18 min read

This tutorial delves into using Graph RAG (Retrieval-Augmented Generation) techniques for domains rich in entities, such as legal and healthcare sectors. Prerequisites include understanding of RAG and graph database concepts.

20 min read

This tutorial explores the tuning of Pgvector indexes using HNSW and IVF methods, specifically for optimizing search capabilities in e-commerce platforms. Prerequisites include basic knowledge of PostgreSQL and vector search concepts.

15 min read

This tutorial covers strategies for implementing cold-start embeddings for new tenants in SaaS applications, focusing on leveraging existing data and models to generate initial embeddings. Prerequisites include familiarity with machine learning concepts and access to a dataset for training.

20 min read

This tutorial covers the implementation of hybrid search combining BM25 and dense re-ranking techniques for e-commerce applications. Prerequisites include knowledge of search algorithms and e-commerce systems.

16 min read

This tutorial explores the use of synthetic data to enhance classifier performance in healthcare applications. Prerequisites include a basic understanding of machine learning and healthcare data.

14 min read

This tutorial discusses implementing metadata filters and access control lists (ACLs) for secure and efficient data retrieval in financial services. Prerequisites include basic knowledge of data security and retrieval systems.

18 min read

This tutorial examines the effects of quantization on retrieval quality in medical data applications. Prerequisites include knowledge of machine learning and data retrieval systems.

15 min read

This tutorial focuses on optimizing chunking strategies for legal documents to enhance retrieval accuracy. Prerequisites include familiarity with document processing and retrieval systems.

15 min read

This tutorial outlines best practices for handling Personally Identifiable Information (PII) in retrieval-augmented generation (RAG) pipelines within healthcare settings. It emphasizes the importance of compliance and security measures. Prerequisites include knowledge of healthcare data regulations and RAG systems.

12 min read

This tutorial provides a comprehensive guide on implementing cost controls in retrieval-augmented generation (RAG) systems, focusing on the balance between batching and streaming tokens in e-commerce applications. It covers the implications of each approach on performance and cost. Prerequisites include familiarity with RAG systems and token management.

10 min read

This tutorial explores the trade-offs between structured outputs and JSON mode in retrieval-augmented generation (RAG) systems specifically for financial services applications. It highlights how structured outputs can improve data integrity and ease of processing but may limit flexibility compared to JSON mode. Prerequisites include a basic understanding of RAG systems and their applications in finance.

10 min read

This tutorial provides a structured approach to creating effective runbooks for addressing quality regressions in machine learning models. Prerequisites include familiarity with ML deployment and monitoring processes.

14 min read

This tutorial focuses on designing golden sets for retrieval-augmented generation (RAG) systems in healthcare, ensuring the generated responses are faithful and reliable. Prerequisites include understanding RAG systems and familiarity with healthcare data.

18 min read

This tutorial outlines methods to reduce hallucinations in academic research models by implementing citation constraints. It targets researchers and developers working on language models for academic purposes. Prerequisites include familiarity with natural language processing and model training.

12 min read

This tutorial outlines how to define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) for generative endpoints, ensuring high availability and performance. Prerequisites include understanding of SLIs, SLOs, and basic API concepts.

15 min read

This tutorial covers how to implement embedding drift monitoring in production systems specifically for e-commerce applications. It focuses on detecting shifts in user behavior and product interactions that can affect recommendation systems. Prerequisites include familiarity with machine learning models and data pipelines.

10 min read

This tutorial explores the trade-offs between offline and online evaluation methods for machine learning models, focusing on their impact on performance metrics and deployment strategies. Prerequisites include familiarity with basic ML concepts and evaluation metrics.

13 min read

This tutorial covers the implementation of embedding drift monitoring in production systems for healthcare applications, ensuring model accuracy over time. Prerequisites include knowledge of machine learning models and monitoring techniques.

14 min read

This tutorial explains how to implement shadow traffic to test new models in an e-commerce environment without affecting live traffic. Prerequisites include knowledge of machine learning deployment and monitoring practices.

15 min read

This tutorial guides you through implementing PII handling in retrieval pipelines specifically tailored for financial services, ensuring compliance with regulations like GDPR and CCPA. Prerequisites include familiarity with data privacy laws and experience in building retrieval systems.

14 min read

This tutorial examines the trade-offs between structured outputs and JSON mode in e-commerce applications. Prerequisites include familiarity with data formats and experience in e-commerce platforms.

16 min read

This tutorial discusses the design of golden sets to ensure the faithfulness of retrieval-augmented generation (RAG) systems in financial services. Prerequisites include experience with RAG systems and access to financial datasets.

15 min read

This tutorial explores how to effectively implement citation constraints to minimize hallucinations in academic research models. Prerequisites include familiarity with natural language processing (NLP) and access to a research dataset.

22 min read

This tutorial focuses on techniques for monitoring embedding drift in production environments specifically tailored for financial services. Prerequisites include understanding of machine learning embeddings and production systems.