Case Study: Shell Trains Custom AI Chatbot With NVIDIA NeMo to Uplevel Operations – NVIDIA

Welcome to the forefront of conversational AI as we explore the fascinating world of AI chatbots in our dedicated blog series. Discover the latest advancements, applications, and strategies that propel the evolution of chatbot technology. From enhancing customer interactions to streamlining business processes, these articles delve into the innovative ways artificial intelligence is shaping the landscape of automated conversational agents. Whether you’re a business owner, developer, or simply intrigued by the future of interactive technology, join us on this journey to unravel the transformative power and endless possibilities of AI chatbots.
Visit your regional NVIDIA website for local content, pricing, and where to buy partners specific to your country.
AI-driven platform for life sciences research and discovery
Fully managed end-to-end AI platform on leading clouds
Build, customize, and deploy multimodal generative AI
Integrate advanced simulation and AI into complex 3D workflows
Guide for using NVIDIA NGC private registry with GPU cloud
Accelerated, containerized AI models and SDKs
Modernizing data centers with AI and accelerated computing
Enterprise AI factory for model development and deployment
Architecture for data centers that transform data into intelligence
A supercomputer purpose-built for AI and HPC
Advanced functional safety and security for edge AI
Accelerated computing with modular servers
Scalable data center infrastructure for high-performance AI
Leading platform for autonomous machines and embedded applications
Powerful in-vehicle computing for AI-driven autonomous vehicle systems
AI-powered computing for innovative medical devices and imaging
RTX graphics cards bring game-changing AI capabilities
Thinnest and longest lasting RTX laptops, optimized by Max-Q
Smooth, tear-free gaming with NVIDIA G-SYNC monitors
Neural rendering tech boosts FPS and enhances image quality
Advanced platform for full ray tracing and neural rendering
Ultimate responsiveness for faster reactions and better aim
AI PCs for gaming, creating, productivity and development
High performance laptops and desktops, purpose-built for creators
RTX-powered cloud gaming. Choose from 3 memberships
Optimize gaming, streaming, and AI-powered creativity
AI-enhanced voice and video for next-level streams, videos, and calls
World-class streaming media performance
The engine of the new industrial revolution
High performance, scalability, and security for every data center
Performance and energy efficiency for endless possibilities
RTX graphics cards bring game-changing AI capabilities
Accelerating professional AI, graphics, rendering and compute workloads
Virtual solutions for scalable, high-performance computing
GPU-powered laptops for gamers and creators
High performance laptops purpose-built for creators
Accelerate professional AI and visual computing from anywhere
Accelerated networks for modern workloads
Software-defined hardware accelerators for networking, storage, and security
Ethernet performance, availability, and ease of use across a wide range of applications
High-performance networking for super computers, AI, and cloud data centers
Networking software for optimized performance and scalability
IO subsystem for modern, GPU-accelerated data centers
A Grace Blackwell AI Supercomputer on your desk
Accelerate innovation and productivity in AI workflows
Powerful AI, graphics, rendering, and compute workloads
Accelerate professional AI and visual computing from anywhere
Simplify AI development with NVIDIA AI Workbench on GPUs
Explore NVIDIA’s AI models, blueprints, and tools for developers
AI and HPC software solutions for data center acceleration
Monitor and manage GPU performance in cluster environments
Explore NVIDIA developer tools for AI, graphics, and HPC
Discover GPU-optimized AI, HPC, and data science software
Optimize enterprise GPU management
Accelerate AI and HPC workloads with NVIDIA GPU Cloud solutions
Enhance multi-display productivity with NVIDIA RTX Desktop Manager
Creative tools and AI-powered apps for artists and designers
AI-powered audio and video enhancement
Add intelligence and efficiency to your business with AI and machine learning
Build AI agents designed to reason, plan, and act
Powering a new class of enterprise infrastructure for AI
Enables natural, personalized interactions with real-time speech AI
AI-driven solutions to strengthen cybersecurity and AI infrastructure
Iterate on large datasets, deploy models more frequently, and lower total cost
Instantly run and deploy Generative AI
Drive breakthrough performance with AI-enabled applications and services
Powering AI, HPC, and modern workloads with NVIDIA
Bringing enterprise storage into the era of agentic AI
Accelerated computing uses specialized hardware to boost IT performance
On-demand IT resources and services, enabling scalability and intelligent insights
Accelerate the scaling of AI across your organization
Accelerate AI with MLOps
High speed ethernet interconnect solutions and services
Save energy and lower cost with AI and accelerated computing
NVIDIA virtual GPU software delivers powerful GPU performance
Streamline building, operating, and connecting metaverse apps
Develop real-time interactive design using AI-accelerated real-time digital twins
Harness the power of large-scale, physically-based OpenUSD simulation
Bring state-of-the-art rendering to professional workflows
Innovative solutions to take on your robotics, edge, and vision AI challenges
Enablies researchers to visualize their large datasets at interactive speeds
AI-defined vehicles are transforming the future of mobility
Transform workflows with immersive, scalable interactions in virtual environments
Discover NVIDIA’s HPC solutions for AI, simulation, and accelerated computing
Boost accuracy with GPU-accelerating HPC and AI
Enables researchers to visualize large datasets at interactive speeds
Accelerate simulation workloads
Fast-tracking the advancement of scientific innovations with QPUs
Innovative solutions to take on robotics, edge, and vision AI challenges
GPU-accelerated advances in AI perception, simulation, and software
Bring the power of NVIDIA AI to the edge for real-time decision-making solutions
Transform data into valuable insights using vision AI
AI-enhanced vehicles are transforming the future of mobility
Essential data center tools for safe autonomous vehicle development
Explore high-fidelity sensor simulation for safe autonomous vehicle development
Develop automated driving functions and immersive in-cabin experiences
State-of-the-art system for AV safety, from the cloud to the car
AI-driven platform for life sciences research and discovery
Fully managed end-to-end AI platform on leading clouds
Build, customize, and deploy multimodal generative AI
Integrate advanced simulation and AI into complex 3D workflows
Guide for using NVIDIA NGC private registry with GPU cloud
Accelerated, containerized AI models and SDKs
Modernizing data centers with AI and accelerated computing
Enterprise AI factory for model development and deployment
Architecture for data centers that transform data into intelligence
A supercomputer purpose-built for AI and HPC
Advanced functional safety and security for edge AI
Accelerated computing with modular servers
Scalable data center infrastructure for high-performance AI
Leading platform for autonomous machines and embedded applications
Powerful in-vehicle computing for AI-driven autonomous vehicle systems
AI-powered computing for innovative medical devices and imaging
RTX graphics cards bring game-changing AI capabilities
Thinnest and longest lasting RTX laptops, optimized by Max-Q
Smooth, tear-free gaming with NVIDIA G-SYNC monitors
Neural rendering tech boosts FPS and enhances image quality
Advanced platform for full ray tracing and neural rendering
Ultimate responsiveness for faster reactions and better aim
AI PCs for gaming, creating, productivity and development
High performance laptops and desktops, purpose-built for creators
RTX-powered cloud gaming. Choose from 3 memberships
Optimize gaming, streaming, and AI-powered creativity
AI-enhanced voice and video for next-level streams, videos, and calls
World-class streaming media performance
The engine of the new industrial revolution
High performance, scalability, and security for every data center
Performance and energy efficiency for endless possibilities
RTX graphics cards bring game-changing AI capabilities
Accelerating professional AI, graphics, rendering and compute workloads
Virtual solutions for scalable, high-performance computing
GPU-powered laptops for gamers and creators
High performance laptops purpose-built for creators
Accelerate professional AI and visual computing from anywhere
Accelerated networks for modern workloads
Software-defined hardware accelerators for networking, storage, and security
Ethernet performance, availability, and ease of use across a wide range of applications
High-performance networking for super computers, AI, and cloud data centers
Networking software for optimized performance and scalability
IO subsystem for modern, GPU-accelerated data centers
A Grace Blackwell AI Supercomputer on your desk
Accelerate innovation and productivity in AI workflows
Powerful AI, graphics, rendering, and compute workloads
Accelerate professional AI and visual computing from anywhere
Simplify AI development with NVIDIA AI Workbench on GPUs
Explore NVIDIA’s AI models, blueprints, and tools for developers
AI and HPC software solutions for data center acceleration
Monitor and manage GPU performance in cluster environments
Explore NVIDIA developer tools for AI, graphics, and HPC
Discover GPU-optimized AI, HPC, and data science software
Optimize enterprise GPU management
Accelerate AI and HPC workloads with NVIDIA GPU Cloud solutions
Enhance multi-display productivity with NVIDIA RTX Desktop Manager
Creative tools and AI-powered apps for artists and designers
AI-powered audio and video enhancement
Add intelligence and efficiency to your business with AI and machine learning
Build AI agents designed to reason, plan, and act
Powering a new class of enterprise infrastructure for AI
Enables natural, personalized interactions with real-time speech AI
AI-driven solutions to strengthen cybersecurity and AI infrastructure
Iterate on large datasets, deploy models more frequently, and lower total cost
Instantly run and deploy Generative AI
Drive breakthrough performance with AI-enabled applications and services
Powering AI, HPC, and modern workloads with NVIDIA
Bringing enterprise storage into the era of agentic AI
Accelerated computing uses specialized hardware to boost IT performance
On-demand IT resources and services, enabling scalability and intelligent insights
Accelerate the scaling of AI across your organization
Accelerate AI with MLOps
High speed ethernet interconnect solutions and services
Save energy and lower cost with AI and accelerated computing
NVIDIA virtual GPU software delivers powerful GPU performance
Streamline building, operating, and connecting metaverse apps
Develop real-time interactive design using AI-accelerated real-time digital twins
Harness the power of large-scale, physically-based OpenUSD simulation
Bring state-of-the-art rendering to professional workflows
Innovative solutions to take on your robotics, edge, and vision AI challenges
Enablies researchers to visualize their large datasets at interactive speeds
AI-defined vehicles are transforming the future of mobility
Transform workflows with immersive, scalable interactions in virtual environments
Discover NVIDIA’s HPC solutions for AI, simulation, and accelerated computing
Boost accuracy with GPU-accelerating HPC and AI
Enables researchers to visualize large datasets at interactive speeds
Accelerate simulation workloads
Fast-tracking the advancement of scientific innovations with QPUs
Innovative solutions to take on robotics, edge, and vision AI challenges
GPU-accelerated advances in AI perception, simulation, and software
Bring the power of NVIDIA AI to the edge for real-time decision-making solutions
Transform data into valuable insights using vision AI
AI-enhanced vehicles are transforming the future of mobility
Essential data center tools for safe autonomous vehicle development
Explore high-fidelity sensor simulation for safe autonomous vehicle development
Develop automated driving functions and immersive in-cabin experiences
State-of-the-art system for AV safety, from the cloud to the car
Energy
Shell International Exploration and Production Inc. (Shell), a global leader in the energy industry, has leveraged NVIDIA NeMo™ to empower its journey toward developing a custom AI chatbot for chemical domain expertise. This innovative solution has the potential to significantly enhance employees’ productivity by streamlining search processes, improving decision-making, and supporting research and development in production environments.
Shell
Generative AI / LLMs
NVIDIA NeMo
NVIDIA NeMo Curator
NVIDIA NeMo Framework
Shell manages an immense and complex body of scientific data that underpins business operations. Rapid access to accurate information is essential across Shell’s R&D organization.
Beyond data management, the company also aims to enhance technology staff’s day-to-day activities and decision-making, ensuring teams can efficiently retrieve the right information to drive productivity and operational effectiveness.
To achieve this goal, Shell leveraged NVIDIA AI to develop custom models capable of understanding Shell’s internal research, with an initial focus on the chemistry domain, while delivering precise, context-aware responses.
Shell
To achieve higher accuracy for its domain-specific LLM tailored to the energy industry, Shell focused on curating high-quality training data as the foundation of its AI solution. The development process began with the curation and preprocessing of a vast dataset of chemistry documents. Initially, Shell had access to 300,000 technical documents collected over decades. These documents cover various technical domains and were curated down to 154,000 high-quality documents using the NVIDIA NeMo Curator.
The curation process involved several steps, including exact and fuzzy deduplication to remove repeated or near-duplicate content. Shell also applied quality filters, removing documents with insufficient information or poor formatting, and used language detection to exclude non-English content. Additionally, domain classification was used to select documents for building domain-specific benchmarks.
Once the dataset was curated, Shell went beyond retrieval-augmented generation (RAG) and used the NVIDIA NeMo framework to perform domain-adaptive pretraining (DAPT) and supervised fine-tuning (SFT) to enhance the model’s domain-specific knowledge and accuracy. DAPT allowed the model to truly understand the unique context and terminology of the chemical industry. At the same time, SFT further refined the model’s performance by training it on labeled data specific to Shell’s needs. Leveraging the parallelism techniques available through NeMo, Shell accelerated the model training time (millions of GPU hours) by 20% compared to other open-sourced frameworks.
Retrieving accurate information from enterprise knowledge sources can be challenging for RAG because standard language models often misinterpret user queries, matching them with broad, generic information instead of domain-specific insights. Adapting LLMs to industry-specific language helps bridge this gap and improves answer accuracy and conversation quality. This need for precision drove Shell to develop in-house capabilities, not available in market products, for customizing LLMs, leading to the company’s collaboration with NVIDIA.
With the AI-powered chatbot developed by Shell, technology staff would have the possibility to quickly access detailed chemical documents and data, reducing the time required for these tasks and reducing the risk of errors. By streamlining knowledge retrieval, the AI chatbot can enhance gaining insights and making decisions in the R&D space, supporting both innovation and operational efficiency.
Aside from enhanced information retrieval, the custom LLM can also be utilized for technical document analysis, helping streamline workflows across departments.
By continuously refining the model through real-world interactions, Shell is positioning its AI ecosystem as an adaptive intelligence layer, transforming enterprise knowledge management into a dynamic and accessible resource.
Looking ahead, Shell plans to further improve the capability of domain-adapted LLM by expanding the training dataset and developing more diverse and challenging evaluation tasks. Together with enhancing the text-to-text model, the ambition is to unlock the multimodal capabilities of the AI chatbot. This will enable the chatbot to handle and process various types of data, including images and videos.
The addition of multimodal capabilities is expected to provide more comprehensive and contextually rich information, which can be particularly valuable for complex decision-making processes.
These enhancements are anticipated to further drive productivity and operational efficiency, solidifying Shell’s commitment to leveraging ahead-of-market advanced AI technologies for the benefit of its operations.
Build, customize, and deploy multimodal generative and agentic AI applications using NVIDIA NeMo.