For a client building generative AI tools for real estate
The Problem
Offering memorandums (OMs) are financial documents about real-estate properties. Investors usually go through these documents before deciding whether to buy a property or not. The goal of this project was to build a chatbot that can answer questions from OMs, making it easier for investors to find relevant information.
Our Solution
We built a chatbot using GPT 3.5 and LangChains. This is a breakdown of our approach:
1. The first step is to extract all of the text from the OM (which is a PDF document). Since an OM can contain normal text, images, figures and tables we need to handle all of these differently. We use an AI-based page-layout understanding module to identify tables, images, paragraphs etc. separately and then extract text from them separately.
2. Once the text is extracted, it is structured and stored into Pinecone vector databases.
3. When a user enters a query (e.g., ‘what is the projected rent of this property’), we use LangChains to identify the most relevant sections that may contain the answer to this query.
4. This ‘context’ is then fed to GPT, which uses it to answer the user’s query
5. Our prompts for GPT are specifically designed to make sure that GPT does not hallucinate and give wrong answers
Results
Our AI model:
- Accurately extracts relevant information from OMs, reducing investor decision-making time.
- Provides accurate and reliable answers, avoiding misinformation or incorrect data.
- Enhances user experience by allowing them to converse in multiple languages including through audio messages.
Overview of the dashboard that shows the information extracted by our AI model
Additional information that the AI model extracts
One of our clients - a nutritional platform - faced a challenge that some of the meal plans that they were recommending were being rejected by customers. This was impacting sales and hurting their brand reputation. They were interested in addressing this by using an AI model that could
Read More
Monitoring and ensuring appropriate temperatures of stocks such as food items is critical. Variations in temperature can end up damaging the stock. One of our clients who provide smart temperature monitoring services, wanted a system for cold storage areas and refrigerators that could automatically raise alarms if the temperature
Read More
Our client wanted to use AI to automatically extract data from invoices and receipts. The extracted data can then be programmatically added to an accounting software such as Quickbooks. This eliminates the need for manual data entry - which is significant for larger companies that may need to process
Read More
