Författare • 30 böcker
Great Expectations for Data Teams : Data Quality Testing That Fits CI/CD
Trex Team
Langfuse : Open-Source LLM Observability, Tracing, and Prompt Versioning
SPLADE Sparse Retrieval : Modern BM25‑Style Search for RAG Pipelines
Production GraphRAG : Building Knowledge Graph Retrieval for Verifiable Enterprise Answers
Typesense Search : Instant Search APIs with Relevance You Can Tune
pgvector for Postgres : Practical Vector Search Without a New Database
Weaviate for RAG : Schema‑Aware Vector Search with Hybrid Queries
Meilisearch for Developers : Fast, Typo‑Tolerant Search for Modern Apps
MongoDB Atlas Vector Search : Retrieval‑Ready Schemas for Operational Data
llama.cpp in the Real World : On‑Device LLM Inference, Profiling, and Deployment
KServe on Kubernetes : Production Model Serving with Canary Releases and Autoscaling
NVIDIA Triton Inference Server in Practice : Operating Multi‑Model GPU Inference at Scale
OpenVINO for GenAI : CPU‑First Acceleration and Edge Deployment Strategies
DeepSpeed Inference : Tensor Parallelism and Memory Efficiency for Large Models
FlashAttention : Speeding Up Transformers with Modern Attention Kernels
Sandboxing AI Tools : Containers, MicroVMs, and Permission Scopes for Agents
Differential Privacy for ML Engineers : Practical Budgets, Noise, and Tradeoffs
Membership Inference & Privacy Leakage : Measuring and Reducing Data Exposure
AI Incident Response : Playbooks for Prompt Leaks, Tool Abuse, and Model Failures
C2PA Content Credentials : Engineering Provenance for AI‑Generated Media
Secure RAG Authorization : Row‑Level Security, ACLs, and Per‑User Retrieval
Apache Polaris Catalog : Operating an Open Iceberg Catalog at Scale
Iceberg REST Catalogs : Managing Table Metadata Across Engines and Clouds
Apache Paimon : Streaming Lakehouse Tables for Fast Inserts and Analytics
Amundsen Data Discovery : Searchable Metadata for Analytics Teams
Airbyte ELT : Running Connectors, Normalization, and Reliable Syncs
Redpanda Streaming : Kafka‑Compatible Performance with Simple Ops
Prefect 2 Workflows : Python‑Native Orchestration for Data and ML Pipelines
28 av 30 titlar
Du har visat alla böcker av Trex Team
