Merge pull request #45 from Azure-Samples/dev-container

jamesmcroft · web-flow · commit 2175391b6986 · 2025-01-02T11:02:30.000Z
Fix devcontainer issues for local and Codespaces run
diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
@@ -1,6 +1,6 @@
 {
     "name": "Azure AI Document Processing Samples",
-    "image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye",
+    "image": "mcr.microsoft.com/vscode/devcontainers/python:1-3.12-bullseye",
     "features": {
         "ghcr.io/devcontainers/features/git:1": {
             "version": "latest",
@@ -30,6 +30,12 @@
         "ghcr.io/devcontainers/features/docker-in-docker",
         "./local-features/dev-tools"
     ],
+    "remoteUser": "vscode",
+    "containerUser": "vscode",
+    "forwardPorts": [],
+    "otherPortsAttributes": {
+        "onAutoForward": "ignore"
+    },
     "customizations": {
         "vscode": {
             "extensions": [
diff --git a/.devcontainer/local-features/dev-tools/install.sh b/.devcontainer/local-features/dev-tools/install.sh
@@ -1,7 +1,8 @@
 #!/usr/bin/env bash
 
-# Default: Exit on any failure.
-set -e
+USERNAME=${USERNAME:-"vscode"}
+
+set -eux
 
 # Setup STDERR.
 err() {
@@ -13,9 +14,12 @@ if [ "$(id -u)" -ne 0 ]; then
     exit 1
 fi
 
-###################
+# Ensure apt is in non-interactive to avoid prompts
+export DEBIAN_FRONTEND=noninteractive
+
+###########################################
 # Helper Functions
-###################
+###########################################
 
 apt_get_update() {
     if [ "$(find /var/lib/apt/lists/* | wc -l)" = "0" ]; then
@@ -36,9 +40,6 @@ check_packages() {
 # Install Feature
 ###########################################
 
-# Ensure apt is in non-interactive to avoid prompts
-export DEBIAN_FRONTEND=noninteractive
-
 # Install dependencies
 check_packages poppler-utils tesseract-ocr libtesseract-dev ffmpeg libsm6 libxext6 python3-opencv
 
diff --git a/.gitattributes b/.gitattributes
@@ -0,0 +1,60 @@
+# Set default behavior to automatically normalize line endings.
+* text=auto
+
+# Collapse these files in PRs by default
+*.xlf linguist-generated=true
+*.lcl linguist-generated=true
+
+*.jpg binary
+*.png binary
+*.gif binary
+
+# Force bash scripts to always use lf line endings so that if a repo is accessed
+# in Unix via a file share from Windows, the scripts will work.
+*.in text eol=lf
+*.sh text eol=lf
+
+# Likewise, force cmd and batch scripts to always use crlf
+*.cmd text eol=crlf
+*.bat text eol=crlf
+
+*.cs text=auto diff=csharp
+*.vb text=auto
+*.resx text=auto
+*.c text=auto
+*.cpp text=auto
+*.cxx text=auto
+*.h text=auto
+*.hxx text=auto
+*.py text=auto
+*.rb text=auto
+*.java text=auto
+*.html text=auto
+*.htm text=auto
+*.css text=auto
+*.scss text=auto
+*.sass text=auto
+*.less text=auto
+*.js text=auto
+*.lisp text=auto
+*.clj text=auto
+*.sql text=auto
+*.php text=auto
+*.lua text=auto
+*.m text=auto
+*.asm text=auto
+*.erl text=auto
+*.fs text=auto
+*.fsx text=auto
+*.hs text=auto
+
+*.csproj text=auto
+*.vbproj text=auto
+*.fsproj text=auto
+*.dbproj text=auto
+*.sln text=auto eol=crlf
+
+# Set linguist language for .h files explicitly based on
+# https://github.com/github/linguist/issues/1626#issuecomment-401442069
+# this only affects the repo's language statistics
+*.h linguist-language=C
diff --git a/.gitignore b/.gitignore
@@ -561,4 +561,5 @@ cython_debug/
 #.idea/
 
 # Repo Specific
-*Outputs.json
+*Outputs.json
+*.pdf.json
diff --git a/.vscode/extensions.json b/.vscode/extensions.json
@@ -0,0 +1,12 @@
+{
+    "recommendations": [
+        "ms-python.vscode-pylance",
+        "ms-python.python",
+        "ms-python.debugpy",
+        "ms-toolsai.jupyter",
+        "ms-azuretools.vscode-bicep",
+        "ms-vscode.vscode-node-azure-pack",
+        "ms-vscode.powershell",
+        "GitHub.vscode-pull-request-github"
+    ]
+}
diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -0,0 +1,3 @@
+{
+    "python.terminal.activateEnvironment": true
+}
diff --git a/README.md b/README.md
@@ -1,12 +1,12 @@
 ---
 page_type: sample
 languages:
-- python
-- bicep
+  - python
+  - bicep
 products:
-- azure
-- ai-services
-- azure-openai
+  - azure
+  - ai-services
+  - azure-openai
 name: Document Processing with Azure AI Samples
 description: This collection of samples demonstrates how to use various Azure AI capabilities to build solution to extract structured data, classify, and analyze documents.
 ---
@@ -27,6 +27,9 @@ The techniques demonstrated take advance of various capabilities from each servi
 
 - [Samples](#samples)
 - [Getting Started](#getting-started)
+  - [Setup on GitHub Codespaces](#setup-on-github-codespaces)
+  - [Setup on Local](#setup-on-local)
+  - [Deploy the Azure environment](#deploy-the-azure-environment)
 - [Contributing](#contributing)
 - [License](#license)
 
@@ -35,38 +38,53 @@ The techniques demonstrated take advance of various capabilities from each servi
 > [!NOTE]
 > All data extraction samples provide both an accuracy and confidence score for the extracted data. The accuracy score is calculated based on the similarity between the extracted data and the ground truth data. The confidence score is calculated based on OCR analysis confidence and `logprobs` in Azure OpenAI requests.
 
-| Sample                                                                                             | Description                                                                                                                                    | Example Use Cases                                                         |
-| -------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
-| [Data Extraction - Azure AI Document Intelligence + Azure OpenAI GPT-4o](./samples/extraction/text-based/document-intelligence-openai.ipynb) | Demonstrates how to use Azure AI Document Intelligence pre-built layout and Azure OpenAI GPT models to extract structured data from documents. | Predominantly text-based documents such as invoices, receipts, and forms. |
-| [Data Extraction - Azure AI Document Intelligence + Phi-3.5 MoE](./samples/extraction/text-based/document-intelligence-phi.ipynb) | Demonstrates how to use Azure AI Document Intelligence pre-built layout and Microsoft's Phi-3 models to extract structured data from documents. | Predominantly text-based documents such as invoices, receipts, and forms. |
-| [Data Extraction - Marker/Surya + Azure OpenAI GPT-4o](./samples/extraction/text-based/marker-surya-openai.ipynb) | Demonstrates how to use Marker/Surya and Azure OpenAI GPT models to extract structured data from documents. | Predominantly text-based documents such as invoices, receipts, and forms. |
-| [Data Extraction - Azure OpenAI GPT-4o with Vision](./samples/extraction/vision-based/openai.ipynb) | Demonstrates how to use Azure OpenAI GPT-4o and GPT-4o-mini models to extract structured data from documents using their built-in vision capabilities. | Complex documents with a mix of text and images, including diagrams, signatures, selection marks, etc. such as reports and contracts. |
-| [Data Extraction - Comprehensive Azure AI Document Intelligence + Azure OpenAI GPT-4o with Vision](./samples/extraction/vision-based/comprehensive.ipynb) | Demonstrates how to improve the accuracy and confidence in extracting structured data from documents by combining Azure AI Document Intelligence and Azure OpenAI GPT-4o models with vision capabilities. | Any structured or unstructured document type. |
-| [Classification - Azure OpenAI GPT-4o with Vision](./samples/classification/openai.ipynb) | Demonstrates how to use Azure OpenAI GPT-4o and GPT-4o-mini models to classify documents using their built-in vision capabilities. | Processing multiple documents types or documents with varying purposes, such as contracts, legal documents, and emails. |
-| [Classification - Azure AI Document Intelligence + Embeddings](./samples/classification/document-intelligence-embeddings.ipynb) | Demonstrates how to use Azure AI Document Intelligence pre-built layout and embeddings models to classify documents based on their content. | Processing multiple documents types or documents with varying purposes, such as contracts, legal documents, and emails. |
+| Sample                                                                                                                                                    | Description                                                                                                                                                                                               | Example Use Cases                                                                                                                     |
+| --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
+| [Data Extraction - Azure AI Document Intelligence + Azure OpenAI GPT-4o](./samples/extraction/text-based/document-intelligence-openai.ipynb)              | Demonstrates how to use Azure AI Document Intelligence pre-built layout and Azure OpenAI GPT models to extract structured data from documents.                                                            | Predominantly text-based documents such as invoices, receipts, and forms.                                                             |
+| [Data Extraction - Azure AI Document Intelligence + Phi-3.5 MoE](./samples/extraction/text-based/document-intelligence-phi.ipynb)                         | Demonstrates how to use Azure AI Document Intelligence pre-built layout and Microsoft's Phi-3 models to extract structured data from documents.                                                           | Predominantly text-based documents such as invoices, receipts, and forms.                                                             |
+| [Data Extraction - Marker/Surya + Azure OpenAI GPT-4o](./samples/extraction/text-based/marker-surya-openai.ipynb)                                         | Demonstrates how to use Marker/Surya and Azure OpenAI GPT models to extract structured data from documents.                                                                                               | Predominantly text-based documents such as invoices, receipts, and forms.                                                             |
+| [Data Extraction - Azure OpenAI GPT-4o with Vision](./samples/extraction/vision-based/openai.ipynb)                                                       | Demonstrates how to use Azure OpenAI GPT-4o and GPT-4o-mini models to extract structured data from documents using their built-in vision capabilities.                                                    | Complex documents with a mix of text and images, including diagrams, signatures, selection marks, etc. such as reports and contracts. |
+| [Data Extraction - Comprehensive Azure AI Document Intelligence + Azure OpenAI GPT-4o with Vision](./samples/extraction/vision-based/comprehensive.ipynb) | Demonstrates how to improve the accuracy and confidence in extracting structured data from documents by combining Azure AI Document Intelligence and Azure OpenAI GPT-4o models with vision capabilities. | Any structured or unstructured document type.                                                                                         |
+| [Classification - Azure OpenAI GPT-4o with Vision](./samples/classification/openai.ipynb)                                                                 | Demonstrates how to use Azure OpenAI GPT-4o and GPT-4o-mini models to classify documents using their built-in vision capabilities.                                                                        | Processing multiple documents types or documents with varying purposes, such as contracts, legal documents, and emails.               |
+| [Classification - Azure AI Document Intelligence + Embeddings](./samples/classification/document-intelligence-embeddings.ipynb)                           | Demonstrates how to use Azure AI Document Intelligence pre-built layout and embeddings models to classify documents based on their content.                                                               | Processing multiple documents types or documents with varying purposes, such as contracts, legal documents, and emails.               |
 
 ## Getting Started
 
-The sample repository comes with a [**Dev Container**](./.devcontainer/README.md) that contains all the necessary tools and dependencies to run the sample. To use the Dev Container, you need to have the following tools installed on your local machine:
+The sample repository comes with a [**Dev Container**](./.devcontainer/README.md) that contains all the necessary tools and dependencies to run the sample.
+
+> [!IMPORTANT]
+> An Azure subscription is required to run these samples. If you don't have an Azure subscription, create an [account](https://azure.microsoft.com/en-us/).
+
+### Setup on GitHub Codespaces
+
+To use the Dev Container in GitHub Codespaces, follow these steps:
+
+1. Click on the `Code` button in the repository and select `Codespaces`.
+2. Click on the **+** button to create a new Codespace using the provided `.devcontainer\devcontainer.json` configuration.
+3. Once the Codespace is created, continue to the [Azure environment setup](#deploy-the-azure-environment) section.
+
+### Setup on Local
+
+To use the Dev Container, you need to have the following tools installed on your local machine:
 
 - Install [**Visual Studio Code**](https://code.visualstudio.com/download)
 - Install [**Docker Desktop**](https://www.docker.com/products/docker-desktop)
 - Install [**Remote - Containers**](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) extension for Visual Studio Code
 
-Additionally, you will require:
-
-- An Azure subscription. If you don't have an Azure subscription, create an [account](https://azure.microsoft.com/en-us/).
-
 To setup a local development environment, follow these steps:
 
-> [!NOTE]
+> [!IMPORTANT]
 > Ensure that Docker Desktop is running on your local machine.
 
 1. Clone the repository to your local machine.
 2. Open the repository in Visual Studio Code.
 3. Press `F1` to open the command palette and type `Dev Containers: Reopen in Container`.
 
-Once the Dev Container is up and running, you can setup the necessary Azure services and run the [samples](#samples) in the repository by running the following command in VS Code's `pwsh` terminal:
+Once the Dev Container is up and running, continue to the [Azure environment setup](#deploy-the-azure-environment) section.
+
+### Deploy the Azure environment
+
+Once the Dev Container is up and running, you can setup the necessary Azure services and run the [samples](#samples) in the repository by running the following command in a `pwsh` terminal:
 
 > [!NOTE]
 > For the most optimal sample experience, it is recommended to run the samples in `East US` which will provide support for all the services used in the samples. Find out more about region availability for [Azure AI Document Intelligence](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept-layout?view=doc-intel-4.0.0&tabs=sample-code), and [`GPT-4o`](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#standard-and-global-standard-deployment-model-quota), [`Phi-3.5 MoE`](https://azure.microsoft.com/en-us/pricing/details/phi-3/), and [`text-embedding-3-large`](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#standard-deployment-model-availability) models.
@@ -77,6 +95,9 @@ az login
 ./Setup-Environment.ps1 -DeploymentName <UniqueDeploymentName> -Location <AzureRegion> -SkipInfrastructure $false
 ```
 
+> [!NOTE]
+> If a specific tenant is required, use the `--tenant <TenantId>` parameter in the `az login` command.
+
 The script will deploy the following resources to your Azure subscription:
 
 - [**Azure AI Studio Hub & Project**](https://learn.microsoft.com/en-us/azure/ai-studio/what-is-ai-studio), a development platform for building AI solutions that integrates with Azure AI Services in a secure manner using Microsoft Entra ID for authentication.
diff --git a/Setup-Environment.ps1 b/Setup-Environment.ps1
@@ -68,6 +68,9 @@ $Phi3PrimaryKey = (az keyvault secret show --vault-name $KeyVaultName --name $Ph
 Write-Host "Updating local settings..."
 
 $ConfigurationFile = './.env'
+if (-not (Test-Path -Path $ConfigurationFile)) {
+    New-Item -Path $ConfigurationFile -ItemType File
+}
 
 Set-ConfigurationFileVariable -configurationFile $ConfigurationFile -variableName 'RESOURCE_GROUP_NAME' -variableValue $ResourceGroupName
 Set-ConfigurationFileVariable -configurationFile $ConfigurationFile -variableName 'MANAGED_IDENTITY_CLIENT_ID' -variableValue $ManagedIdentityClientId
diff --git a/requirements.txt b/requirements.txt
@@ -2,6 +2,7 @@ azure-ai-documentintelligence==1.0.0b4
 azure-core==1.32.0
 azure-identity==1.19.0
 azure-storage-blob==12.24.0
+httpx==0.25.2
 ipycanvas==0.13.3
 ipykernel==6.29.5
 marker-pdf==0.3.10

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+{`
	`2`	`+ "python.terminal.activateEnvironment": true`
	`3`	`+}`