Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added latest GPT4 Omni and replaced preview GPT4 models with gpt-4-turbo #214

Open
wants to merge 1 commit into
base: master
Choose a base branch
from

Conversation

glienard
Copy link

No description provided.

@spppaul
Copy link

spppaul commented May 18, 2024

Please get this into nuget soon :)

It would be better if you could provide a string override so people didn't have to wait for you to make a change when a new model was introduced.

@GuyEzro
Copy link

GuyEzro commented May 19, 2024

is it possible to add support for vectorStore?

@shotyme
Copy link

shotyme commented May 19, 2024

Great, please merge this asap!

@ghostrider0470
Copy link

really urgently required , thanks for making this PR

@OkGoDoIt
Copy link
Owner

OkGoDoIt commented May 30, 2024

You can always pass in the model name as a string rather than using the strongly typed models class. Just use the model name identifier string that’s in the official OpenAI API docs. There’s an implicit cast of string to Model.

For example:

var chat = api.Chat.CreateConversation();
chat.Model = "gpt-4o";

Unfortunately I’m not able to make any updates for the next couple weeks, and I can’t publicly announce what’s up for another week or two. But I promise you it’ll be worth the wait. Keep an eye on the official Microsoft blogs perhaps 😉

@spppaul
Copy link

spppaul commented May 30, 2024

You can always pass in the model name as a string rather than using the strongly typed models class. Just use the model name identifier string that’s in the official OpenAI API. There’s an implicit cast of string to Model

Unfortunately I’m not able to make any updates for the next couple weeks, and I can’t publicly announce what’s up for another week or two. But I promise you it’ll be worth the wait. Keep an eye on the official Microsoft blogs perhaps 😉

This worked for me:

    public static Model GPT4_Omni => new Model("gpt-4o") { OwnedBy = "openai" };

......
var response = await openAi.Chat.CreateChatCompletionAsync(
new ChatRequest
{
Model = GPT4_Omni,
......

/// <summary>
/// GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.
/// </summary>
public static Model GPT4_Vision => new Model("gpt-4-turbo") { OwnedBy = "openai" };
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The model name for GPT4_Vision is the same as GPT4_Turbo. So basically they are referencing the same model.

/// Our most advanced, multimodal flagship model that’s cheaper and faster than GPT-4 Turbo.
/// </summary>
public static Model GPT4_Omni => new Model("gpt-4o") { OwnedBy = "openai" };
#endregion
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we add gpt-4o-mini

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

8 participants