-
Notifications
You must be signed in to change notification settings - Fork 151
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Commit from GitHub Actions (Generate Site)
- Loading branch information
Showing
10 changed files
with
8,209 additions
and
7,719 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,311 @@ | ||
| <!DOCTYPE html> | ||
| <!--[if IE]><![endif]--> | ||
| <html lang="en"> | ||
|
|
||
| <head> | ||
| <meta charset="utf-8"> | ||
| <title>Extract Invoice Details from Any File Format Using Azure OCR and OpenAI | PnP Samples </title> | ||
| <meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" "=""> | ||
| <meta name="title" content="Extract Invoice Details from Any File Format Using Azure OCR and OpenAI | PnP Samples "> | ||
| <meta name="generator" content="docfx 2.56.7.0"> | ||
| <meta name="description" content="A sample gallery of scripts to manage all things Microsoft 365."> | ||
|
|
||
| <!-- Social Media --> | ||
| <meta property="og:locale" content="en_GB"> | ||
| <meta property="og:title" content="Extract Invoice Details from Any File Format Using Azure OCR and OpenAI | PnP Samples "> | ||
| <meta property="og:type" content="website"> | ||
| <meta property="og:url" content="https://pnp.github.io/script-samples"> | ||
| <meta property="og:image" content="https://pnp.github.io/script-samples/assets/social-media-screenshot.png"> | ||
| <meta property="og:image:alt" content="Screenshot example of the PnP Script Samples Site"> | ||
| <meta property="og:site_name" content="PnP Script Samples"> | ||
| <meta name="msvalidate.01" content="04EFEDA66EC42C08A1247C979E2F9ADD"> | ||
| <meta property="og:description" content="A sample gallery of scripts to manage all things Microsoft 365."> | ||
|
|
||
| <link rel="shortcut icon" href="https://c.s-microsoft.com/favicon.ico?v2"> | ||
| <link rel="stylesheet" href="../styles/docfx.vendor.css"> | ||
| <link rel="stylesheet" href="../styles/docfx.css"> | ||
| <link rel="stylesheet" href="../styles/main.css"> | ||
| <link rel="stylesheet" href="../styles/extra.css"> | ||
| <link rel="stylesheet" href="../styles/filter.css"> | ||
| <link rel="stylesheet" href="../styles/site.css"> | ||
| <link href="https://fonts.googleapis.com/css?family=Roboto" rel="stylesheet"> | ||
| <meta property="docfx:navrel" content="../toc.html"> | ||
| <meta property="docfx:tocrel" content="../toc.html"> | ||
|
|
||
|
|
||
| <meta property="docfx:newtab" content="true"> | ||
| <script type="text/javascript"> | ||
| (function(c,l,a,r,i,t,y){ | ||
| c[a]=c[a]||function(){(c[a].q=c[a].q||[]).push(arguments)}; | ||
| t=l.createElement(r);t.async=1;t.src="https://www.clarity.ms/tag/"+i; | ||
| y=l.getElementsByTagName(r)[0];y.parentNode.insertBefore(t,y); | ||
| })(window, document, "clarity", "script", "8j6pedl344"); | ||
| </script> | ||
| </head> <body data-spy="scroll" data-target="#affix" data-offset="120"> | ||
| <div id="wrapper"> | ||
| <header> | ||
|
|
||
| <nav id="autocollapse" class="navbar navbar-inverse ng-scope" role="navigation"> | ||
| <div class="container"> | ||
| <div class="github-mark"> | ||
| <a href="https://github.com/pnp/script-samples" title="Go to repository"> | ||
| <div class="github-wrapper"> | ||
| <div class="github-icon"> | ||
| <img src="https://pnp.github.io/script-samples/assets/icons/github-light-64px.png" alt="GitHub Icon Image"> | ||
| </div> | ||
| <div class="github-repository"> | ||
| <span>GitHub</span> | ||
| <ul class="github-facts"> | ||
| <li> | ||
| <i class="fa fa-code-fork" aria-hidden="true"></i> | ||
| <span class="github-forks"></span> | ||
| </li> | ||
| <li> | ||
| <i class="fa fa-star-o" aria-hidden="true"></i> | ||
| <span class="github-stars"></span> | ||
| </li> | ||
| </ul> | ||
| </div> | ||
| </div> | ||
| </a> | ||
| </div> | ||
| <div class="navbar-header"> | ||
| <button type="button" class="navbar-toggle" data-toggle="collapse" data-target="#navbar"> | ||
| <span class="sr-only">Toggle navigation</span> | ||
| <span class="icon-bar"></span> | ||
| <span class="icon-bar"></span> | ||
| <span class="icon-bar"></span> | ||
| </button> | ||
| <a class="navbar-brand" href="../index.html"> | ||
| <img id="logo" class="svg" src="../assets/logo.svg" alt=""> | ||
| </a> </div> | ||
| <div class="collapse navbar-collapse" id="navbar"> | ||
| <form class="navbar-form navbar-right" role="search" id="search"> | ||
| <div class="form-group"> | ||
| <label class="glyphicon glyphicon-search" for="search-query"></label> | ||
| <input type="text" class="form-control" id="search-query" placeholder="Search" autocomplete="off"> | ||
| </div> | ||
| </form> | ||
| </div> | ||
| </div> | ||
| </nav> </header> | ||
| <div role="main" class="container body-content hide-when-search"> | ||
| <div class="article row grid"> | ||
| <div class="col-md-12"> | ||
| <article class="content wrap" id="_content" data-uid=""> | ||
| <div class="contribution-panel mobile-hide pull-right"> | ||
| <a href="https://github.com/pnp/script-samples/blob/main/scripts/azure-ocr-openai-json-invoice-extractor/README.md/#L1" title="Improve this Doc" class="improve-doc-lg"><i class="glyphicon glyphicon-pencil"></i></a> | ||
| </div> | ||
| <h1 id="extract-invoice-details-from-any-file-format-using-azure-ocr-and-openai">Extract Invoice Details from Any File Format Using Azure OCR and OpenAI</h1> | ||
|
|
||
| <h2 id="summary">Summary</h2> | ||
| <p>This sample script integrates Azure's Document Intelligence and OpenAI services to extract from either images or pdfs or embedded images from any unstructured data and to use this script for any other purpose , please change the system prompt in the script.</p> | ||
| <h3 id="functionality"><strong>Functionality</strong></h3> | ||
| <ul> | ||
| <li><strong>Text Extraction</strong>: Utilizes Azure's Document Intelligence Read OCR model to extract text from documents, including PDFs and images.</li> | ||
| <li><strong>Data Processing</strong>: Employs Azure OpenAI's GPT models to analyze the extracted text and identify key invoice details, such as <strong>Invoice Number</strong>, <strong>Sales Person</strong>, <strong>Date of Invoice</strong>, <strong>SubTotal</strong>, <strong>Tax</strong>, and <strong>Total</strong>.</li> | ||
| <li><strong>JSON Output</strong>: Structures the identified information into a JSON format for streamlined data handling and integration.</li> | ||
| </ul> | ||
| <hr> | ||
| <h2 id="prerequisites">Prerequisites</h2> | ||
| <ul> | ||
| <li><strong>OpenAI API Key</strong>: Create an account <a href="https://platform.openai.com/signup/">here</a> to obtain the API key.</li> | ||
| <li><strong>Document Intelligence API Key</strong>: Create a key in the <a href="https://documentintelligence.ai.azure.com/studio/">Document Intelligence Studio</a>.</li> | ||
| <li><strong>Settings</strong>: The settings of the script is part of set Settings-Agreements.json , ensure the script and its settings file are in same location</li> | ||
| </ul> | ||
| <hr> | ||
| <h2 id="settings">Settings</h2> | ||
| <pre><code class="lang-json">{ | ||
| "APIKeys": { | ||
| "OpenAI": "<OCRKeyFromAzureOpenAI>", | ||
| "DocumentIntelligence": "<OCRKeyFromADocumentIntelligence>"" | ||
| }, | ||
| "Endpoints": { | ||
| "OpenAI": "https://<openaiendpoint>.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-08-01-preview", | ||
| "DocumentIntelligence": "https://<docintelligendeendpoint>.cognitiveservices.azure.com" | ||
| }, | ||
| "FilePath": "/Users/divyaakula/Documents/VidesoReview/SyntexDemo/AI Builder Document Processing Sample Data/Invoices/Adatum/Train/Adatum 1.pdf", | ||
| "Base64String": null, | ||
| "OCRVersion": "2024-07-31-preview", | ||
| "ChunkSize": 4194304 | ||
| } | ||
|
|
||
| </code></pre> | ||
| <hr> | ||
| <h2 id="example-screenshot">Example Screenshot</h2> | ||
| <p><img src="assets/output.png" alt="Example Screenshot"></p> | ||
| <hr> | ||
| <div class="tabGroup" id="tabgroup_CeZOj-G++Q"> | ||
| <ul role="tablist"> | ||
| <li role="presentation"> | ||
| <a href="#tabpanel_CeZOj-G++Q_powershell" role="tab" aria-controls="tabpanel_CeZOj-G++Q_powershell" data-tab="powershell" tabindex="0" aria-selected="true">PowerShell</a> | ||
| </li> | ||
| </ul> | ||
| <section id="tabpanel_CeZOj-G++Q_powershell" role="tabpanel" data-tab="powershell"><button class="article-clipboard" title="Copy to clipboard" data-toggle="tooltip" data-placement="top" data-clipboard-target="section[id^='tabpanel'][data-tab='powershell'] pre"> | ||
| <span class="glyphicon glyphicon-copy" aria-hidden="true"></span> | ||
| <span class="article-clipboard__message done">Copied</span> | ||
| </button> | ||
|
|
||
| <pre><code class="lang-powershell"># A PowerShell script to extract invoice details using Azure OCR and OpenAI. | ||
|
|
||
| # Path to your config file | ||
| $configFilePath = "Settings-Agreements.json" | ||
| if (-not (Test-Path $configFilePath)) { | ||
| throw "Configuration file not found at $configFilePath" | ||
| } | ||
|
|
||
| # Load configuration from JSON file | ||
| $Config = Get-Content -Path $configFilePath | ConvertFrom-Json | ||
|
|
||
| # Extract Values from Config | ||
| $OpenAI_Key = $Config.APIKeys.OpenAI | ||
| $OCR_Key = $Config.APIKeys.DocumentIntelligence | ||
| $OCR_Endpoint = $Config.Endpoints.DocumentIntelligence | ||
| $OpenAI_Endpoint = $Config.Endpoints.OpenAI | ||
| $OCR_Version = $Config.OCRVersion | ||
| $FilePath = $Config.FilePath | ||
| $Base64String = $Config.Base64String | ||
|
|
||
| # Function to Extract Text from PDF/Image Using Azure OCR | ||
| function Get-TextFromDocument($Base64String) { | ||
| # Convert Base64 to binary | ||
| $BinaryData = [Convert]::FromBase64String($Base64String) | ||
|
|
||
| # Set OCR request headers | ||
| $Headers = @{ | ||
| "Ocp-Apim-Subscription-Key" = $OCR_Key | ||
| "Content-Type" = "application/pdf" # Change to "image/jpeg" for images | ||
| } | ||
|
|
||
| # Send file to Azure Document Intelligence OCR API | ||
| Invoke-RestMethod -Uri "$OCR_Endpoint/documentintelligence/documentModels/prebuilt-read:analyze?api-version=$OCR_Version" ` | ||
| -Headers $Headers -Method Post -ResponseHeadersVariable HeaderInfo -Body $BinaryData | ||
|
|
||
| if (-not $HeaderInfo) { | ||
| throw "Failed to start OCR process." | ||
| } | ||
|
|
||
| # Extract operation URL | ||
| $OperationUrl = ($HeaderInfo."Operation-Location")[0] | ||
|
|
||
| # Poll for result | ||
| Start-Sleep -Seconds 5 # Wait before checking status | ||
| do { | ||
| $Result = Invoke-RestMethod -Uri $OperationUrl -Headers @{ "Ocp-Apim-Subscription-Key" = $OCR_Key } | ||
| $Status = $Result.status | ||
| Start-Sleep -Seconds 2 | ||
| } while ($Status -ne "succeeded") | ||
|
|
||
| # Extract recognized text | ||
| $ExtractedText = ($Result.analyzeResult.pages.lines.content) -join " " | ||
| return $ExtractedText | ||
| } | ||
|
|
||
| # Function to Extract Names Using Azure OpenAI | ||
| function Get-Inputs($ExtractedText) { | ||
| # OpenAI Request Payload | ||
| $OpenAI_Request = @{ | ||
| messages = @( | ||
| @{ role = "system"; content = "Extract Invoice No, Sales Person, Date Of Invoice, SubTotal, Tax and Total and return in plain json format" } | ||
| @{ role = "user"; content = "Text: $ExtractedText" } | ||
| ) | ||
| } | ConvertTo-Json -Depth 3 | ||
|
|
||
| # OpenAI Headers | ||
| $OpenAI_Headers = @{ | ||
| "api-key" = $OpenAI_Key | ||
| "Content-Type" = "application/json" | ||
| } | ||
|
|
||
| # Call OpenAI API | ||
| $OpenAI_Response = Invoke-RestMethod -Uri "$OpenAI_Endpoint" ` | ||
| -Method Post -Headers $OpenAI_Headers -Body $OpenAI_Request | ||
|
|
||
| # Extract Names from Response | ||
| $responseContent = $OpenAI_Response.choices[0].message.content | ||
| # Remove leading and trailing triple backticks and 'json' label | ||
| $jsonString = $responseContent -replace '^```json\s*', '' -replace '\s*```$', '' | ||
| return $jsonString | ||
| } | ||
|
|
||
| # Function to Process Base64 Document Input | ||
| function Get-Data($Base64String) { | ||
| try { | ||
| $Base64String = Convert-Base64String $FilePath | ||
| # Step 1: Extract text using OCR | ||
| $ExtractedText = Get-TextFromDocument -Base64String $Base64String | ||
|
|
||
| # Step 2: Extract Names using OpenAI | ||
| $Names = Get-Inputs -ExtractedText $ExtractedText | ||
| # Step 3: Return as JSON | ||
| return $Names | ||
| } | ||
| catch { | ||
| return @{ "error" = $_.Exception.Message } | ConvertTo-Json | ||
| } | ||
| } | ||
|
|
||
| # Function to convert file to Base64 string | ||
| function Convert-Base64String($path) { | ||
| $Base64Input = [Convert]::ToBase64String([IO.File]::ReadAllBytes($path)) | ||
| return $Base64Input | ||
| } | ||
|
|
||
| # Example Usage: Provide a Base64 String of a PDF or Image | ||
| $Base64Input = "" | ||
| # Call the Function | ||
| $Result = Get-Data -Base64String $Base64Input | ||
| Write-Output $Result | ||
|
|
||
| </code></pre> | ||
| <p><a href="https://learn.microsoft.com/en-us/azure/ai-studio/what-is-ai-studio?wt.mc_id=MVP_366830">More about OpenAI API</a></p> | ||
| </section> | ||
| </div> | ||
| <h2 id="contributors">Contributors</h2> | ||
| <table> | ||
| <thead> | ||
| <tr> | ||
| <th>Author(s)</th> | ||
| <th>Author(s)</th> | ||
| </tr> | ||
| </thead> | ||
| <tbody> | ||
| <tr> | ||
| <td>Divya Akula</td> | ||
| <td><a href="https://www.linkedin.com/in/ms-divya-akula/">https://www.linkedin.com/in/ms-divya-akula/</a></td> | ||
| </tr> | ||
| </tbody> | ||
| </table> | ||
| <h2 id="disclaimer">Disclaimer</h2> | ||
| <p><strong>THESE SAMPLES ARE PROVIDED <em>AS IS</em> WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING ANY IMPLIED WARRANTIES OF FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR NON-INFRINGEMENT.</strong></p> | ||
| <img src="https://m365-visitor-stats.azurewebsites.net/script-samples/scripts/azure-ocr-openai-json-invoice-extractor" aria-hidden="true"> | ||
| </article> | ||
| </div> | ||
| </div> | ||
| </div> | ||
|
|
||
| <footer> | ||
| <div class="grad-bottom"></div> | ||
| <div class="footer"> | ||
| <div class="container"> | ||
| <span class="pull-right"> | ||
| <a href="#top">Back to top</a> | ||
| </span> | ||
| <span>Script Samples<br>Generated by <strong><a href='https://dotnet.github.io/docfx' alt='Doc FX Website'>DocFX</a></strong> with <strong><a href='https://ovasquez.github.io/docfx-material' alt='DocFx Material Theme'>Material UI</a></strong></span> | ||
|
|
||
| <!-- <img src="https://telemetry.sharepointpnp.com/@pnp.github.io/index/" alt="spacer"> --> | ||
| </div> | ||
| </div> | ||
| </footer> </div> | ||
|
|
||
| <script type="text/javascript" src="../styles/docfx.vendor.js"></script> | ||
| <script type="text/javascript" src="../styles/docfx.js"></script> | ||
| <script type="text/javascript" src="../styles/main.js"></script> | ||
|
|
||
| <script type="text/javascript" src="../styles/clipboard.min.js"></script> | ||
| <script type="text/javascript" src="../styles/isotope.pkgd.min.js"></script> | ||
| <script type="text/javascript" src="../styles/loadsamples.js"></script> | ||
| <script type="text/javascript" src="../styles/filtersamples.js"></script> | ||
|
|
||
| </body> | ||
| </html> |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
61 changes: 61 additions & 0 deletions
61
azure-ocr-openai-json-invoice-extractor/assets/sample.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,61 @@ | ||
| [ | ||
| { | ||
| "name": "azure-ocr-openai-json-invoice-extractor", | ||
| "source": "openai", | ||
| "title": "Get data from OpenAI deployment/model", | ||
| "shortDescription": "This sample shows how to use both OpenAI and document intelligene studio to process and extract data in a json format", | ||
| "url": "https://pnp.github.io/script-samples/azure-ocr-openai-json-invoice-extractor/README.html", | ||
| "longDescription": [ | ||
| "" | ||
| ], | ||
| "creationDateTime": "2025-01-26", | ||
| "updateDateTime": "2025-01-26", | ||
| "products": [ | ||
| "OpenAI", | ||
| "Document Intelligence Studio" | ||
| ], | ||
| "metadata": [ | ||
| { | ||
| "key": "POWERSHELL", | ||
| "value": "7.2.0" | ||
| } | ||
| ], | ||
| "categories": [ | ||
| "Status", | ||
| "Summary", | ||
| "AI" | ||
| ], | ||
| "tags": [ | ||
| "Invoke-WebRequest" | ||
| ], | ||
| "thumbnails": [ | ||
| { | ||
| "type": "image", | ||
| "order": 100, | ||
| "url": "https://raw.githubusercontent.com/pnp/script-samples/main/scripts/azure-ocr-openai-json-invoice-extractor/assets/preview.png", | ||
| "alt": "Preview of the sample Get data from OpenAI deployment/model" | ||
| } | ||
| ], | ||
| "authors": [ | ||
| { | ||
| "gitHubAccount": "divya-akula", | ||
| "company": "", | ||
| "pictureUrl": "https://github.com/divya-akula.png", | ||
| "name": "Divya Akula" | ||
| } | ||
| ], | ||
| "references": [ | ||
| { | ||
| "name": "Want to learn more about Azure OpenAI AI Deployments", | ||
| "description": "If you're interested in learning more about OpenAI API and its capabilities, this link provides a list of resources and tools to help you get started. Whether you're a developer looking to integrate Open AI into your applications or a researcher exploring the latest advances in artificial intelligence, this guide offers a range of helpful resources, including documentation, tutorials, and community forums.", | ||
| "url": "https://learn.microsoft.com/en-us/azure/ai-studio/what-is-ai-studio" | ||
| }, | ||
| { | ||
| "name": "Create and Configure an Azure OpenAI Resource", | ||
| "description": "Learn to create and configure an Azure OpenAI resource using the Azure portal for seamless AI integration.", | ||
| "url": "https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal" | ||
| } | ||
| ] | ||
| } | ||
| ] | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.