.png)
Letting Data Speak!
Case Study
Enhancing Spiritual Education with AI-Powered QA System
About the Client
A prominent spiritual foundation dedicated to spreading the teachings of a revered spiritual leader.
Challenge
The foundation needed to develop an advanced question-answering system to make spiritual teachings more accessible and interactive for devotees. They faced challenges in processing and retrieving information from various unstructured data sources, including audio files and books.
Key Results
Improved information retrieval accuracy by 80% through embedding model experimentation.
Solution
JashDS implemented a comprehensive AI-powered solution to address the client's needs:
Created a robust QA evaluation pipeline using Langsmith, enabling efficient testing and iteration of the system.
Conducted extensive experiments with different datasets, comparing results within Langsmith to optimize performance.
Explored various technical parameters to enhance the system's effectiveness:
Experimented with chunk sizes (x=5, 20) to optimize text processing.
Tested multiple embedding models, including OpenAI embeddings and a Hindi fine-tuned Huggingface model, to improve language understanding and context retention.
Proposed a roadmap for future enhancements, including:
Code refactoring for efficient deployment and version control.
Further experimentation with embedding models and prompts to improve accuracy.
Expanding the knowledge base by ingesting data from books written by the spiritual leader.
Integrating voice input capabilities for improved user interaction.
Developing a web interface for broader accessibility.
Creating specialized agents for tasks such as playing kirtans and videos.
Technologies Used
Langsmith
OpenAI Embeddings
Huggingface
Natural Language Processing (NLP)
Machine Learning
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.