20 min read

This tutorial demonstrates how to generate synthetic data for fine-tuning classifiers in legal AI applications, ensuring compliance and accuracy. Prerequisites include a basic understanding of machine learning and legal terminology.

15 min read

This tutorial explores effective chunking strategies tailored for medical PDFs, enhancing retrieval performance for patient data. Prerequisites include familiarity with PDF structures and basic NLP techniques.

13 min read

This tutorial explores the generation and use of synthetic data to fine-tune classifiers in legal AI applications, addressing challenges like data scarcity. Prerequisites include knowledge of machine learning concepts and experience with data generation techniques.

10 min read

This tutorial outlines the implementation of metadata filters and Access Control List (ACL)-aware retrieval systems in legal document management applications. Prerequisites include knowledge of legal data structures and basic programming skills.

12 min read

This tutorial investigates the effects of quantization on retrieval quality in healthcare applications, focusing on the trade-offs between model size and accuracy. Prerequisites include a basic understanding of machine learning models and quantization techniques.

16 min read

This tutorial discusses effective backfill strategies to manage data consistency and integrity after schema changes in data warehousing environments. Prerequisites include knowledge of SQL and data warehousing concepts.

22 min read

This tutorial focuses on implementing cross-encoder re-rankers for large-scale content recommendation systems, emphasizing their performance and scalability. Prerequisites include experience with machine learning and recommendation systems.

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.