Using Intelligent Data Extraction to Augment Contextual LLM Queries - Setup for Linux and Windows

To run the provided examples, you will need to do some initial setup. All commands provided should be run from within the idp_rag_guide folder, unless otherwise stated. We'll ## assume you already have Python version >= 3.5 installed (If not, see instructions here). Perform the following setup steps:

Download the the sample code and unpack it. You should see an idp_rag_guide folder with the following structure:

idp_rag_guide/
├── data
│   └── pdf
│       └── travel_expenses.pdf
├── doc_context.py
├── idp_rag_utils
│   ├── bookmark_utils.py
│   ├── document_structure.py
│   └── __init__.py
├── iso32000_rag.py
└── requirements.txt

Your license should include our IDP offerings. If you don't already have one, you can request a demo key. A demo key will be sufficient to run the simpler Document Context Example , but won't be able to run the more complex Document RAG Example .

Get your Apryse trial key:

Running the code included in this guide will make requests to Open AI that are not free, so you will need a funded account.

python3 -m venv idp-venv
source idp-venv/bin/activate
python3 -m pip install -r requirements.txt

export OPENAI_API_KEY=<your-api-key>
export APRYSE_SDK_LICENSE_KEY=<your-license-key>

New-Item -ItemType Directory -Force -Path apryse_sdk_modules
Set-Location apryse_sdk_modules
Invoke-WebRequest -Uri https://www.pdftron.com/downloads/StructuredOutputModuleWindows.zip -OutFile StructuredOutputModuleWindows.zip
tar -xf StructuredOutputModuleWindows.zip
Remove-Item StructuredOutputModuleWindows.zip
Set-Location ..

If you plan on running the Document RAG example , you should also download the ISO_32000-2 PDF standard, which is used in this sample, and is available for free download from Adobe. Place the downloaded file at the following location: idp_rag_guide/data/pdf/PDF_ISO_32000-2.pdf

You should now be ready to run the examples.

Document Context Example

In this section, we show how to run a simple example that demonstrates how to attach contextual information from a document to your queries.