To do this, I cloned the repository and used pip to install the required packages. After that, I zipped the directory back up and proceeded to install the addon from the preferences menu. Once installed, I entered my own OpenAI API key to authenticate the addon.

[codyvb]

hey. I did all of that and installed the add on. this is the error I get when I attempt to use it. are you using chat gpt-3 or gpt-4?

[gd3kr]

The addon defaults to GPT3 if you don't have access to GPT4. So it should be fine even if you're not using GPT4

[Ruuubickk]

I have GPT-4 access and getting the same error as above regardless.

[gd3kr]

@Ruuubickk openai.error.RateLimitError suggests that you might not have enough credits to satisfy the API request. Could you make sure you’re not being bottlenecked by your usage limit? https://platform.openai.com/account/billing/limits

[Ruuubickk]

I've not made any API calls today, not have I come anywhere close to my soft limit cap!

Edit: After waiting ~10 minutes after entering a new API key, it seems to now be working !