From 24072f2de03e95f55ebf844d307d3eebd714e5b0 Mon Sep 17 00:00:00 2001 From: Jo Stichbury Date: Mon, 25 Mar 2024 12:15:09 +0000 Subject: [PATCH] Update faq.md --- vizro-ai/docs/pages/user-guides/faq.md | 40 ++++++++++++-------------- 1 file changed, 19 insertions(+), 21 deletions(-) diff --git a/vizro-ai/docs/pages/user-guides/faq.md b/vizro-ai/docs/pages/user-guides/faq.md index 1414c52d0..fb27a5220 100644 --- a/vizro-ai/docs/pages/user-guides/faq.md +++ b/vizro-ai/docs/pages/user-guides/faq.md @@ -1,4 +1,20 @@ -# How to configure Vizro-AI parameters +# Frequently asked questions + +## Which LLMs are supported by Vizro-AI? +Vizro-AI currently supports OpenAI models as follows: + +- gpt-3.5-turbo-0613 (to be deprecated on June 13, 2024) +- gpt-4-0613 +- gpt-3.5-turbo-1106 (under testing) +- gpt-4-1106-preview (under testing, not suitable for production use) + +These models provide different levels of performance and +cost. In general, the `gpt-3.5-turbo` collection provides the most cost-effective models, +which would be a good starting point for most users. `gpt-4` models are more powerful than `gpt-3` models, e.g. they allow for more tokens per request. You can refer to these models' [capabilities](https://platform.openai.com/docs/models/overview) +and [pricing](https://openai.com/pricing) for more information. + +We are working on supporting more models and more vendors. Please stay tuned! + !!! Warning @@ -10,15 +26,13 @@ Users are also recommended to review the third party API key section of the [disclaimer](../explanation/disclaimer.md) documentation. -## Supported parameters +## What parameters does Vizro-AI support? Currently, Vizro-AI supports the following parameters: - `temperature`: A parameter for tuning the randomness of the output. It is set to 0 by default. We recommend setting it to 0 for Vizro-AI usage, as it's mostly deterministic. -- `model_name`: The name of the model to use. Please refer to the section - [Models currently supported by Vizro-AI](#supported-models) for available - model options. +- `model_name`: The name of the model to use. See above for [models currently supported by Vizro-AI](#which-llms-are-supported-by-vizro-ai) for the models supported. !!! example "Config and construct Vizro-AI" === "python" @@ -30,19 +44,3 @@ Currently, Vizro-AI supports the following parameters: -## Supported models -Vizro-AI currently supports the following LLMs: - -### OpenAI models - -- gpt-3.5-turbo-0613 (to be deprecated on June 13, 2024) -- gpt-4-0613 -- gpt-3.5-turbo-1106 (under testing) -- gpt-4-1106-preview (under testing, not suitable for production use) - -These models provide different levels of performance and -cost. In general, the `gpt-3.5-turbo` collection provides the most cost-effective models, -which would be a good starting point for most users. `gpt-4` models are more powerful than `gpt-3` models, e.g. they allow for more tokens per request. You can refer to these models' [capabilities](https://platform.openai.com/docs/models/overview) -and [pricing](https://openai.com/pricing) for more information. - -We are working on supporting more models and more vendors. Please stay tuned!