Ricardo Santos

Same issue here. The env vars look like this: ``` LLM_MODEL=azure/gpt-4 ``` And still is showing resource not found. After debugging a bit further and printing the value of the...

Found the error: https://github.com/OpenDevin/OpenDevin/blob/0e572c3e415dd11eb9b3fa0a286c17edb4051f06/opendevin/server/agent/agent.py#L138 This line is executing this: ```python model = self.get_arg_or_default(args, ConfigType.LLM_MODEL) ``` It is taking the default value from the args. This should be rather replaced to:...

I created this PR to address this: https://github.com/OpenDevin/OpenDevin/pull/1271

When using azure, and when we change the LLM_MODEL environment variable to replace the LLM version, you will notice that the highlighted piece of code, uses the args default value...

Btw, it is hardcoded here, when launching the monologe agent https://github.com/OpenDevin/OpenDevin/blob/2242702cf94eab7275f2cb148859135018d9b280/frontend/src/services/settingsService.ts#L30

I did this with Poetry. This is the error log: ``` Because no versions of crewai-tools match >0.2.5,=0.4.22,=0.2.5,=0.4.22,=0.5.0,0.1.103,=0.2.5,=0.1.103,

As of this moment we dont have docummentation, and we need to improve that. We are working on this!

I am also facing the same issue. MetadataMode being changed to either `EMBED` or `ALL` it is always returning metadata `NONE`.

Thank you so much for your follow-up. I am familiar with the latest changes, as I also went through the code differences when debugging locally. I am currently harnessing v0.15.0....

Dear Team, @scanny answering your questions: > - You are partitioning DOCX documents that contain tables. Yes, that is the case > -The Table elements produced include .metadata.text_as_html fields that...