We help global brands transform into AI driven enterprises

We transform top organizations with product design & development, data science, machine learning

Get Started

Case studies across various verticals
such as education, sports, retail etc

Us Open

Crowd Counting at US Open

We have partnered with PMY and deployed a crowd-counting visual interface at US Open 2021.

Read More
IOTech

Visual Inference on Edge

We have partnered with a leading IoT edge company to offer visual inferencing solutions.

Read More
Educompass

Building an entire EduTech platform

Lotus Labs helped realize an entrepreneur’s vision of creating an advanced scholastic planner capable of empowering educational planning. Lotus Labs’s data-driven solutions have paved the way for this product to be further implemented on a larger scale.

Read More
CHSI Technologies

Modernizing Web Technology Infrastructure

Learn how Lotus Labs helped modernize CHSI’s web technology

Read More
CHSI Technologies

Implementing the Most Suitable Dashboard and Reporting Tool

Lotus Labs built a custom analytics dashboard

Read More
PMY

Ingress Egress

The application of computer vision and deep learning in an application which allows the user to read a video and count his desired object in the desired direction. This has a phenomenal impact on retail and supply-chain sectors for various use-cases.

Read More
Automating Data Entry with LLM

Automating Data Entry with LLM: A Game Changer

In this article we talk about how data from documents can be extracted in structured format ,this helps in automating the tasks of data entry and can help in making data validation faster.

Read More
CS Wholesale and Grocers

Reinventing Workflow of a Grocery Giant (CSWG)

A Case study about how Lotus Labs partnered with C&S Wholesale Grocers (CSWG) to develop innovative products that streamline and enhance operational efficiency

Read More

Blogs related to some of our POC's
and latest trends in AI tech
‍

How to create a RAG engine with Local LLM using Ollama

To create a RAG Engine with Local LLM Using Ollama without relying on cloud-based language models. In an era where data privacy, latency, and cost are critical considerations, this article demonstrates how to build an efficient, fully local RAG system using Ollama, a powerful tool for running LLMs on your own machine. The article begins by unpacking the core architecture of a RAG pipeline, explaining how to ingest and preprocess documents, convert them into vector embeddings using models such as all-MiniLM or nomic-embed-text, and store them using chroma for fast semantic search. It then shows how to retrieve relevant context from these vectors and pass it to a locally hosted LLM like mistral or llama3 via Ollama, enabling grounded, accurate, and context-aware responses.

Read More

Decoding the PDF Maze: A Definitive Guide to Extracting Data from Textual and Scanned Documents with a Real-World Project

In the world of modern automation, PDFs are both a treasure trove and a technical trap. They contain invoices, contracts, insurance forms, bank statements, and other documents brimming with information critical to decision-making. But this information doesn’t give itself up easily. PDFs weren’t designed to be friendly to machines. They were made to look good and stay consistent. PDFs carry text, tables, images, etc. PDFs are popular for maintaining layout consistency across platforms, but are not designed for easy text extraction. Based on our required use case and the nature of PDF, it is very important to build a PDF data extraction strategy.

Read More

How Predictive Modeling for Medical Cost Estimation Has Transformed with LLMs, AI, and Agents

Predictive modeling in health insurance has long been a crucial tool for estimating medical costs, helping insurers manage risk, set premiums, and detect fraud. Traditional predictive models relied heavily on statistical techniques and machine learning (ML) algorithms trained on historical claims data. However, the emergence of Large Language Models (LLMs), AI, and autonomous AI agents has revolutionized this process, bringing unparalleled improvements in accuracy, automation, and adaptability.

Read More

Retrieve augment and generate (RAG): A technique to hack LLMs to your command

Retrieve-Augmented Generation (RAG) is a powerful technique for making Large Language Models (LLMs) more effective, accurate, and context-aware by enhancing their responses with external knowledge sources. It combines retrieval (finding relevant text from documents) with generation (LLM text creation), effectively enabling models to respond with updated, accurate information not contained in their original training data.

Read More

A simple guide to understand AI agents

According to a Gartner survey and industry trends, there is no doubt that we are in the era of AI evolution. AI agents are at the forefront of recent developments. Their ability to handle complex tasks enables full-scale automation. They break down tasks like the human mind and address these sub-tasks in a step-by-step, appropriate manner. Industry leaders such as Nvidia, Google, Meta, and Microsoft are betting on their immense potential. Even tech-averse companies are catching up with the trend of using agents to improve their bottom line.

Read More

What is Object Tracking

Object tracking is a subfield of computer vision that focuses on continuously identifying and following objects as they move across frames in a video. Unlike object detection, which identifies and locates objects in individual frames, object tracking maintains the identity of the detected objects across multiple frames, allowing for the analysis of their movement and behavior over time.

Read More

Call Quality Checks with OpenAI's GPT API

In today's digital age, customer service is crucial in shaping brand perception and ensuring customer satisfaction. OpenAI's GPT-based API emerges as a powerful tool for automating quality checks in customer call centers, transforming the way businesses ensure the efficiency and effectiveness of their customer interactions.

Read More

Dwell Time and Behavior Analysis

Dwell time and behavior analysis help businesses understand how people move through and interact with spaces. By tracking how long individuals stay in specific areas and their movement patterns, companies can optimize layouts, improve customer experiences, and enhance operational efficiency in environments like retail stores and public venues.

Read More

Disability Insurance Service

Lotus Labs transformed Disability Insurance Services' (DIS) outdated DMS platform by modernizing both the front-end and back-end, drastically improving performance and adding new features. The overhaul included updating React libraries, optimizing database queries to reduce proposal generation time from 161 seconds to 0.7 seconds, and enhancing system stability. Lotus Labs also introduced automated email and SMS campaign management tools, streamlined proposal PDF generation, and implemented secure login features.

Read More

Object Detection

Object detection, a subfield of computer vision, focuses on identifying and locating objects in images or videos. It involves classifying objects and determining their positions using bounding boxes. This capability is crucial for applications like autonomous vehicles, surveillance, retail, medical imaging, and sports. Object detection includes multi-class detection, identifying multiple types of objects, and multi-object detection, detecting multiple instances of objects.

Read More

Querying and summarizing text using LLMs

Brief overview of how query-focused multi-document summarization (QFMS) works, along with a small demo using Python. The evolution of Natural Language Processing (NLP) and computer hardware has assisted us with efficient summarization and querying, saving us a lot of time and solving the issue of redundant information.

Read More

Decoding Visual Relationships: Analyzing Stacked Boxes with OpenCV Edge Detection

In the realm of computer vision, the analysis of stacked objects is a fascinating area that holds immense potential for various applications, from industrial automation to robotics. In this article, we delve into a specific scenario involving stacked boxes, utilizing the power of OpenCV's edge detection to unravel the visual relationships and distances between these boxes.

Read More

Connect With Us

We transform top organizations with product design & development, data science, machine learning, and artificial intelligence.

Get Started