PDF Parser

x

x

x

At some stage you will have to deal with unstructured data. This can be tricky especially if you need to output the results in a specific format - csv, json, etc ..

In Open WebUI download the mistral:7b model

1. Let's create a new Chain. Click on: '+ Add New' blue button in top right.

2. Save as: 'PDF Parser'.

PDF Parser

1. Add a Tool Agent. Click on the blue + sign and select Chains > LLM Chain.

2. Drag & drop onto the canvas.

Note that the LLM Chain has an option to define the Output Parser

Add Chains > LLM Chain

1. Next add a Chat Model. Again, Click on the blue + sign and select Chat Models > ChatOllama.

2. Connect the ChatOllama to the LLM Chain, by dragging a connector from ChatOllama to LLM Chain.

3. Configure the model as illustrated.

Add Ollama Model

The ChatOllama has an option to upload images. Check that the model has reasoning image capabilities: mistral:7b

Use the options at the bottom to resize canvas.

1. Let's add a Prompt Template: Prompts > Prompt Template, and connect to LLM Chain.

Add Prompt Template

A Prompt Template is similar to the System Prompt in the Chat Model.

1. Before we progress any further, lets Save.

2. In the Prompt Template, expand the Template. Were going to add some instructions based on the PDF.

Take a look at the main section of the sample-invoice.pdf:

Invoice Number

Order Number

Invoice Date

Due Date

Tax

Total

and so on ...

We can instruct the model to extract the required information.

To include the invoice content within the prompt we need to add a variable: {invoice}. It can be anything that makes sense..!

1. In the Template lets add some instructions.

Add instructions

1. Save .. now we need to associate the PDF with the {invoice} variable. Click on Format Prompt Values.

Associate PDF with {invoice}

1. Save .. To enable the file to be uploaded into the chat: Settings > Configuration.

Configuration

1. Enable File Upload .. and Save.

File Upload

1. Let's give it a go ..!

The sample-invoice.pdf is located in: Workshop--LLM/ Data folder.

The purpose of this Chain is to be called from some external system to parse the unstructured data source, extract the required information to be consumed further downstream - JSON Object.

Execute Chain ..

1. Add the Structured Output Parser: Output Parsers > Structured Output Parser

Add Structured Output Parser

1. Enable Autofix and click on: 'Additional Parameters'.

The Additional Parameters setting enables you to define the fields and data type in the JSON object. The model uses the description to map the value to the 'Property'.

1. Double-click in the Property / Type / description field to edit and select the type.

Property	Type	Description
invoice_id	string	Invoice Number
order_id	number	Order Number
service_type	string	Service
due_date	string	Due Date
total	number	Total

Set Property - Data Type

1. And finally ..

JSON output

This workflow could be in a number of use cases: from document classification to