From 8035067175bf8a317e4a110033350e8d7f8941f9 Mon Sep 17 00:00:00 2001 From: Jo Stichbury Date: Fri, 2 Aug 2024 14:16:19 +0100 Subject: [PATCH] Update vizro-ai/docs/pages/user-guides/customize-vizro-ai.md Co-authored-by: Lingyi Zhang --- vizro-ai/docs/pages/user-guides/customize-vizro-ai.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vizro-ai/docs/pages/user-guides/customize-vizro-ai.md b/vizro-ai/docs/pages/user-guides/customize-vizro-ai.md index d9502f050..2fda1ba10 100644 --- a/vizro-ai/docs/pages/user-guides/customize-vizro-ai.md +++ b/vizro-ai/docs/pages/user-guides/customize-vizro-ai.md @@ -46,7 +46,7 @@ Refer to the [OpenAI documentation for more about model capabilities](https://pl === "OpenAI" - gpt-3.5-turbo `default`: Ideal for smaller requests and simple specifications. However, due to the complexity of dashboard creation, `gpt-3.5-turbo` often produces incomplete responses for larger tasks. - - gpt-4-turbo: Excels in dashboard creation tasks, providing the most reliable and complete responses. + - gpt-4-turbo: Excels in dashboard creation tasks, providing the most stable and complete responses. - gpt-4o: Performance is inconsistent. The dashboard creation workflow heavily depends on the model's ability to generate structured output, which `gpt-4o` struggles with. As a result, it often fails to provide responses with the correct schema, leading to dashboard building failures.