Skip to content

Commit 15e304f

Browse files
committed
Add scenario use case for invoice classification and extraction
1 parent 77b4919 commit 15e304f

6 files changed

Lines changed: 2409 additions & 3 deletions

File tree

.gitignore

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -564,6 +564,6 @@ cython_debug/
564564
*Outputs.json
565565
*.pdf.json
566566
*redacted*.pdf
567-
samples/python/scenarios/invoices/*
568-
!samples/python/scenarios/invoices/*.py
569-
!samples/python/scenarios/invoices/*.ipynb
567+
samples/**/scenarios/invoices/*
568+
!samples/**/scenarios/invoices/*.py
569+
!samples/**/scenarios/invoices/*.ipynb

README.md

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,7 @@ The techniques demonstrated take advantage of various capabilities from each ser
3535
- [Document Classification](#document-classification)
3636
- [Document Redaction](#document-redaction)
3737
- [Document Extraction](#document-extraction)
38+
- [Use Case Scenarios](#use-case-scenarios)
3839
- [Getting Started](#getting-started)
3940
- [Setup on GitHub Codespaces](#setup-on-github-codespaces)
4041
- [Setup on Local](#setup-on-local)
@@ -70,6 +71,14 @@ The techniques demonstrated take advantage of various capabilities from each ser
7071
| Vision-based Extraction with Azure OpenAI GPT-4o GPT-4o | [Python](./samples/python/extraction/vision/document-extraction-gpt-vision.ipynb) \| [.NET](./samples/dotnet/extraction/vision/document-extraction-gpt-vision.ipynb) | Use Azure OpenAI GPT-4o models to extract structured data from documents using vision capabilities. | Complex documents with a mix of text and images, including diagrams, signatures, selection marks, etc. such as reports and contracts. |
7172
| Multi-Modal (Text and Vision) Extraction with Azure AI Document Intelligence and Azure OpenAI GPT-4o | [Python](./samples/python/extraction/multimodal/document-extraction-gpt-text-and-vision.ipynb) \| [.NET](./samples/dotnet/extraction/multimodal/document-extraction-gpt-text-and-vision.ipynb) | Improve the accuracy and confidence in extracting structured data from documents by combining text and images with LLMs. | Any structured or unstructured document type. |
7273

74+
## Use Case Scenarios
75+
76+
This repo also contains a collection of end-to-end use case scenarios that demonstrate how to combine the various samples to create a real-world scenario for document processing.
77+
78+
| Scenario | Link | Description |
79+
| ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
80+
| **Invoice** | [Python](./samples/python/scenarios/invoices/invoice-extraction.ipynb) \| [.NET](./samples/dotnet/scenarios/invoices/invoice-extraction.ipynb) | Using a structured Invoice object ([Python](./samples/python/modules/samples/models/invoice.py) \| [.NET](./samples/dotnet/modules/samples/models/Invoice.csx)), invoice documents can be extracted into a standard Invoice schema by first classifying which pages to extract from using boundary detection. |
81+
7382
## Getting Started
7483

7584
The sample repository comes with a [**Dev Container**](./.devcontainer/README.md) that contains all the necessary tools and dependencies to run the sample. Please review the [**container and it's dependencies**](./.devcontainer/README.md) to understand all of the necessary components required to run these in a real-world environment, including the use of [Poppler](https://poppler.freedesktop.org/).

samples/dotnet/scenarios/README.md

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
# Document Processing with Azure AI Samples - Use Case Scenarios
2+
3+
This folder contains a collection of end-to-end use case scenarios that demonstrate how to combine the various .NET samples to create a real-world scenario for document processing.
4+
5+
## Scenarios
6+
7+
| Document Type | Description |
8+
| -------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
9+
| [**Invoice**](./invoices/invoice-extraction.ipynb) | Using a [structured Invoice object](../modules/samples/models/Invoice.csx), invoice documents can be extracted into a standard Invoice schema by first classifying which pages to extract from using boundary detection. |

0 commit comments

Comments
 (0)