Trex Team

Langfuse : Open-Source LLM Observability, Tracing, and Prompt Versioning

Trex Team

SPLADE Sparse Retrieval : Modern BM25‑Style Search for RAG Pipelines

Trex Team

Production GraphRAG : Building Knowledge Graph Retrieval for Verifiable Enterprise Answers

Trex Team

Typesense Search : Instant Search APIs with Relevance You Can Tune

Trex Team

Meilisearch for Developers : Fast, Typo‑Tolerant Search for Modern Apps

Trex Team

pgvector for Postgres : Practical Vector Search Without a New Database

Trex Team

Weaviate for RAG : Schema‑Aware Vector Search with Hybrid Queries

Trex Team

MongoDB Atlas Vector Search : Retrieval‑Ready Schemas for Operational Data

Trex Team

llama.cpp in the Real World : On‑Device LLM Inference, Profiling, and Deployment

Trex Team

KServe on Kubernetes : Production Model Serving with Canary Releases and Autoscaling

Trex Team

NVIDIA Triton Inference Server in Practice : Operating Multi‑Model GPU Inference at Scale

Trex Team

OpenVINO for GenAI : CPU‑First Acceleration and Edge Deployment Strategies

Trex Team

DeepSpeed Inference : Tensor Parallelism and Memory Efficiency for Large Models

Trex Team

FlashAttention : Speeding Up Transformers with Modern Attention Kernels

Trex Team

Sandboxing AI Tools : Containers, MicroVMs, and Permission Scopes for Agents

Trex Team

Membership Inference & Privacy Leakage : Measuring and Reducing Data Exposure

Trex Team

AI Incident Response : Playbooks for Prompt Leaks, Tool Abuse, and Model Failures

Trex Team

Differential Privacy for ML Engineers : Practical Budgets, Noise, and Tradeoffs

Trex Team

Secure RAG Authorization : Row‑Level Security, ACLs, and Per‑User Retrieval

Trex Team

C2PA Content Credentials : Engineering Provenance for AI‑Generated Media

Trex Team

Apache Polaris Catalog : Operating an Open Iceberg Catalog at Scale

Trex Team

Apache Paimon : Streaming Lakehouse Tables for Fast Inserts and Analytics

Trex Team

Iceberg REST Catalogs : Managing Table Metadata Across Engines and Clouds

Trex Team

Amundsen Data Discovery : Searchable Metadata for Analytics Teams

Trex Team

Great Expectations for Data Teams : Data Quality Testing That Fits CI/CD

Trex Team

Redpanda Streaming : Kafka‑Compatible Performance with Simple Ops

Trex Team

Prefect 2 Workflows : Python‑Native Orchestration for Data and ML Pipelines

Trex Team

Airbyte ELT : Running Connectors, Normalization, and Reliable Syncs

Trex Team