DEVPOST Challenge - Nvidia / Dell
- Bobbi Muscara
- Sonu Mondal
Elevator pitch :
Are you tired of sifting through endless documents to find the information you need? Our Hyperledger Labs project is here to revolutionize your search process. We’re developing an open-source conversational AI tool designed to streamline your workflow by delivering context-specific answers swiftly and accurately.
Our prototype features a chatbot that leverages a RESTful API and requires GPU resources for optimal performance. Built with Python, this project serves as a versatile framework that other communities and organizations can adapt to their needs. By employing Retrieval Augmented Generation (RAG), our system enhances answer quality by integrating knowledge from external databases, like vector databases.
The application’s architecture supports two key workflows: data ingestion and chat interaction. During ingestion, the system loads context documents and constructs a vector database from resources such as online guides and wiki pages. Post-ingestion, the chatbot is primed to respond to user queries efficiently.
Currently utilizing the open-source HuggingFace Zephyr-7b-beta model, we plan to explore other models to further improve performance. Users can interact with the system via HTTP requests, with future plans to offer UI samples for enhanced accessibility. Join us every Monday for a public meeting to learn more about our progress and contributions to the Hyperledger Labs community.
NVIDIA AI
Hosted by Dell and NVIDIA, this hackathon invites developers and data scientists to build groundbreaking Generative AI projects using NVIDIA AI Workbench. AI Workbench is an all-in-one solution for developing, customizing, and using GPU enabled workflows and applications.
NVIDIA AI Workbench is a free, user-friendly development environment manager that streamlines data science, ML and AI projects on systems of choice – PC, workstation, datacenter, or cloud. Users can develop, test, and prototype projects locally on Windows, macOS and Ubuntu and easily transfer development environments and computational work between systems (local and remote) to optimize cost, availability, and scale.
Build something cool in AI Workbench and then share it on GitHub. Demonstrate how AI Workbench can be used to build and deliver applications for a wide range of tasks and workflows. Provide a user-friendly solution for anything from data science to generative AI applications. Check out some of our existing projects on NVIDIA’s GitHub. Even better, AI Workbench will let other people run it on their own systems, from local machines like laptops and workstations, to remote systems like servers, cloud instances, and VMs.
For an added twist, tackle one of our Bonus Categories and vie for a special prize! Dive into Enterprise Generative AI to streamline workflows and automate complex processes, explore Enterprise Data Analysis to enhance decision-making and security, or venture into Enterprise Computer Vision to transform industries from agriculture to retail. Get inspired, get coding, and show us how far your creativity can take you!
Check out the NVIDIA Developer Program to get free access to the latest NVIDIA tools, SDKs, and NIM microservices that can be used with AI Workbench.