.png)
Letting Data Speak!
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
AI Model for Retail Shelf Monitoring
JashDS revolutionized retail shelf management for a major grocery chain by developing an AI-powered real-time monitoring system. The solution utilized advanced computer vision techniques and deep learning models to detect out-of-stock and misplaced products, significantly improving inventory accuracy and enhancing the customer shopping experience while reducing manual labor costs.
AI-Driven Candidate Screening Revolution
JashDS revolutionized a company's hiring process by developing a GenAI-powered candidate screener that reduced time-to-hire by 50% and improved hiring outcomes. The solution leverages advanced language models to conduct dynamic, role-specific interviews, automatically generating and adapting questions based on job descriptions and candidate responses.
AI-Powered Resume-Job Matching Engine
JashDS developed an AI-powered resume-job matching engine for a leading Indian job portal, processing over 1M resumes and 50k job descriptions. The solution employed BERT embeddings and HNSW algorithms to create personalized job recommendations for candidates and streamline resume screening for recruiters, significantly enhancing the job search and recruitment processes.