Merge branch 'main' into feat-chat-history-cosmos

Author: pamelafox

.azdo/pipelines/azure-dev.yml

@@ -101,6 +101,7 @@ steps:
       AZURE_SPEECH_SERVICE_RESOURCE_GROUP: $(AZURE_SPEECH_SERVICE_RESOURCE_GROUP)
       AZURE_SPEECH_SERVICE_LOCATION: $(AZURE_SPEECH_SERVICE_LOCATION)
       AZURE_SPEECH_SERVICE_SKU: $(AZURE_SPEECH_SERVICE_SKU)
+      AZURE_SPEECH_SERVICE_VOICE: $(AZURE_SPEECH_SERVICE_VOICE)
       AZURE_KEY_VAULT_NAME: $(AZURE_KEY_VAULT_NAME)
       AZURE_USE_AUTHENTICATION: $(AZURE_USE_AUTHENTICATION)
       AZURE_ENFORCE_ACCESS_CONTROL: $(AZURE_ENFORCE_ACCESS_CONTROL)

.github/workflows/azure-dev.yml

@@ -32,13 +32,14 @@ jobs:
       AZURE_OPENAI_SERVICE: ${{ vars.AZURE_OPENAI_SERVICE }}
       AZURE_OPENAI_API_VERSION: ${{ vars.AZURE_OPENAI_API_VERSION }}
       AZURE_OPENAI_RESOURCE_GROUP: ${{ vars.AZURE_OPENAI_RESOURCE_GROUP }}
+      AZURE_DOCUMENTINTELLIGENCE_SERVICE: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_SERVICE }}
+      AZURE_DOCUMENTINTELLIGENCE_RESOURCE_GROUP: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_RESOURCE_GROUP }}
+      AZURE_DOCUMENTINTELLIGENCE_SKU: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_SKU }}
+      AZURE_DOCUMENTINTELLIGENCE_LOCATION: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_LOCATION }}
       AZURE_COMPUTER_VISION_SERVICE: ${{ vars.AZURE_COMPUTER_VISION_SERVICE }}
       AZURE_COMPUTER_VISION_RESOURCE_GROUP: ${{ vars.AZURE_COMPUTER_VISION_RESOURCE_GROUP }}
       AZURE_COMPUTER_VISION_LOCATION: ${{ vars.AZURE_COMPUTER_VISION_LOCATION }}
       AZURE_COMPUTER_VISION_SKU: ${{ vars.AZURE_COMPUTER_VISION_SKU }}
-      AZURE_FORMRECOGNIZER_SERVICE: ${{ vars.AZURE_FORMRECOGNIZER_SERVICE }}
-      AZURE_FORMRECOGNIZER_RESOURCE_GROUP: ${{ vars.AZURE_FORMRECOGNIZER_RESOURCE_GROUP }}
-      AZURE_FORMRECOGNIZER_SKU: ${{ vars.AZURE_FORMRECOGNIZER_SKU }}
       AZURE_SEARCH_INDEX: ${{ vars.AZURE_SEARCH_INDEX }}
       AZURE_SEARCH_SERVICE: ${{ vars.AZURE_SEARCH_SERVICE }}
       AZURE_SEARCH_SERVICE_RESOURCE_GROUP: ${{ vars.AZURE_SEARCH_SERVICE_RESOURCE_GROUP }}
@@ -62,6 +63,11 @@ jobs:
       AZURE_OPENAI_EMB_DEPLOYMENT_CAPACITY: ${{ vars.AZURE_OPENAI_EMB_DEPLOYMENT_CAPACITY }}
       AZURE_OPENAI_EMB_DEPLOYMENT_VERSION: ${{ vars.AZURE_OPENAI_EMB_DEPLOYMENT_VERSION }}
       AZURE_OPENAI_EMB_DIMENSIONS: ${{ vars.AZURE_OPENAI_EMB_DIMENSIONS }}
+      AZURE_OPENAI_GPT4V_MODEL: ${{ vars.AZURE_OPENAI_GPT4V_MODEL }}
+      AZURE_OPENAI_GPT4V_DEPLOYMENT: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT }}
+      AZURE_OPENAI_GPT4V_DEPLOYMENT_CAPACITY: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT_CAPACITY }}
+      AZURE_OPENAI_GPT4V_DEPLOYMENT_VERSION: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT_VERSION }}
+      AZURE_OPENAI_GPT4V_DEPLOYMENT_SKU: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT_SKU }}
       OPENAI_HOST: ${{ vars.OPENAI_HOST }}
       OPENAI_API_KEY: ${{ vars.OPENAI_API_KEY }}
       OPENAI_ORGANIZATION: ${{ vars.OPENAI_ORGANIZATION }}
@@ -81,6 +87,7 @@ jobs:
       AZURE_SPEECH_SERVICE_RESOURCE_GROUP: ${{ vars.AZURE_SPEECH_RESOURCE_GROUP }}
       AZURE_SPEECH_SERVICE_LOCATION: ${{ vars.AZURE_SPEECH_SERVICE_LOCATION }}
       AZURE_SPEECH_SERVICE_SKU: ${{ vars.AZURE_SPEECH_SERVICE_SKU }}
+      AZURE_SPEECH_SERVICE_VOICE: ${{ vars.AZURE_SPEECH_SERVICE_VOICE }}
       AZURE_KEY_VAULT_NAME: ${{ vars.AZURE_KEY_VAULT_NAME }}
       AZURE_USE_AUTHENTICATION: ${{ vars.AZURE_USE_AUTHENTICATION }}
       AZURE_ENFORCE_ACCESS_CONTROL: ${{ vars.AZURE_ENFORCE_ACCESS_CONTROL }}

.github/workflows/python-test.yaml

@@ -26,13 +26,21 @@ jobs:
       matrix:
         os: ["ubuntu-20.04", "windows-latest"]
         python_version: ["3.9", "3.10", "3.11", "3.12"]
+    env:
+      UV_SYSTEM_PYTHON: 1
     steps:
         - uses: actions/checkout@v4
         - name: Setup python
           uses: actions/setup-python@v5
           with:
             python-version: ${{ matrix.python_version }}
             architecture: x64
+        - name: Install uv
+          uses: astral-sh/setup-uv@v3
+          with:
+            enable-cache: true
+            version: "0.4.20"
+            cache-dependency-glob: "requirements**.txt"
         - name: Setup node
           uses: actions/setup-node@v4
           with:
@@ -44,8 +52,7 @@ jobs:
             npm run build
         - name: Install dependencies
           run: |
-            python -m pip install --upgrade pip
-            pip install -r requirements-dev.txt
+            uv pip install -r requirements-dev.txt
         - name: Lint with ruff
           run: ruff check .
         - name: Check types with mypy

.pre-commit-config.yaml

@@ -1,17 +1,17 @@
 exclude: '^tests/snapshots/'
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
     -   id: check-yaml
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.14
+    rev: v0.7.2
     hooks:
     -   id: ruff
 -   repo: https://github.com/psf/black
-    rev: 24.1.0
+    rev: 24.10.0
     hooks:
     -   id: black
 -   repo: https://github.com/pre-commit/mirrors-prettier

.vscode/launch.json

@@ -5,7 +5,7 @@
     "version": "0.2.0",
     "configurations": [
         {
-            "name": "Python: Quart",
+            "name": "Backend (Python)",
             "type": "debugpy",
             "request": "launch",
             "module": "quart",
@@ -22,18 +22,17 @@
                 "-p 50505"
             ],
             "console": "integratedTerminal",
-            "justMyCode": false,
-            "envFile": "${input:dotEnvFilePath}",
+            "justMyCode": false
         },
         {
-            "name": "Frontend: watch",
+            "name": "Frontend",
             "type": "node-terminal",
             "request": "launch",
             "command": "npm run dev",
             "cwd": "${workspaceFolder}/app/frontend",
         },
         {
-            "name": "Python: Debug Tests",
+            "name": "Tests (Python)",
             "type": "debugpy",
             "request": "launch",
             "program": "${file}",
@@ -42,11 +41,11 @@
             "justMyCode": false
           }
     ],
-    "inputs": [
+    "compounds": [
         {
-            "id": "dotEnvFilePath",
-            "type": "command",
-            "command": "azure-dev.commands.getDotEnvFilePath"
+          "name": "Frontend & Backend",
+          "configurations": ["Backend (Python)", "Frontend"],
+          "stopAll": true
         }
     ]
 }

.vscode/tasks.json

@@ -3,14 +3,6 @@
     "tasks": [
         {
             "label": "Start App",
-            "type": "dotenv",
-            "targetTasks": [
-                "Start App (Script)"
-            ],
-            "file": "${input:dotEnvFilePath}"
-        },
-        {
-            "label": "Start App (Script)",
             "type": "shell",
             "command": "${workspaceFolder}/app/start.sh",
             "windows": {
@@ -24,12 +16,5 @@
             },
             "problemMatcher": []
         }
-    ],
-    "inputs": [
-        {
-            "id": "dotEnvFilePath",
-            "type": "command",
-            "command": "azure-dev.commands.getDotEnvFilePath"
-        }
     ]
-}
+}

README.md

@@ -1,4 +1,25 @@
-# ChatGPT-like app with your data using Azure OpenAI and Azure AI Search (Python)
+<!--
+---
+name: RAG chat app with your data (Python)
+description: Chat with your domain data using Azure OpenAI and Azure AI Search.
+languages:
+- python
+- typescript
+- bicep
+- azdeveloper
+products:
+- azure-openai
+- azure-cognitive-search
+- azure-app-service
+- azure
+page_type: sample
+urlFragment: azure-search-openai-demo
+---
+-->
+
+# RAG chat app with Azure OpenAI and Azure AI Search (Python)
+
+This solution creates a ChatGPT-like frontend experience over your own documents using RAG (Retrieval Augmented Generation). It uses Azure OpenAI Service to access GPT models, and Azure AI Search for data indexing and retrieval.
 
 This solution's backend is written in Python. There are also [**JavaScript**](https://aka.ms/azai/js/code), [**.NET**](https://aka.ms/azai/net/code), and [**Java**](https://aka.ms/azai/java/code) samples based on this one. Learn more about [developing AI apps using Azure AI Services](https://aka.ms/azai).
 
@@ -65,8 +86,8 @@ The repo includes sample data so it's ready to try end to end. In this sample ap
 Pricing varies per region and usage, so it isn't possible to predict exact costs for your usage.
 However, you can try the [Azure pricing calculator](https://azure.com/e/a87a169b256e43c089015fda8182ca87) for the resources below.
 
-- Azure App Service: Basic Tier with 1 CPU core, 1.75 GB RAM. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/app-service/linux/)
-- Azure Container Apps: Only provisioned if you deploy to Azure Container Apps following [the ACA deployment guide](docs/azure_container_apps.md). Consumption plan with 1 CPU core, 2.0 GB RAM. Pricing with Pay-as-You-Go. [Pricing](https://azure.microsoft.com/pricing/details/container-apps/)
+- Azure Container Apps: Default host for app deployment as of 10/28/2024. See more details in [the ACA deployment guide](docs/azure_container_apps.md). Consumption plan with 1 CPU core, 2.0 GB RAM. Pricing with Pay-as-You-Go. [Pricing](https://azure.microsoft.com/pricing/details/container-apps/)
+- Azure App Service: Only provisioned if you deploy to Azure App Service following [the App Service deployment guide](docs/azure_app_service.md).  Basic Tier with 1 CPU core, 1.75 GB RAM. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/app-service/linux/)
 - Azure OpenAI: Standard tier, GPT and Ada models. Pricing per 1K tokens used, and at least 1K tokens are used per question. [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/)
 - Azure AI Document Intelligence: SO (Standard) tier using pre-built layout. Pricing per document page, sample documents have 261 pages total. [Pricing](https://azure.microsoft.com/pricing/details/form-recognizer/)
 - Azure AI Search: Basic tier, 1 replica, free level of semantic search. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/search/)
@@ -128,7 +149,7 @@ A related option is VS Code Dev Containers, which will open the project in your
 
 ## Deploying
 
-The steps below will provision Azure resources and deploy the application code to Azure App Service. To deploy to Azure Container Apps instead, follow [the container apps deployment guide](docs/azure_container_apps.md).
+The steps below will provision Azure resources and deploy the application code to Azure Container Apps. To deploy to Azure App Service instead, follow [the app service deployment guide](docs/azure_app_service.md).
 
 1. Login to your Azure account:
 
@@ -137,6 +158,7 @@ The steps below will provision Azure resources and deploy the application code t
     ```
 
     For GitHub Codespaces users, if the previous command fails, try:
+
    ```shell
     azd auth login --use-device-code
     ```
@@ -158,7 +180,7 @@ It will look like the following:
 
 !['Output from running azd up'](docs/images/endpoint.png)
 
-> NOTE: It may take 5-10 minutes after you see 'SUCCESS' for the application to be fully deployed. If you see a "Python Developer" welcome screen or an error page, then wait a bit and refresh the page. See [guide on debugging App Service deployments](docs/appservice.md).
+> NOTE: It may take 5-10 minutes after you see 'SUCCESS' for the application to be fully deployed. If you see a "Python Developer" welcome screen or an error page, then wait a bit and refresh the page.
 
 ### Deploying again
 
@@ -262,16 +284,16 @@ Here are the most common failure scenarios and solutions:
 
 1. You see `CERTIFICATE_VERIFY_FAILED` when the `prepdocs.py` script runs. That's typically due to incorrect SSL certificates setup on your machine. Try the suggestions in this [StackOverflow answer](https://stackoverflow.com/questions/35569042/ssl-certificate-verify-failed-with-python3/43855394#43855394).
 
-1. After running `azd up` and visiting the website, you see a '404 Not Found' in the browser. Wait 10 minutes and try again, as it might be still starting up. Then try running `azd deploy` and wait again. If you still encounter errors with the deployed app, consult the [guide on debugging App Service deployments](docs/appservice.md). Please file an issue if the logs don't help you resolve the error.
+1. After running `azd up` and visiting the website, you see a '404 Not Found' in the browser. Wait 10 minutes and try again, as it might be still starting up. Then try running `azd deploy` and wait again. If you still encounter errors with the deployed app and are deploying to App Service, consult the [guide on debugging App Service deployments](docs/appservice.md). Please file an issue if the logs don't help you resolve the error.
 
 ### Resources
 
 - [Additional documentation for this app](docs/README.md)
-- [📖 Revolutionize your Enterprise Data with ChatGPT: Next-gen Apps w/ Azure OpenAI and AI Search](https://aka.ms/entgptsearchblog)
+- [📖 Revolutionize your Enterprise Data with ChatGPT: Next-gen Apps w/ Azure OpenAI and AI Search](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/revolutionize-your-enterprise-data-with-chatgpt-next-gen-apps-w-azure-openai-and/3762087)
 - [📖 Azure AI Search](https://learn.microsoft.com/azure/search/search-what-is-azure-search)
 - [📖 Azure OpenAI Service](https://learn.microsoft.com/azure/cognitive-services/openai/overview)
 - [📖 Comparing Azure OpenAI and OpenAI](https://learn.microsoft.com/azure/cognitive-services/openai/overview#comparing-azure-openai-and-openai/)
-- [📖 Access Control in Generative AI applications with Azure Cognitive Search](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/access-control-in-generative-ai-applications-with-azure/ba-p/3956408)
+- [📖 Access Control in Generative AI applications with Azure AI Search](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/access-control-in-generative-ai-applications-with-azure-ai-search/3956408)
 - [📺 Quickly build and deploy OpenAI apps on Azure, infused with your own data](https://www.youtube.com/watch?v=j8i-OM5kwiY)
 - [📺 AI Chat App Hack series](https://www.youtube.com/playlist?list=PL5lwDBUC0ag6_dGZst5m3G72ewfwXLcXV)
 

SECURITY.md

@@ -38,4 +38,4 @@ We prefer all communications to be in English.
 
 Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://www.microsoft.com/msrc/cvd).
 
-<!-- END MICROSOFT SECURITY.MD BLOCK -->
+<!-- END MICROSOFT SECURITY.MD BLOCK -->

app/backend/app.py

@@ -429,6 +429,8 @@ async def setup_clients():
     )
     AZURE_OPENAI_EMB_DEPLOYMENT = os.getenv("AZURE_OPENAI_EMB_DEPLOYMENT") if OPENAI_HOST.startswith("azure") else None
     AZURE_OPENAI_CUSTOM_URL = os.getenv("AZURE_OPENAI_CUSTOM_URL")
+    # https://learn.microsoft.com/azure/ai-services/openai/api-version-deprecation#latest-ga-api-release
+    AZURE_OPENAI_API_VERSION = os.getenv("AZURE_OPENAI_API_VERSION") or "2024-06-01"
     AZURE_VISION_ENDPOINT = os.getenv("AZURE_VISION_ENDPOINT", "")
     # Used only with non-Azure OpenAI deployments
     OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
@@ -453,7 +455,7 @@ async def setup_clients():
 
     AZURE_SPEECH_SERVICE_ID = os.getenv("AZURE_SPEECH_SERVICE_ID")
     AZURE_SPEECH_SERVICE_LOCATION = os.getenv("AZURE_SPEECH_SERVICE_LOCATION")
-    AZURE_SPEECH_VOICE = os.getenv("AZURE_SPEECH_VOICE", "en-US-AndrewMultilingualNeural")
+    AZURE_SPEECH_SERVICE_VOICE = os.getenv("AZURE_SPEECH_SERVICE_VOICE") or "en-US-AndrewMultilingualNeural"
 
     USE_GPT4V = os.getenv("USE_GPT4V", "").lower() == "true"
     USE_USER_UPLOAD = os.getenv("USE_USER_UPLOAD", "").lower() == "true"
@@ -560,6 +562,7 @@ async def setup_clients():
             openai_custom_url=AZURE_OPENAI_CUSTOM_URL,
             openai_deployment=AZURE_OPENAI_EMB_DEPLOYMENT,
             openai_dimensions=OPENAI_EMB_DIMENSIONS,
+            openai_api_version=AZURE_OPENAI_API_VERSION,
             openai_key=clean_key_if_exists(OPENAI_API_KEY),
             openai_org=OPENAI_ORGANIZATION,
             disable_vectors=os.getenv("USE_VECTORS", "").lower() == "false",
@@ -580,12 +583,11 @@ async def setup_clients():
             raise ValueError("Azure speech resource not configured correctly, missing AZURE_SPEECH_SERVICE_LOCATION")
         current_app.config[CONFIG_SPEECH_SERVICE_ID] = AZURE_SPEECH_SERVICE_ID
         current_app.config[CONFIG_SPEECH_SERVICE_LOCATION] = AZURE_SPEECH_SERVICE_LOCATION
-        current_app.config[CONFIG_SPEECH_SERVICE_VOICE] = AZURE_SPEECH_VOICE
+        current_app.config[CONFIG_SPEECH_SERVICE_VOICE] = AZURE_SPEECH_SERVICE_VOICE
         # Wait until token is needed to fetch for the first time
         current_app.config[CONFIG_SPEECH_SERVICE_TOKEN] = None
 
     if OPENAI_HOST.startswith("azure"):
-        api_version = os.getenv("AZURE_OPENAI_API_VERSION") or "2024-03-01-preview"
         if OPENAI_HOST == "azure_custom":
             current_app.logger.info("OPENAI_HOST is azure_custom, setting up Azure OpenAI custom client")
             if not AZURE_OPENAI_CUSTOM_URL:
@@ -598,12 +600,14 @@ async def setup_clients():
             endpoint = f"https://{AZURE_OPENAI_SERVICE}.openai.azure.com"
         if api_key := os.getenv("AZURE_OPENAI_API_KEY_OVERRIDE"):
             current_app.logger.info("AZURE_OPENAI_API_KEY_OVERRIDE found, using as api_key for Azure OpenAI client")
-            openai_client = AsyncAzureOpenAI(api_version=api_version, azure_endpoint=endpoint, api_key=api_key)
+            openai_client = AsyncAzureOpenAI(
+                api_version=AZURE_OPENAI_API_VERSION, azure_endpoint=endpoint, api_key=api_key
+            )
         else:
             current_app.logger.info("Using Azure credential (passwordless authentication) for Azure OpenAI client")
             token_provider = get_bearer_token_provider(azure_credential, "https://cognitiveservices.azure.com/.default")
             openai_client = AsyncAzureOpenAI(
-                api_version=api_version,
+                api_version=AZURE_OPENAI_API_VERSION,
                 azure_endpoint=endpoint,
                 azure_ad_token_provider=token_provider,
             )

app/backend/approaches/approach.py

@@ -123,9 +123,12 @@ def __init__(
         self.vision_token_provider = vision_token_provider
 
     def build_filter(self, overrides: dict[str, Any], auth_claims: dict[str, Any]) -> Optional[str]:
+        include_category = overrides.get("include_category")
         exclude_category = overrides.get("exclude_category")
         security_filter = self.auth_helper.build_security_filters(overrides, auth_claims)
         filters = []
+        if include_category:
+            filters.append("category eq '{}'".format(include_category.replace("'", "''")))
         if exclude_category:
             filters.append("category ne '{}'".format(exclude_category.replace("'", "''")))
         if security_filter: