[GH-ISSUE #3839] [CHORE]: Migrate AzureOpenAI model key away from OpenAI to prevent naming collision #2454

Closed
opened 2026-02-22 18:29:44 -05:00 by yindo · 8 comments
Owner

Originally created by @jojac47 on GitHub (May 16, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3839

How are you running AnythingLLM?

Docker (local)

What happened?

When using an Azure Open AI as the llm provider I noticed that the individual workspace chat model selection was set to GPT-4o instead of the set deployment value name. This leads to please provide model errors until I change it in every workspace.

Are there known steps to reproduce?

No response

Originally created by @jojac47 on GitHub (May 16, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3839 ### How are you running AnythingLLM? Docker (local) ### What happened? When using an Azure Open AI as the llm provider I noticed that the individual workspace chat model selection was set to GPT-4o instead of the set deployment value name. This leads to please provide model errors until I change it in every workspace. ### Are there known steps to reproduce? _No response_
yindo added the enhancementgood first issue labels 2026-02-22 18:29:44 -05:00
Author
Owner

@timothycarambat commented on GitHub (May 16, 2025):

This is because of a legacy reason that both OpenAI and Azure share the same model key. That being said, If you set the deployment name at the system settings LLM you wont have to modify each workspace independently.

@timothycarambat commented on GitHub (May 16, 2025): This is because of a legacy reason that both OpenAI and Azure share the same model key. That being said, If you set the deployment name at the _system settings LLM_ you wont have to modify each workspace independently.
Author
Owner

@jojac47 commented on GitHub (May 16, 2025):

Makes sense, I did notice it works right away with system default as the llm provider. But my default provider is ollama. Good to know the cause, thank you!

@jojac47 commented on GitHub (May 16, 2025): Makes sense, I did notice it works right away with system default as the llm provider. But my default provider is ollama. Good to know the cause, thank you!
Author
Owner

@jojac47 commented on GitHub (May 16, 2025):

I should say my usual system default is ollama

@jojac47 commented on GitHub (May 16, 2025): I should say my usual system default is ollama
Author
Owner

@atharvanaik225 commented on GitHub (May 23, 2025):

Hi, I want to take up this issue,

If I understand correctly, I think this is caused by the naming collision between Azure OpenAI and regular OpenAI environment variables. I think changing the environment variable name for Azure OpenAI and making corresponding changes wherever Azure OpenAI model is used, should solve the problem.

@atharvanaik225 commented on GitHub (May 23, 2025): Hi, I want to take up this issue, If I understand correctly, I think this is caused by the naming collision between Azure OpenAI and regular OpenAI environment variables. I think changing the environment variable name for Azure OpenAI and making corresponding changes wherever Azure OpenAI model is used, should solve the problem.
Author
Owner

@timothycarambat commented on GitHub (May 25, 2025):

Yes, but it would also cause issues with every existing Azure setup in containers pre-patch

@timothycarambat commented on GitHub (May 25, 2025): Yes, but it would also cause issues with every existing Azure setup in containers pre-patch
Author
Owner

@atharvanaik225 commented on GitHub (May 25, 2025):

added backward compatibility to avoid issues in existing setups

@atharvanaik225 commented on GitHub (May 25, 2025): added backward compatibility to avoid issues in existing setups
Author
Owner

@eureka928 commented on GitHub (Jan 13, 2026):

Hi @timothycarambat nice to meet you.
Is this still opening?
I'd like to take up this issue if so.

@eureka928 commented on GitHub (Jan 13, 2026): Hi @timothycarambat nice to meet you. Is this still opening? I'd like to take up this issue if so.
yindo changed title from [CHORE]: Migrate AzureOpenAI model key away from OpenAI to prevent naming collision to [GH-ISSUE #3839] [CHORE]: Migrate AzureOpenAI model key away from OpenAI to prevent naming collision 2026-06-05 14:46:37 -04:00
yindo closed this issue 2026-06-05 14:46:38 -04:00
Author
Owner

@eureka0928 commented on GitHub (Jan 13, 2026):

Hi @timothycarambat nice to meet you.
Is this still opening?
I'd like to take up this issue if so.

<!-- gh-comment-id:3747188129 --> @eureka0928 commented on GitHub (Jan 13, 2026): Hi @timothycarambat nice to meet you. Is this still opening? I'd like to take up this issue if so.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2454