diff --git a/gen_ai_configs/azure.mdx b/gen_ai_configs/azure.mdx index 14f3fcf..a6f5221 100644 --- a/gen_ai_configs/azure.mdx +++ b/gen_ai_configs/azure.mdx @@ -10,37 +10,49 @@ 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. +1. Access the Azure Portal and search for "Azure OpenAI Service" -## 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. +![Azure OpenAI Service](/images/gen_ai/azure/1_azure.png) -Start by creating the Azure OpenAI Resource -- Search for `Azure OpenAI` service -- Click on **+Create** to create a new Azure OpenAI resource +2. Click "Create a resource" to begin setup -![AzureResource](/images/gen_ai/AzureResource.png) +![Create a resource](/images/gen_ai/azure/2_create.png) -## Getting the Model Endpoint Info -Once the resource is created, visit it in **Azure OpenAI Studio** -Select **Chat** +3. Create a new resource group and complete the required form fields -![AzurePlayground](/images/gen_ai/AzurePlayground.png) +![Create resource group](/images/gen_ai/azure/3_createopenai.png) -Then click on **View Code** to see the connection info which we will configure for Danswer +4. Wait for the deployment to complete, then navigate to Azure OpenAI Studio at https://oai.azure.com/ -![AzureViewCode](/images/gen_ai/AzureViewCode.png) +5. In the studio, access the chat panel -Note the values provided in the sample code (also feel free to try out the code to verify it works) +![Chat panel](/images/gen_ai/azure/4_chatplayground.png) -![AzureSample](/images/gen_ai/AzureSample.png) +6. Create a new deployment by selecting a chat completion model -## Configuring Danswer to use Azure OpenAI Endpoint -Following the image above, you would configure Danswer with the following values: +![Create deployment](/images/gen_ai/azure/5_model.png) +![Select model](/images/gen_ai/azure/6_deploy.png) -![AzureLLMProvider](/images/gen_ai/AzureLLMProvider.png) +7. Configure your settings and deploy the model + +8. Test your configuration using the chat bar on the right side of the screen + +![Validate configuration](/images/gen_ai/azure/7_validate.png) + +9. After validation, click "View Code" to access your credentials + +![View Code](/images/gen_ai/azure/8_secrets.png) + +10. Locate your credentials: + - API version: The string after `?api-version=` + - API Base: The Endpoint value + - API Key: The obfuscated key + +![Credentials](/images/gen_ai/azure/9_version.png) + +With these steps completed, you'll have successfully set up and configured Azure OpenAI for use with Danswer. + + +Your Danswer configuration should look like the following: + +![Danswer config](/images/gen_ai/azure/10_danswer.png) \ No newline at end of file diff --git a/images/gen_ai/azure/10_danswer.png b/images/gen_ai/azure/10_danswer.png new file mode 100644 index 0000000..a6f2534 Binary files /dev/null and b/images/gen_ai/azure/10_danswer.png differ diff --git a/production/aws/eks.mdx b/production/aws/eks.mdx index 457cfa4..2f76200 100644 --- a/production/aws/eks.mdx +++ b/production/aws/eks.mdx @@ -127,4 +127,4 @@ kubectl -n danswer get pods | grep api-server | awk '{print $1}' | xargs -I {} k You can navigate find the nginx load balancer by running the following command and then navigating to the url provided. ```shell kubectl get svc -n danswer | grep nginx-service | awk '{print $4}' -``` +``` \ No newline at end of file