Initial changes for text-embedding-3

Author: pamelafox

app/backend/app.py

@@ -421,8 +421,8 @@ async def setup_clients():
     # Shared by all OpenAI deployments
     OPENAI_HOST = os.getenv("OPENAI_HOST", "azure")
     OPENAI_CHATGPT_MODEL = os.environ["AZURE_OPENAI_CHATGPT_MODEL"]
-    OPENAI_EMB_MODEL = os.getenv("AZURE_OPENAI_EMB_MODEL_NAME", "text-embedding-ada-002")
-    OPENAI_EMB_DIMENSIONS = int(os.getenv("AZURE_OPENAI_EMB_DIMENSIONS") or 1536)
+    OPENAI_EMB_MODEL = os.environ["AZURE_OPENAI_EMB_MODEL_NAME"]
+    OPENAI_EMB_DIMENSIONS = int(os.environ["AZURE_OPENAI_EMB_DIMENSIONS"])
     # Used with Azure OpenAI deployments
     AZURE_OPENAI_SERVICE = os.getenv("AZURE_OPENAI_SERVICE")
     AZURE_OPENAI_GPT4V_DEPLOYMENT = os.environ.get("AZURE_OPENAI_GPT4V_DEPLOYMENT")

docs/deploy_existing.md

@@ -31,8 +31,8 @@ You should set these values before running `azd up`. Once you've set them, retur
 1. Run `azd env set AZURE_OPENAI_CHATGPT_DEPLOYMENT_VERSION {Version string for existing chat deployment}`. Only needed if your chat deployment model version is not the default '0125'. You definitely need to change this if you changed the model.
 1. Run `azd env set AZURE_OPENAI_CHATGPT_DEPLOYMENT_SKU {Name of SKU for existing chat deployment}`. Only needed if your chat deployment SKU is not the default 'Standard', like if it is 'GlobalStandard' instead.
 1. Run `azd env set AZURE_OPENAI_EMB_DEPLOYMENT {Name of existing embedding deployment}`. Only needed if your embeddings deployment is not the default 'embedding'.
-1. Run `azd env set AZURE_OPENAI_EMB_MODEL_NAME {Model name of existing embedding deployment}`. Only needed if your embeddings model is not the default 'text-embedding-ada-002'.
-1. Run `azd env set AZURE_OPENAI_EMB_DIMENSIONS {Dimensions for existing embedding deployment}`. Only needed if your embeddings model is not the default 'text-embedding-ada-002'.
+1. Run `azd env set AZURE_OPENAI_EMB_MODEL_NAME {Model name of existing embedding deployment}`. Only needed if your embeddings model is not the default 'text-embedding-3-large'.
+1. Run `azd env set AZURE_OPENAI_EMB_DIMENSIONS {Dimensions for existing embedding deployment}`. Only needed if your embeddings model is not the default 'text-embedding-3-large'.
 1. Run `azd env set AZURE_OPENAI_EMB_DEPLOYMENT_VERSION {Version string for existing embedding deployment}`. If your embeddings deployment is one of the 'text-embedding-3' models, set this to the number 1.
 1. This project does *not* use keys when authenticating to Azure OpenAI. However, if your Azure OpenAI service must have key access enabled for some reason (like for use by other projects), then run `azd env set AZURE_OPENAI_DISABLE_KEYS false`. The default value is `true` so you should only run the command if you need key access.
 

docs/deploy_features.md

@@ -5,8 +5,8 @@ This document covers optional features that can be enabled in the deployed Azure
 You should typically enable these features before running `azd up`. Once you've set them, return to the [deployment steps](../README.md#deploying).
 
 * [Using different chat completion models](#using-different-chat-completion-models)
-* [Using text-embedding-3 models](#using-text-embedding-3-models)
-* [Enabling GPT-4 Turbo with Vision](#enabling-gpt-4-turbo-with-vision)
+* [Using different embedding models](#using-different-embedding-models)
+* [Enabling GPT vision feature](#enabling-gpt-vision-feature)
 * [Enabling media description with Azure Content Understanding](#enabling-media-description-with-azure-content-understanding)
 * [Enabling client-side chat history](#enabling-client-side-chat-history)
 * [Enabling persistent chat history with Azure Cosmos DB](#enabling-persistent-chat-history-with-azure-cosmos-db)
@@ -121,12 +121,16 @@ This process does *not* delete your previous model deployment. If you want to de
 > [!NOTE]
 > To revert back to a previous model, run the same commands with the previous model name and version.
 
-## Using text-embedding-3 models
+## Using different embedding models
 
-By default, the deployed Azure web app uses the `text-embedding-ada-002` embedding model. If you want to use one of the text-embedding-3 models, you can do so by following these steps:
+By default, the deployed Azure web app uses the `text-embedding-3-large` embedding model. If you want to use a different embeddig model, you can do so by following these steps:
 
 1. Run one of the following commands to set the desired model:
 
+    ```shell
+    azd env set AZURE_OPENAI_EMB_MODEL_NAME text-embedding-ada-002
+    ```
+
     ```shell
     azd env set AZURE_OPENAI_EMB_MODEL_NAME text-embedding-3-small
     ```
@@ -137,32 +141,65 @@ By default, the deployed Azure web app uses the `text-embedding-ada-002` embeddi
 
 2. Specify the desired dimensions of the model: (from 256-3072, model dependent)
 
+    Default dimensions for text-embedding-ada-002
+
+    ```shell
+    azd env set AZURE_OPENAI_EMB_DIMENSIONS 1536
+    ```
+
+    Default dimensions for text-embedding-3-small
+
     ```shell
-    azd env set AZURE_OPENAI_EMB_DIMENSIONS 256
+    azd env set AZURE_OPENAI_EMB_DIMENSIONS 1536
     ```
 
-3. Set the model version to "1" (the only version as of March 2024):
+    Default dimensions for text-embedding-3-large
+
+    ```shell
+    azd env set AZURE_OPENAI_EMB_DIMENSIONS 3072
+    ```
+
+3. Set the model version, depending on the model you are using:
+
+    For text-embedding-ada-002:
+
+    ```shell
+    azd env set AZURE_OPENAI_EMB_DEPLOYMENT_VERSION 2
+    ```
+
+    For text-embedding-3-small and text-embedding-3-large:
 
     ```shell
     azd env set AZURE_OPENAI_EMB_DEPLOYMENT_VERSION 1
     ```
 
-4. When prompted during `azd up`, make sure to select a region for the OpenAI resource group location that supports the text-embedding-3 models. There are [limited regions available](https://learn.microsoft.com/azure/ai-services/openai/concepts/models#embeddings-models).
+4. To set the embedding model deployment SKU name, run this command with [the desired SKU name](https://learn.microsoft.com/azure/ai-services/openai/how-to/deployment-types#deployment-types).
+
+    For GlobalStandard:
+
+    ```bash
+    azd env set AZURE_OPENAI_EMB_DEPLOYMENT_SKU GlobalStandard
+    ```
+
+    For Standard:
+
+    ```bash
+    azd env set AZURE_OPENAI_EMB_DEPLOYMENT_SKU Standard
+    ```
+
+5. When prompted during `azd up`, make sure to select a region for the OpenAI resource group location that supports the desired embedding model and deployment SKU. There are [limited regions available](https://learn.microsoft.com/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#models-by-deployment-type).
 
 If you have already deployed:
 
 * You'll need to change the deployment name by running `azd env set AZURE_OPENAI_EMB_DEPLOYMENT <new-deployment-name>`
 * You'll need to create a new index, and re-index all of the data using the new model. You can either delete the current index in the Azure Portal, or create an index with a different name by running `azd env set AZURE_SEARCH_INDEX new-index-name`. When you next run `azd up`, the new index will be created and the data will be re-indexed.
 * If your OpenAI resource is not in one of the supported regions, you should delete `openAiResourceGroupLocation` from `.azure/YOUR-ENV-NAME/config.json`. When running `azd up`, you will be prompted to select a new region.
 
-> ![NOTE]
-> The text-embedding-3 models are not currently supported by the integrated vectorization feature.
-
-## Enabling GPT-4 Turbo with Vision
+## Enabling GPT vision feature
 
 ⚠️ This feature is not currently compatible with [integrated vectorization](#enabling-integrated-vectorization).
 
-This section covers the integration of GPT-4 Vision with Azure AI Search. Learn how to enhance your search capabilities with the power of image and text indexing, enabling advanced search functionalities over diverse document types. For a detailed guide on setup and usage, visit our [Enabling GPT-4 Turbo with Vision](gpt4v.md) page.
+This section covers the integration of GPT vision models with Azure AI Search. Learn how to enhance your search capabilities with the power of image and text indexing, enabling advanced search functionalities over diverse document types. For a detailed guide on setup and usage, visit our page on [Using GPT vision model with RAG approach](gpt4v.md).
 
 ## Enabling media description with Azure Content Understanding
 

docs/gpt4v.md

@@ -21,10 +21,10 @@ For more details on how this feature works, read [this blog post](https://techco
 
 * Create a [AI Vision account in Azure Portal first](https://ms.portal.azure.com/#create/Microsoft.CognitiveServicesComputerVision), so that you can agree to the Responsible AI terms for that resource. You can delete that account after agreeing.
 * The ability to deploy a gpt-4o model in the [supported regions](https://learn.microsoft.com/azure/ai-services/openai/concepts/models#standard-deployment-model-availability). If you're not sure, try to create a gpt-4o deployment from your Azure OpenAI deployments page.
-* Ensure that you can deploy the Azure OpenAI resource group in [a region where all required components are available](https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models#model-summary-table-and-region-availability):
+* Ensure that you can deploy the Azure OpenAI resource group in [a region and deployment SKU where all required components are available](https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models#model-summary-table-and-region-availability):
   * Azure OpenAI models
     * gpt-4o-mini
-    * text-embedding-ada-002
+    * text-embedding-3-large
     * gpt-4o (for vision/evaluation features)
   * [Azure AI Vision](https://learn.microsoft.com/azure/ai-services/computer-vision/)
 

infra/main.bicep

@@ -146,12 +146,12 @@ param embeddingDeploymentSkuName string = ''
 param embeddingDeploymentCapacity int = 0
 param embeddingDimensions int = 0
 var embedding = {
-  modelName: !empty(embeddingModelName) ? embeddingModelName : 'text-embedding-ada-002'
-  deploymentName: !empty(embeddingDeploymentName) ? embeddingDeploymentName : 'embedding'
-  deploymentVersion: !empty(embeddingDeploymentVersion) ? embeddingDeploymentVersion : '2'
-  deploymentSkuName: !empty(embeddingDeploymentSkuName) ? embeddingDeploymentSkuName : 'Standard'
+  modelName: !empty(embeddingModelName) ? embeddingModelName : 'text-embedding-3-large'
+  deploymentName: !empty(embeddingDeploymentName) ? embeddingDeploymentName : 'text-embedding-3-large'
+  deploymentVersion: !empty(embeddingDeploymentVersion) ? embeddingDeploymentVersion : '1'
+  deploymentSkuName: !empty(embeddingDeploymentSkuName) ? embeddingDeploymentSkuName : 'GlobalStandard'
   deploymentCapacity: embeddingDeploymentCapacity != 0 ? embeddingDeploymentCapacity : 30
-  dimensions: embeddingDimensions != 0 ? embeddingDimensions : 1536
+  dimensions: embeddingDimensions != 0 ? embeddingDimensions : 3072
 }
 
 param gpt4vModelName string = ''

tests/conftest.py

@@ -95,7 +95,7 @@ async def mock_acreate(*args, **kwargs):
                     object="embedding",
                 )
             ],
-            model="text-embedding-ada-002",
+            model="text-embedding-3-large",
             usage=Usage(prompt_tokens=8, total_tokens=8),
         )
 

tests/test_prepdocs.py

@@ -51,7 +51,7 @@ async def mock_create_client(*args, **kwargs):
                             object="embedding",
                         )
                     ],
-                    model="text-embedding-ada-002",
+                    model="text-embedding-3-large",
                     usage=Usage(prompt_tokens=8, total_tokens=8),
                 )
             )

tests/test_searchmanager.py

@@ -258,7 +258,7 @@ async def mock_create_client(*args, **kwargs):
                             object="embedding",
                         )
                     ],
-                    model="text-embedding-ada-002",
+                    model="text-embedding-3-large",
                     usage=Usage(prompt_tokens=8, total_tokens=8),
                 )
             )

tests/test_upload.py

@@ -75,7 +75,7 @@ async def mock_create_client(self, *args, **kwargs):
                             object="embedding",
                         )
                     ],
-                    model="text-embedding-ada-002",
+                    model="text-embedding-3-large",
                     usage=Usage(prompt_tokens=8, total_tokens=8),
                 )
             )