LangSmith: Tracing, Debugging, and Monitoring LLM Apps
«LangSmith: Tracing, Debugging, and Monitoring LLM Apps» è un corso online di RAG e AI engineering di livello intermedio, tenuto da InsightLearn Curated AI su InsightLearn. Il percorso comprende 8 lezioni organizzate in 3 sezioni, per una durata complessiva di 7h 0m. Master LangSmith for full observability of LLM applications: tracing, prompt management, and production monitoring.
- Docente: InsightLearn Curated AI
- Categoria: RAG e AI engineering
- Livello: intermedio
- Durata: 7h 0m
- Accesso: gratuito in questa fase di validazione, in cambio di un feedback al termine
- Certificato: certificato di completamento verificabile online
Descrizione del corso
InsightLearn è in fase di sviluppo (work in progress): i contenuti di questa pagina sono pubblicati esclusivamente a fini di verifica e test.
LangSmith provides full-stack observability for LLM applications. This course covers LangSmith setup, instrumenting Python and TypeScript apps with automatic tracing, building datasets from production traces, running evaluations against datasets, prompt management and versioning, A/B testing prompts in LangSmith Hub, monitoring dashboards, alerting on hallucinations and latency, and integrating LangSmith into CI/CD pipelines.
Cosa imparerai
- Curated from public resources. Master LangSmith for full observability of LLM applications: tracing, prompt management, and production monitoring.
Programma del corso
- LangSmith overview: tracing and evaluation platform (18 min)
- Instrumenting LangChain apps with automatic tracing (22 min)
- Manual tracing with @traceable and RunTree (20 min)
- Creating datasets from production traces (28 min)
- Running automated evals with LangSmith Evaluate (32 min)
- LangSmith Hub: sharing and versioning prompts (18 min)
- Setting up production dashboards and alerts (25 min)
- Online evaluations: monitoring quality in real traffic (30 min)
Dalle lezioni
Estratto della trascrizione di «LangSmith overview: tracing and evaluation platform»
Welcome to this lecture of the course of Ang Smith, Tracing, Debugging, and Monitoring LLM Hubs. In this session, we will explore Ang Smith for the first time. Tracing is a big devaluation platform. We will start with the fundamental concepts and the basic theoretical principles. We will then see practical applications and practical cases in the world of development. Let's analyze them in a concrete way. of the sector. At the end of this lesson you will be able to apply autonomously the techniques of Lang Smith for you and your projects. We will start with the fundamental concepts and the basic theoretical principles. We will then see practical applications and almost real uses in the world of development.…
Estratto della trascrizione di «Instrumenting LangChain apps with automatic tracing»
Welcome to this lecture of the Corsodunk's Meet. Traching, Debugging, and Monitoring LLM apps. In this session, we will explore instrumenting from China with automatic traching. We will start with the fundamental concepts and the theoretical principles of the base. We will then see practical applications and almost practical uses in the world of development. We will analyze concrete elements of my work. of the sector. At the end of this lesson, you will be able to apply autonomously the techniques of instrumenting like China, its automatic tracings and your projects. We will start with the fundamental concepts and the theoretical principles of the base. We will then see practical applications and almost real uses in the world of development…
Estratto della trascrizione di «Manual tracing with @traceable and RunTree»
Three controllers, one that tilts us, complete your side rails. Three controllers, one that tilts us. And it also goes up and down, it's up way across this right, helps you shut the door. One here that steers, brings your blade up and down. This in here, will tilt my blade at the end. And it also, my turn. And it extracts my boom out. Getting further and further. Thanks for watching! I've got a damn scrap beat in here. you
Altri corsi di RAG e AI engineering
- LLM Evals: RAGAS, DeepEval, and Automated Testing
- Local LLMs: Ollama, vLLM, and Self-Hosted AI
- Multimodal AI: Vision, Audio, and Image Generation APIs
- Advanced Prompt Engineering: Chain-of-Thought, Few-Shot, and Beyond
- RAG from Scratch: Complete Retrieval-Augmented Generation
- Vector Databases in Production: Chroma, FAISS, pgvector
Domande frequenti
Quanto dura il corso LangSmith: Tracing, Debugging, and Monitoring LLM Apps?
Il corso dura 7h 0m in totale, con 8 lezioni suddivise in 3 sezioni, da seguire online al proprio ritmo.
Serve esperienza pregressa?
Il corso è di livello intermedio e non indica requisiti specifici di ingresso.
Il corso rilascia un certificato?
Sì: al completamento del corso ricevi un certificato di completamento verificabile online.