documentation

Azure · Dec 30, 2024 · f9d9fe7 · f9d9fe7
1 parent fcfb1d0
commit f9d9fe7
Show file tree

Hide file tree

Showing 4 changed files with 29 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -136,6 +136,9 @@ Upload your documents to the 'documents' folder located in the storage account.
 
  ![storage_sample](media/readme-storage_sample.png)
 
+> [!Note]
+> If you want to upload documents for ingestion into the GPT-RAG storage account, you must have the **Storage Blob Data Contributor** role assigned in Azure Entra ID.
+
 **Done! Basic deployment is completed.**
 
 **Recommended**: [Add app authentication](https://learn.microsoft.com/en-us/azure/app-service/scenario-secure-app-authentication-app-service). [Watch this quick tutorial](https://youtu.be/sA-an25jMB4) for step-by-step guidance.
@@ -227,6 +230,9 @@ azd deploy
    
 **Done! Zero trust deployment is completed.**
 
+> [!Note]
+> If you want to upload documents for ingestion into the GPT-RAG storage account, you must have the **Storage Blob Data Contributor** role assigned in Azure Entra ID.
+
 **Recommended**: [Add app authentication](https://learn.microsoft.com/en-us/azure/app-service/scenario-secure-app-authentication-app-service). [Watch this quick tutorial](https://youtu.be/sA-an25jMB4) for step-by-step guidance.
 
 ## How to?

diff --git a/docs/CUSTOMIZATIONS.md b/docs/CUSTOMIZATIONS.md
@@ -6,7 +6,8 @@ On this page, you will find some options to configure your deployment:
 - [Configuring AOAI content filters](#configuring-aoai-content-filters)
 - [Setting Custom Names for Resources](#defining-resources-names)
 - [Applying Tags to All Resources](#adding-tags-for-all-resources)
-- [Bringing Your Own Resources](#bring-your-own-resources)- [Accessing Data Ingest function using AI Search Managed Identity](#accessing-the-data-ingest-function-from-ai-search-using-a-managed-identity)
+- [Bringing Your Own Resources](#bring-your-own-resources)
+- [Accessing Data Ingest function using AI Search Managed Identity](#accessing-the-data-ingest-function-from-ai-search-using-a-managed-identity)
 - [Extending Enteprise RAG components](#extending-solution-components)
 
 <!-- - [Filter Files with AI Search Using Security Trimming](#Filter-Files-with-AI-Search-Using-Security-Trimming) -->

diff --git a/docs/CUSTOMIZATIONS_BYOR.md b/docs/CUSTOMIZATIONS_BYOR.md
@@ -94,6 +94,15 @@ Additionally, the original resource must have two deployments, one for a GPT mod
 
 Ensure the embeddings model is **text-embedding-3-large** version 1, with the deployment named **text-embedding**.
 
+If you're using a different name for the Embedding model, you'll need to set the corresponding environment variables as shown in the table below.
+
+| Item                       | Environment Variable Name               |
+|----------------------------|-----------------------------------------|
+| Embeddings Model Name      | AZURE_EMBEDDINGS_MODEL_NAME             |
+| Embeddings Model Version   | AZURE_EMBEDDINGS_VERSION                |
+| Embeddings Deployment Name | AZURE_EMBEDDINGS_DEPLOYMENT_NAME        |
+| Embeddings Vector Size     | AZURE_EMBEDDINGS_VECTOR_SIZE            |
+
 The default GPT model is **gpt-4o** version **2024-11-20** and the default deployment name is **chat**. If you're using the pre-created service with these default settings, no further modifications are required.
 
 However, if you're using a different name for the GPT, or a different model, you'll need to set the corresponding environment variables as shown in the table below.
@@ -102,10 +111,12 @@ However, if you're using a different name for the GPT, or a different model, you
 |----------------------------|-----------------------------------------|
 | GPT Deployment Name        | AZURE_CHAT_GPT_DEPLOYMENT_NAME          |
 | GPT Model Name             | AZURE_CHAT_GPT_MODEL_NAME               |
+| GPT Model Version          | AZURE_CHAT_GPT_MODEL_VERSION            |
 
 To set these environment variables, use the `azd env set` command as described earlier.
 
 For instance, to inform the name of the GPT deployment, you would update the `AZURE_CHAT_GPT_DEPLOYMENT_NAME` variable like this:
+
 `azd env set AZURE_CHAT_GPT_DEPLOYMENT_NAME my-gpt-deployment-name`
 
 ### CosmosDB

diff --git a/docs/GUIDE.md b/docs/GUIDE.md
@@ -28,8 +28,9 @@
    - [4.6 Entra Authentication](#configuring-entra-authentication)
    - [4.7 Authorization Setup](#configuring-authorization)  
    - [4.8 Sharepoint Indexing](#sharepoint-setup)
-   - [4.9 Search Trimming](#search-trimming)     
-   - [4.10 Setting Up Git Repos](#setting-up-git-repos)
+   - [4.9 Search Trimming](#search-trimming)
+   - [4.10 Bringing Your Own Resources](#bring-your-own-resources)   
+   - [4.11 Setting Up Git Repos](#setting-up-git-repos)
 5. [**Reference**](reference)
    - [5.1 Azure Resources](#azure-resources)
 6. [**Troubleshooting**](#troubleshooting)
@@ -645,6 +646,9 @@ azd deploy
 
 🎉 **Congratulations! Your Zero Trust deployment is now complete.**
 
+> [!Note]
+> If you want to upload documents for ingestion into the GPT-RAG storage account, you must have the **Storage Blob Data Contributor** role assigned in Azure Entra ID.
+
 > [!Note]  
 > After the initial deployment, you may choose to customize or update specific features, such as adjusting prompts, adding a logo to the frontend, testing different chunking strategies, or configuring a custom orchestration strategy like NL2SQL. For detailed guidance on these optional customizations, refer to the deployment section in each component's repository. [Orchestrator](https://github.com/azure/gpt-rag-agentic), [Front-end](https://github.com/azure/gpt-rag-frontend), [Data Ingestion](https://github.com/Azure/gpt-rag-ingestion).
 
@@ -972,6 +976,10 @@ The SharePoint connector indexes and purges files using scheduled Azure Function
 
 This customization is particularly valuable in scenarios where sensitive documents need to be accessed by specific groups or individuals within an organization. With this feature you can ensure that AI Search returns results tailored to each user’s access (no RBAC permissions), please take a look at the [Filter Files with AI Search Using Security Trimming](CUSTOMIZATIONS_SEARCH_TRIMMING.md) page.
 
+## Bring Your Own Resources
+
+In some cases, you may want to use one or more pre-existing resources in your subscription instead of creating new ones. Our Bicep template allows you to do this. For detailed instructions on how this can be achieved, please take a look at the [Bring Your Own Resources](CUSTOMIZATIONS_BYOR.md) page.
+
 ## Setting Up Git Repos
 
 The GPT-RAG Solution Accelerator comprises four Git repositories, each housing the code for specific application components. Whether you're using GitHub, Azure Repos in Azure DevOps, or another Git service, this section outlines the organization of the codebase and provides instructions for integrating it into your own Git repositories. You can incorporate the Solution Accelerator's code into your Git repositories either by using the repositories as templates or by forking and then creating pull requests in case you want to contribute to the GPT-RAG repo.