Skip to content

Commit b33c61c

Browse files
committed
Update README for scenarios
1 parent 3e150a9 commit b33c61c

3 files changed

Lines changed: 13 additions & 11 deletions

File tree

README.md

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -75,9 +75,10 @@ The techniques demonstrated take advantage of various capabilities from each ser
7575

7676
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.
7777

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. |
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+
| **US Tax 1040** | [Python](./samples/python/scenarios/us_tax/us-tax-1040-extraction.ipynb) | Using Azure AI Document Intelligence prebuilt-tax.us.1040 models, US Tax 1040 documents can be extracted into a standard schema for each form type by first classifying which pages to extract from using boundary detection with Azure OpenAI. |
8182

8283
## Getting Started
8384

requirements.txt

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -8,16 +8,16 @@ azure-storage-blob~=12.25.1
88
ipycanvas~=0.13.3
99
ipykernel~=6.29.5
1010
matplotlib~=3.10.3
11-
notebook~=7.4.2
11+
notebook~=7.4.3
1212
numpy
13-
openai~=1.81.0
13+
openai~=1.93.0
1414
opencv-python~=4.11.0.86
1515
openpyxl~=3.1.5
16-
pandas~=2.2.3
16+
pandas~=2.3.0
1717
pdf2image~=1.17.0
18-
pydantic~=2.11.4
18+
pydantic~=2.11.7
1919
pytesseract~=0.3.13
20-
python-dotenv~=1.1.0
20+
python-dotenv~=1.1.1
2121
seaborn~=0.13.2
2222
scikit-learn
2323
tabulate~=0.9.0

samples/python/scenarios/README.md

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,7 @@ This folder contains a collection of end-to-end use case scenarios that demonstr
44

55
## Scenarios
66

7-
| Document Type | Description |
8-
| -------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
9-
| [**Invoice**](./invoices/invoice-extraction.ipynb) | Using a [structured Invoice object](../modules/samples/models/invoice.py), invoice documents can be extracted into a standard Invoice schema by first classifying which pages to extract from using boundary detection. |
7+
| Document Type | Description |
8+
| -------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
9+
| [**Invoice**](./invoices/invoice-extraction.ipynb) | Using a [structured Invoice object](../modules/samples/models/invoice.py), invoice documents can be extracted into a standard Invoice schema by first classifying which pages to extract from using boundary detection. |
10+
| [**US Tax 1040**](./us_tax/us-tax-1040-extraction.ipynb) | Using Azure AI Document Intelligence prebuilt-tax.us.1040 models, US Tax 1040 documents can be extracted into a standard schema for each form type by first classifying which pages to extract from using boundary detection with Azure OpenAI. |

0 commit comments

Comments
 (0)