From 07ccfbcee5479f7a4b2f35935b817aebed9502a4 Mon Sep 17 00:00:00 2001 From: Rahim Nathwani Date: Sun, 4 May 2025 10:30:37 -0700 Subject: [PATCH] Improved docs for extra-openai-models.yaml (#957) - Mention mandatory model_name field - Document support_schema option --- docs/openai-models.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs/openai-models.md b/docs/openai-models.md index 9e34624..f8310b5 100644 --- a/docs/openai-models.md +++ b/docs/openai-models.md @@ -137,12 +137,15 @@ Let's say OpenAI have just released the `gpt-3.5-turbo-0613` model and you want ```yaml - model_id: gpt-3.5-turbo-0613 + model_name: gpt-3.5-turbo-0613 aliases: ["0613"] ``` The `model_id` is the identifier that will be recorded in the LLM logs. You can use this to specify the model, or you can optionally include a list of aliases for that model. If the model is a completion model (such as `gpt-3.5-turbo-instruct`) add `completion: true` to the configuration. +If the model supports structured extraction using json_schema, add `supports_schema: true` to the configuration. + For reasoning models like `o1` or `o3-mini` add `reasoning: true`. With this configuration in place, the following command should run a prompt against the new model: