2024:Grooper and AI

Grooper version 2024 is GrooperAI!

Version 2024 contains a slew of features incorporating cutting edge AI technologies into Grooper. That's why we're calling this version GrooperAI. These AI based features accelerate Grooper's design and development. GrooperAI makes deployment easier, gets results with less setup, and incorporates a document search and retrieval mechanism for the first time.

GrooperAI's features include:

Large Language Model (LLM) based data extraction at scale
Document assistants allowing users to chat with their documents
A robust and speedy document search and retrieval mechanism

GrooperAI article links

Here, you will find links to all currently available articles pertaining to GrooperAI functionality.

LLM connectivity and constructs

Major LLM constructs

LLM Connector - A "Repository Option" set on the Grooper Root node. This provides connectivity to LLMs offered by OpenAI and Microsoft Azure.
Ask AI - An LLM-based Extractor Type. This extractor returns results by passing the document's text and a natural language prompt to a chat completion service (a chatbot). The chatbot uses the document's text and the prompt to respond with an answer. The chatbot's answer is the extractor's result.
AI Extract - An LLM-based Fill Method. Fill Methods are configured on Data Models and Data Sections. They perform a secondary extraction after the child Data Elements extractors and extract methods execute. Or, they can act as the primary extraction mechanism if no extractors or extract methods are configured. AI Extract extracts the Data Model using an LLM chat completion service. In many cases, the only configuration required is Data Elements added to the model. AI Extract fills in the Data Model based on what its Data Elements are named.
Clause Detection - An LLM-based Data Section Extract Method. Clause Detection is designed to locate specified types of clauses in natural language documents and return them as section instances in Grooper. The user provides one or more sample clauses, then an embeddings model determines the portion of the document (or "chunk") most similar to the samples, and Grooper returns the paragraph(s) in the chunk. Data Sections using this Extract Method can then use AI Extract to return data using only the text-content of the detected paragraph.
AI Analyst - AI Analysts facilitate document chat in Grooper. They use an LLM service's "assistants" API to create document chatbots with domain-specific knowledge. This allows Grooper users to chat with one or more selected documents. When the AI Analyst spins up a chat session, it creates an analyst and passes the document(s) text into its custom knowledge file used to answer questions.
- AI Dialogue - A Grooper Activity that automates a chat conversion in a Batch Process. The responses can then be accessed by a human operator in a Review step with a Chat Viewer.

LLM construct related properties and concepts

Parameters - These properties adjust how an LLM gives a response. For example, Temperature controls the "randomness" of an LLMs response.
Document Quoting - This property determines what text is fed to an LLM. This could be the whole document, an extracted portion of the document, a paragraph semantically similar to a given example, or the documents previously extracted Data Model values depending on its configuration.
Alignment - These properties control how Grooper highlights LLM-based results in a Document Viewer (or how it "aligns" an LLM response to what text on the document was used to give that response).
Prompt Engineering - This concept refers to the process of designing and refining natural language prompts to get a desired answer from an LLM chatbot.

AI Search

Azure AI Search - This is a larger article covering Grooper's document search and retreival mechanism. This mechanism uses Microsoft Azure AI Search to index Grooper processed documents for fast and efficient searching. Documents can be searched using their full text content (e.g. OCR from Recognize) and their extracted data (e.g. Data Model values from Extract). This article covers the following topics:

OpenAI and Azure account setup

For Azure OCR connectivity

GrooperAI can implement Azure AI Vision's Read engine for OCR. "Read" is a machine learning based OCR engine used to recognize text from images with superior accuracy, including both machine printed and handwritten text.

Azure OCR Quickstart

In Azure:

If not done so already, create an Azure account.
Go to your Azure portal
If not done so already, create a "Subscription" and "Resource Group."
Click the "Create a resource" button
Search for "Computer Vision"
Find "Computer Vision" in the list click the "Create" button.
Follow the prompts to create the Computer Vision resource.
Go to the resource.
Under "Keys and endpoint", copy the API key.

In Grooper

Go to an OCR Profile in Grooper.
For the OCR Engine property, select Azure OCR.
Paste the API key in the API Key property.
Adjust the API Region property to match your Computer Vision resource's Region value
- You can find this by going to the resource in the Azure portal and inspecting its "Location" value.

Additional resources

For Azure AI Search connectivity

GrooperAI uses Azure AI Search's API to create a document search and retrieval mechanism.

Azure AI Search Quickstart

In Azure:

If not done so already, create an Azure account.
Go to your Azure portal
If not done so already, create a "Subscription" and "Resource Group."
Click the "Create a resource" button
Search for "Azure AI Search"
Find "Azure AI Search" in the list click the "Create" button.
Follow the prompts to create the Azure AI Search resource.
- The pricing tier defaults to "Standard". There is a "Free" option if you're just wanting to try this feature out.
Go to the resource.
In the "Essentials" panel, copy the "Url" value. You will need this in Grooper.
In the left-hand navigation panel, expand "Settings" and select "Keys"
Copy the "Primary admin key" or "Secondary admin key." You will need this in Grooper.

In Grooper:

Connect to the Azure AI Search service by adding the "AI Search" option to your Grooper Repository.
From the Design page, go to the Grooper Root node.
Select the Options property and open its editor.
Add the AI Search option.
Paste the AI Search service's URL in the API Key property.
Paste the AI Search service's API key in the API Key property.
Full documentation on Grooper's AI Search capabilities can be found in the Azure AI Search article.

Additional resources

For LLM connectivity

GrooperAI can integrate with OpenAI and Microsoft Azure's LLM models to implement various LLM-based functionality. Before you are able to connect Grooper to these resources, you will need accounts setup with these providers. For information on how to set up these accounts/resources, refer to the following links:

OpenAI LLM Quickstart

In OpenAI:

If you have not done so already, create an OpenAI account.
Go to the API keys section of the OpenAI Platform.
Press the "Crate new secret key" button.
Follow the prompts to create a new key.
Copy the API key. You will not be able to view/copy it again.

In Grooper:

Connect to the OpenAI API by adding an "LLM Connector" option to your Grooper Repository.
From the Design page, go to the Grooper Root node.
Select the Options property and open its editor.
Add the LLM Connector option.
Select the Service Providers property and open its editor.
Add an OpenAI provider.
Paste the OpenAI API key in the API Key property.
Refer to the following articles for more information on functionality enabled by the LLM Connector:

Additional resources

OpenAI full documentation

Azure LLM Quickstart

Microsoft Azure offers access to several LLMs through their "Model Catalog". This includes Azure OpenAI models, Mistral AI models, Meta's Llama models, and more. To access a model from the catalog in Grooper, it must first be deployed in Azure from Azure AI Studio.

In Azure:

Create a "project" in Azure AI Studio

If not done so already, create an Azure account.
If not done so already, create a "Subscription" and "Resource Group" in the Azure portal
Go to Azure AI Studio.
From the Home page, press the "New project" button.
A dialogue will appear to create a new project. Enter a name for the project.
If you don't have a "hub", select "Create a new hub"
- For more information on "projects" and "hubs" refer to Microsoft's hubs and projects documentation.
Follow the prompts to create a new hub.
- When selecting your "Location" for the hub, be aware Azure AI services availability differs per region. Certain models may not be available in certain regions.
- When selecting "Connect Azure AI Services or Azure OpenAI", you can connect to an existing Azure OpenAI or Azure AI Services resource or create one. Azure OpenAI is a subset of Azure AI Services. If you are only wanting to connect to Azure OpenAI models, create and use an Azure OpenAI resource. If you want wider access to Azure's model catalog, you will need an Azure AI Services resource.

Once a project is created, you can deploy an LLM model.

Select your project in Azure AI Studio.
In the left-hand navigation panel, select "Deployments"
Select the "Deploy model" button.
Select the model you wish to use from the list.
- Grooper's integration with Azure's Model Catalog uses either "chat completion" or "embeddings" models depending on the feature. To better narrow down your list of options, expand the "Inference tasks" dropdown and select "Chat completion" and/or "Embeddings."
- Embeddings models are only required when using Clause Detection or the "Semantic" Document Quoting method in Grooper.
Select "Confirm"