ToOne - Transforming Data Analysis with AI

Prompt Engineering

MVP of AI-based product

NLP

GPT-4o mini

In use

Embeddings

In use

Language

TypeScript

Language

React

Front End

Weaviate

Database

Case Summary

How can businesses rapidly extract, understand, and use insights buried within oceans of unstructured data? Think about contracts, specifications, instruction manuals, policies… To address this challenge, we've created 'ToOne', an AI-powered business analyst application designed to retrieve precise information from extensive documentation in mere seconds. Simply by typing a query into a chat interface, users can get a precise answer instantly. With ToOne, insights are just one query away.

Custom-created document database

Users can upload all types of business documentation (such as documents, spreadsheets, Azure DevOps/JIRA Wiki, Azure DevOps/JIRA tickets, and emails) into the application. ToOne combines all documentation into one comprehensive source for each specific project.

Source reviewing

To ensure reliability, each response is accompanied by a link to its originating source.

Estimate 10.12.2023.xls

Ticket 2345

Technical Explanation of the main features

How Does ToOne search for the right answer?

Uploading and pre-processing documents:

Documents are organized into projects, with metadata describing them to help resolve potential consistency issues. To ensure optimal processing, we prepare documents for embedding by splitting them into smaller chunks first.

Embedding process

The app converts individual chunks of documents into embeddings, and then stores them in a vector database. Options for embedding include OpenAI API and local open-source models. The numerical form of embeddings allows AI models to easily understand the text context, predict similarities, and provide accurate responses.

Questions & Answers

Users can interact with ToOne by asking questions, which the application embeds in order to search the database for the most suitable responses. This contextual search process involves ranking top responses, which are sent to OpenAI for interpretation by the LLM.

How Is the Azure DevOps integration set up?

Login & data security

Utilizing OAuth2, a protocol commonly used in Google’s services, allows users to connect to their AzDo organization within the app. We utilize authorization tokens to foster secure and authenticated access to the Rest API of AzDO, thereby reducing constant reauthorization.

User permissions

Permissions are primarily managed by AzDo. Two tiers of permissions are applied – one for the admin (Project Manager, Business Analyst, etc.) and another for general users. The flexibility permits organizations to have different project setups and granular access to their organization’s data. The current system supports embedding Wiki, tickets, comments, descriptions, and other fields.

Main Challenges

Estimate the project

Avoiding GPT Hallucinations.

We aimed for precise answers from documents without compromising on the conversational human-like outputs, in other words, minimal hallucinations from GPT models. To achieve this, we relied on several techniques to prompt, such as assigning roles and demonstrating examples. This approach led to an improvement in output accuracy.

Minimal Hallucinations

OpenAI Embeddings as a technical solution.

We opted for OpenAI Embeddings, in contrast to other AI techniques, due to its ability to process vast amounts of data — an impressive feature that provides a strategic advantage in data management.

Extensive data processing

Document Preparation for embedding.

The process of preparing business documents for effective embedding brought another hurdle our way. Our solution involved breaking vast documents into smaller, digestible chunks. This included formatting those documents — deleting empty lines and tidying up the appearance.

Document formatting

Data Synchronization with AzDo.

Handling extensive datasets demands intelligent data handling strategies due to REST API limitations. We are looking into ways to sync only data changes, a feat we find both challenging and crucial.

Azdo API

Next steps

Our roadmap to expand ToOne's capabilities includes:

Broader Third-Party Integration.

As the application already successfully integrates with AzDo, connecting it with other popular platforms such as Google Workspace, Jira, and GitHub can extend its versatility and utility. This will enable users to retrieve data from various sources, simplifying the data analysis process.