Introducing Arize-Phoenix and OpenInference for AI Evaluation and Observability
Explore AI observability and evaluation with OpenInference and Arize-Phoenix. Learn practical techniques for incorporating LLMs to guard against hallucinations and poor retrieval.
Mitigating RAG Hallucinations with Aporia Guardrails
Explore techniques to reduce hallucinations in Retrieval-Augmented Generation (RAG) systems using Aporia Guardrails, enhancing AI reliability and accuracy.
Evaluation Engineering: Iterative Strategies to Testing Prompts
Explore iterative strategies for testing prompts, including backtesting and regression testing, to enhance evaluation engineering in prompt development.
Private, Local AI: Running Open-Source LLMs Locally
Explore private AI applications running open-source LLMs locally on personal devices. Learn about encrypted environments for fine-tuning models on sensitive data.
The Journey of Building a Leading Open Source LLM Security Toolkit
Explore the development of LLM Guard, an open-source toolkit for securing LLM applications in production. Learn about challenges, solutions, and real-world implementations for confident LLM deployment.
The Secret Sauce for Deploying LLM Applications into Production
Discover the key to deploying LLM applications in production through structured evaluation. Learn to log, evaluate, and make critical decisions for successful AI implementation in enterprise settings.
Towards Robust GenAI: Techniques for Evaluating Enterprise LLM Applications
Discover emerging automated evaluation solutions for LLMs, combining micro evaluators and human feedback to confidently deploy AI in enterprise applications.
Efficiently Fine-Tune and Serve Your Own LLMs
Learn to efficiently fine-tune and deploy large language models, optimizing performance and resource utilization for production environments.
Finding Training Inefficiencies with CentML DeepView
Optimize deep learning model training with DeepView. Gain insights into performance bottlenecks, enhance resource utilization, and achieve significant throughput improvements through intuitive visualizations and targeted optimizations.
Evaluating LLMs and RAG Pipelines at Scale
Explore techniques for evaluating Large Language Models and RAG pipelines in production, focusing on Valor, an open-source evaluation service for rigorous real-world testing.
The Best Component for Your RAG System - Optimizing with AutoRAG
Optimize RAG systems automatically with AutoRAG. Boost performance by finding the ideal pipeline for your data and use-case through efficient evaluation of various modules.
Why AI Apps Don't Work in Production: AI Reliability Survey
Explore AI reliability challenges in production, survey techniques for improvement, and gain insights from 18 months of solving AI engineering reliability issues.
Deploying GenAI Applications to Enterprises: Custom Evaluation Models and LLMOps Workflow - MLOps World
Explore challenges and solutions in deploying conversational AI to enterprises, focusing on accuracy optimization, LLMOps workflows, and infrastructure requirements for scalable implementation.
From Idea to Production: AI Infrastructure for Scaling LLM Applications
Explore strategies for scaling LLM applications from beta to production, addressing challenges and building adaptable AI infrastructure for evolving models and workflows.
Lessons Learned from Scaling Large Language Models in Production
Discover strategies for scaling LLMs in production, covering performance profiling, GPU optimization, and guardrail interactions with real-world examples.
Data Versioning in Generative AI - A Pathway to Cost-effective Machine Learning
Explore data versioning strategies for generative AI, focusing on cost-effective techniques to minimize processing time and API calls while enhancing collaboration and efficient versioning of annotations and embeddings.
Running Prompts at CI: Why It Doesn't Make Your GenAI App Enterprise-Ready
Explore challenges and best practices for deploying GenAI applications in enterprise environments beyond basic CI prompt testing.
From Model T to Machine Learning: Ford's MLOps and Hybrid Infrastructure Strategy
Explore Ford's AI/ML platform journey, from inception to present day. Learn about product strategy decisions, challenges, and organizational hurdles in modernizing a traditional company.
Apache Airflow: Where Data Engineers and ML Engineers Meet
Explore production-quality Generative AI pipelines using Apache Airflow. Learn to orchestrate workflows, integrate data engineering, and implement MLOps best practices for robust AI applications.
Beyond the Model Zoo - Optimizing Foundation Models for Your Application
Optimize foundation models for specific applications, exploring techniques beyond pre-trained models to enhance performance and efficiency in machine learning projects.
Defining Open-Source AI: Challenges and Opportunities in the Evolving Landscape
Explore the complexities of defining Open-Source AI, balancing innovation with core open-source principles in the evolving AI landscape. Engage in shaping a definition that reflects technological progress.