Vision Pipelines in Production: Serving and Optimizations - AI in Production
Explore vision model production: fine-tuning LORAs, upscaling pipelines, constraints-based generations, and step-by-step enhancements for optimal performance and quality in production-ready services.
RAG and RecSys - Parallels in Retrieval Quality Improvement
Explore parallels between RAG and recommender systems, focusing on improving retrieval quality through hybrid reranking techniques using LanceDB in this concise AI production talk.
Fine-Tuning LLMs: Helix for Text and Image AI Models
Explore Helix for fine-tuning text and image AI using open-source models. Learn about challenges in creating a fine-tuning service platform from a software infrastructure expert.
Graphs and Language - AI in Production Lightning Talk
Explore building knowledge graphs with language models and small language models to improve quality. Learn about NLP, recommender systems, and blockchain applications in digital solutions.
Lessons from Building LLM-based Social Media Products
Explore Gen AI product development for social media: from ideation to success measurement. Learn efficient strategies for user-centric AI products, hardware planning, and building user trust.
Building Conversational AI Agents with Voice
Discover tips for creating conversational AI agents with voice, focusing on user experience. Learn from a Deepgram product manager about building effective speech-to-text interactions.
Explaining ChatGPT to Anyone in 10 Minutes
Learn to effectively communicate the complexities of ChatGPT and generative AI to diverse audiences using a simple three-part framework, enhancing public understanding and fostering responsible AI development.
LLMOps and GenAI at Enterprise Scale - Challenges and Opportunities
Explore challenges and opportunities in deploying GenAI solutions at enterprise scale. Learn about LLMOps, model selection, emerging stacks, and best practices for robust implementation.
The Role of ML Engineers in the Era of GPT-4 and BARD
Explore the evolving role of ML engineers amid the rise of large language models. Learn to evaluate API suitability, address privacy concerns, and adapt skills for future projects.
Efficiently Scaling and Deploying Large Language Models
Explore efficient scaling and deployment of LLMs, focusing on decentralized approaches, custom model training, and practical insights for building and implementing AI solutions.
Solving LLM Data Problems with Vector Databases - Part 2
Explore vector databases' role in LLM apps, focusing on solving data issues and democratizing access to this technology for efficient billion-scale vector search.
Navigating Through the Generative AI Landscape
Explore the latest trends in Generative AI, gaining practical insights for startups to leverage advancements and enhance products in this dynamic field.
Challenging Traditional Machine Learning Principles with LLMs - Part 2
Challenge traditional ML principles and explore how LLMs are reshaping methodology. Discover which rules still apply and which are becoming obsolete in the era of self-supervising, extrapolating models.
Enabling Defense Missions with Local LLMs - Part 2
Explore LeapfrogAI, an open-source toolkit for deploying and managing LLMs in sensitive, regulated environments, addressing challenges in defense missions and air-gapped systems.
Taming AI Product Development Through Test-driven Prompt Engineering
Explore test-driven development's crucial role in prompt engineering for AI systems. Learn to create reliable, predictable AI products through effective TDD practices.
LLM-based Feature Extraction for Operational Optimization
Explore LLM-based feature extraction for operational optimization in AI applications. Learn how to leverage GPT-3.5 for efficient content understanding and improved accuracy in product development.
LLMs vs LMs in Production - Key Differences in Using 100M vs 100B Parameter Models
Explore key differences between using 100M vs 100B parameter models in production, covering MLOps processes, prompt testing, automated training, and real-time inference for conversational AI.
Product Strategy for LLM Features When LLM Isn't Your Product
Discover strategies for integrating LLM features into existing products, focusing on practical use cases beyond chatbots. Learn to plan, roadmap, and measure success of LLM implementations in various industries.
Building a Python-Centric Feature Platform to Power Production AI Applications
Explore Tecton's journey in developing a Python-based platform for powering large-scale real-time AI applications. Learn about reliable solutions for productionizing AI using only Python skills.
Graduating from Proprietary to Open Source Models in Production
Explore the transition to open source ML models for production, focusing on security, performance, and scalability. Learn how AI companies leverage these models for core workloads.
Productionizing Health Insurance Appeal Generation - AI in Production
Explore fine-tuning models for health insurance appeals, cloud resource utilization, and on-premises Kubernetes deployment. Learn about unexpected challenges in server setup and graphics card installation.