Add Optional `displayName` Field for Model Selection
planned
Pascal M
Hello Dify Community,
I'd like to propose a feature that addresses a challenge I've encountered: selecting the correct model for Dify apps when faced with non-descriptive deployment names from model providers.
Is this request related to a challenge you are facing?
Yes, the challenge is the difficulty in identifying the correct model due to generic or non-descriptive deployment names that are carried over from model providers like Azure to Dify.
What is the feature you'd like to see?
I propose adding an optional field called
displayName
to the model setup form in Dify. This field would allow users to enter a more descriptive and user-friendly name for the model. If a displayName
is provided, it should be displayed in the UI select inputs instead of the model name. If not provided, the model name would be used as a fallback.How will this feature improve your workflow / experience?
This feature will significantly enhance the model selection process by allowing me—and potentially other users—to quickly identify the right model for our Dify apps. It also enables the creation of model aliases tailored to specific use cases, such as "coding assistant model" for coding-related tasks, which simplifies the selection process for non-experts.
Additional Context or Comments
The UI should prioritize displaying the
displayName
over the model name in all selection interfaces within Dify when both are available. This will ensure a user-friendly and efficient model selection experience.Can you help with this feature?
I am open to assisting with testing and providing feedback to ensure the feature is implemented effectively and meets user needs.
I believe this feature will be a valuable addition to Dify, enhancing usability and reducing confusion during model selection. I look forward to the community's thoughts and feedback on this suggestion.
Chenhe Gu
planned
Chenhe Gu
Merged in a post:
Define different Organization ID for each app when using OpenAI API
MathieuTrachino
Hello team,
At the moment, when you enter your OpenAI API key in the model provider settings, it applies to all your Dify Apps.
The feature I propose is to be able to choose your Organization ID for each app.
It is particularly useful when working on different projects with different billing informations.
For instance :
- App A -> Organization ID A
- App B -> Organization ID B
Thank you
Chenhe Gu
Hey - thanks for the suggestion.
Would be highly interested in the underlying problem here - a potential feature we're thinking of is actually to provide some billing and token management on Dify, which would allow you to add token caps per app etc. Perhaps that would solve it from another direction?
MathieuTrachino
Chenhe Gu: Hi, billing management would be great if we could choose which OpenAI organization to bill for each app on dify. A token cap per app would not solve the issue.
My problem is that I work for 2 different organizations. so i'd like to be able to bill each organization independently. Like for example, when I select OpenAI as a model provider, i could assign which organization to bill.
This feature is crucial since it is mandatory if you intend to work for different clients/teams/projects...
one workaround would be to be able to assign a different OpenAI API key for each app instead of putting it at account level.
This request from Pascal could help identifying a newly added LLM with a different organization id :
Please reach out to me if you have any question or if I can help any further
Chenhe Gu
MathieuTrachino: Thanks for the background info! Pascal M's proposal seems indeed like an useful addon :) I'll merge these two together.
crazywoola
under review
Pascal M
It's possible to add additional models to the OpenAI Model Provider. I think you can use this to add a second gpt-4 for example, with another organization ID. But I think you then have the model 2 times in the list, and it would be hard to find out which model is for which organization.
This feature could fix that: https://dify.canny.io/user-feedback/p/add-optional-displayname-field-for-model-selection
MathieuTrachino
Pascal M: It works. the only way to identify to which organization it is connected is to send a request and check the usage logs in openAI