Tag: #llmops
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 12 posts
Self-Hosting Langfuse — Deployment Paths, Secrets, and What Catches You on First Boot
Running Langfuse yourself means standing up two containers and four datastores at once. Working from the official documentation, this post lays out the docker compose path and the Helm chart path, which secrets you have
2026-08-14 · 9 min read #observability#langfuse#self-hosting#docker-compose#kubernetesWhy Langfuse Puts Traces in ClickHouse — How the Storage Layer Splits the Work
The first surprise when you self-host Langfuse is that there is not one datastore but four. ClickHouse, Postgres, Redis, and object storage each take a different share. Working from the official documentation, this post
2026-08-14 · 10 min read #observability#langfuse#clickhouse#architecture#postgresThe Langfuse Tracing Data Model — How Trace, Observation, and Score Hold One Execution
Looking at the Langfuse UI first tells you nothing about what you are looking at. This post starts from the shape of the data Langfuse collects. What a trace groups, what separates a span from a generation from an event,
2026-08-14 · 8 min read #observability#langfuse#llm-tracing#data-modeling#opentelemetryAfter You Have Collected It — Langfuse Dashboards, the Metrics API, and Scores on Traces
Collecting traces and getting answers out of them are different jobs. This post lays out which metric axes Langfuse offers and which dimensions you have to slice them by, then walks the Metrics API v2 query structure as
2026-08-14 · 9 min read #observability#langfuse#llm-evaluation#metrics-api#dashboardWhat LLM Ops Actually Does — Reproducibility, Contamination, Checkpoints, Promotion, and Rollback
This post organizes LLM Ops as a list of responsibilities, not a list of tools. It covers what belongs in a run manifest that lets you reconstruct a training run, how to prevent and audit eval-set contamination, the form
2026-08-02 · 14 min read #mlops#llmops#reproducibility#evaluation#model-registryThe Complete LLMOps Guide: Three-Axis Versioning of Model, Prompt, and Eval Set, Canary, Cost Control, and the Platform Team (2025)
Building an LLM product fast has become easy. Running it sustainably is the hard part. Three-axis versioning across model, prompt, and eval set; Shadow/Canary/Blue-Green deployment; cost control through tokens, caching,
2026-04-15 · 11 min read #llmops#mlops#devops#canary#cost-controlPrompt Caching for Agent Apps: A Practical Guide to Lower Cost and Latency
A practical guide to prompt caching for agent applications, including why it matters, how OpenAI and Anthropic differ, prompt structuring patterns, ROI scenarios, common mistakes, and a migration checklist.
2026-04-12 · 7 min read #prompt-caching#latency#cost-optimization#ai-agent#llmopsMLOps & Model Lifecycle Management: MLflow, DVC, and LLMOps Complete Guide
A comprehensive guide to ML production pipelines covering MLOps maturity models, MLflow experiment tracking, DVC data versioning, feature stores, and LLMOps.
2026-03-17 · 16 min read #mlops#mlflow#dvc#llmops#featurestoreGemini API in Production: Prompting, Guardrails, Evaluation, and Cost Control
A production guide to building on the Gemini API with practical prompting, tool and schema design, safety handling, evaluation loops, and cost-aware operating patterns.
2026-03-17 · 4 min read #gemini#generative-ai#ai#llmops#prompt-engineeringLLMOps Platform Architecture Guide: Model Deployment, Monitoring, and A/B Testing
A comprehensive guide to designing and implementing an LLMOps platform. Covers vLLM/TGI-based model serving, token usage/latency/quality monitoring, prompt version management, A/B testing framework, guardrail integration
2026-03-13 · 14 min read #ai-platform#llmops#model-serving#monitoring#ab-testingChatbot Tool Calling Guardrails Design: Safe Tool Invocation Architecture in Practice
Covers guardrail design for safely operating tool-calling chatbots in production. Addresses schema validation, permission control, policy engines, risk scoring, observability, and regression testing with code.
2026-03-04 · 18 min read #chatbot#tool-calling#guardrails#ai-agent#securityRAG Chatbot Evaluation in Practice: From Offline/Online Quality Measurement to Production Guardrails
Covers the evaluation system for reliably operating RAG chatbots in production. Addresses offline benchmarks, LLM-as-a-Judge, online experiments, alert thresholds, and regression prevention pipelines with code.
2026-03-04 · 16 min read #chatbot#rag#evaluation#llmops#production