Files
2023-08-14 23:54:26 -07:00

51 lines
2.0 KiB
Plaintext

---
title: Azure OpenAI
description: 'Configure Danswer to use GPT models hosted on Azure'
---
Refer to [Model Configs](https://docs.danswer.dev/gen_ai_configs/overview#model-configs) for how to set the
environment variables for your particular deployment.
If you're already familiar with Azure OpenAI, feel free to skip to the
[configuring Danswer](https://docs.danswer.dev/gen_ai_configs/azure#configuring-danswer-to-use-azure-openai-endpoint)
section at the end
## Why use Azure OpenAI
By far the most requested model integration has been Azure OpenAI. As of Aug 2023, GPT-4 is the most capable LLM
available. When combined with the Enterprise grade security and geographical deployment options of Azure, this
becomes a very attractive option for using with Danswer.
## Set up Azure OpenAI Endpoint
As of Aug 2023, Azure OpenAI access is by
[application](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/limited-access) only. This may change
moving forward, please check online for the latest information.
Start by creating the Azure OpenAI Resource
- Search for `Azure OpenAI` service
- Click on **+Create** to create a new Azure OpenAI resource
![AzureResource](/images/gen_ai/AzureResource.png)
## Getting the Model Endpoint Info
Once the resource is created, visit it in **Azure OpenAI Studio**
Select **Chat**
![AzurePlayground](/images/gen_ai/AzurePlayground.png)
Then click on **View Code** to see the connection info which we will configure for Danswer
![AzureViewCode](/images/gen_ai/AzureViewCode.png)
Note the values provided in the sample code (also feel free to try out the code to verify it works)
![AzureSample](/images/gen_ai/AzureSample.png)
## Configuring Danswer to use Azure OpenAI Endpoint
Following the image above, you would configure Danswer with the following environment variables:
```
API_TYPE_OPENAI=azure
API_BASE_OPENAI=https://danswer.openai.azure.com/
API_VERSION_OPENAI=2023-03-15-preview
AZURE_DEPLOYMENT_ID=Danswer
GEN_AI_API_KEY=<your-azure-key> # found below the code section in the above image
```