A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.
There are a number of env vars used when using Azure OpenAI On Your Data in the BYOD endpoint, which are not used when calling the custom endpoint, such as top p and temperature:
Motivation
There are a number of env vars used when using Azure OpenAI On Your Data in the BYOD endpoint, which are not used when calling the custom endpoint, such as top p and temperature:
https://github.com/Azure-Samples/chat-with-your-data-solution-accelerator/blob/54723fe9b13baf1096abff135c67a98fcdf1a2cb/code/create_app.py#L96-L160
These should be added to the custom endpoint, to create a consistent experience when switching between the two endpoints.
Requirements
A list of requirements to consider this feature delivered
Tasks
To be filled in by the engineer picking up the issue