.png)
Letting Data Speak, AI Act!
Case Study
RAG Based Chatbot for Publication Discovery and Q&A
About the Client
A leading trusted platform empowering AI professionals to share their projects, insights, and innovations with the global AI community.
Challenge
Publication hub provides a space for individuals and teams to showcase their work, collaborate with peers, and contribute to the advancement of AI in a responsible and accessible way.
Key Results
Publication Discovery on platform
Publication Engagement
Code Understanding and accessibility
Publication Discovery
Need to discover publications related to the question/topic asked
Ex - Give me publications related to RAG. Bot should only return publications related to RAG from all the publications
Publication Engagement
Engage with publications through natural language queries, making technical content more accessible and discoverable
Ex - What is RAG? - It should give definition of RAG
Code Understanding
Q&A for the Python code associated with the publication to understand the code
Solution
The JashDS team developed an Intelligent assistant (RAG based system) that enables users to interact with AI/ML publications through natural language queries
Technologies Used
User Layer: Next.js frontend with intuitive chat interface
Processing Layer: AWS Lambda implementing Retrieval-Augmented Generation (RAG)
Data Layer: OpenSearch vector database, S3 document storage, DynamoDB conversation history
AI Layer: Anthropic Claude 3 Sonnet via Amazon Bedrock for natural language understanding
Implemented a configuration-driven charge calculation system allowing utility providers to easily modify rates and rebates.
Other Case Study Items
Revolutionizing Personal Loans with AI-Driven Underwriting
A leading Indian personal loan provider revolutionized their underwriting process by leveraging AI and machine learning to automate 80% of loan decisions. By integrating social and financial data into a sophisticated predictive algorithm, the company drastically reduced decision times to seconds expanded access to underserved segments, and achieved lower default rates compared to human underwriters.
Artificial Intelligence - Powered Tyre Dimension Extraction System
JashDS developed an AI-powered computer vision system for a leading automotive e-commerce platform, enabling accurate extraction of tire dimensions from images. The solution, which increased conversion rates by 25% and reduced customer support inquiries by 80%, utilized advanced technologies such as YoloV8 for instance segmentation and custom-designed augmentation techniques to simplify the online tire purchasing process.
Enhanced Jira Data Analysis for Strategic Insights
JashDS developed a flexible framework for analyzing Jira project data that is capable of handling varying export structures and custom fields. The solution leveraged GenAI and LLM technologies to provide actionable insights, identify productivity trends, and uncover potential risks across diverse software projects, resulting in a ___% improvement in team efficiency and a ___% increase in successful project outcomes.