Using memory with LLM applications in production
This talk will review how you can use Metal to give your LLM chatbots both short and long-term memory.
Videos
Lessons Learned from Building a Managed RAG Solution
This talk will discuss technical and business lessons learned from building a managed Retrieval Augmented Generation solution into Voiceflow.
Large Language Models for Program Synthesis
This talk will be about large language models for code generation.
Gorilla: Large Language Model Connected with Massive APIs
This talk will introduce the Gorilla project, designed to connect LLMs with various services and applications exposed through APIs.
Trends and Applications of AI/ML and Analytics in Sports
This overview talk will be about sports analytics and using AI/ML for player performance, business operations, and recruitment statistics.
Best Security Practices for the LLMs
This talk will explore potential risks, break down advanced defense methods, and share the latest on keeping Large Language Models safe.
Go Beyond Chatbot - Emerging Patterns in Generative AI Apps
This talk will share some reference architectures and demos for emerging Generative AI applications and use cases.
Leveraging Large Language Models for Enterprise Usage
This talk will discuss foundation and ChatGPT-style models, GenAI and LLM technology at NVIDIA, shortcomings, and proposed guardrails.
Best practices for building LLM-based applications
During the talk, we will review the existing tools and see how to move from development to production without a headache.
LlamaIndex: How to use LLMs to Interface with Multiple Data Sources
This talk will dive into “data frameworks” like LlamaIndex, and demonstrate how to create hierarchical indexes from different data sources.
Rise in the use of synthetic data for regulated industries
This talk will discuss synthetic data, some impactful use cases associated with it, and the challenges companies face while harnessing it.
Multilingual Semantic Search
This talk will discuss why multilingual semantic search is amazing, how respective models are trained, and the new use cases this unlocks.