Corsi di RAG, Evals & AI Engineering online

La categoria

Retrieval-Augmented Generation, vector database, evaluation pipeline, observability, MLOps e production AI engineering.

Tutti i corsi di RAG, Evals & AI Engineering (12)

• Advanced Prompt Engineering: Chain-of-Thought, Few-Shot, and Beyond — Go beyond basic prompting: CoT, ToT, self-consistency, constitutional AI, and systematic prompt optimization. (10h 0m)
• Agentic AI Patterns: ReAct, Plan-and-Execute, and Multi-Agent — Build production-grade AI agents with ReAct, Plan-and-Execute, and multi-agent patterns with reliability guarantees. (13h 0m)
• AI Engineering: Building Production LLM Applications — End-to-end guide to shipping LLM applications to production: architecture, latency optimization, caching, safety, and observability. (15h 0m)
• Fine-Tuning LLMs: LoRA, QLoRA, and Full Fine-Tuning — Fine-tune open-source LLMs with LoRA and QLoRA: dataset preparation, training, evaluation, and deployment. (14h 0m)
• Function Calling & Tool Use: Multi-Model Production Patterns — Master function calling across OpenAI, Claude, and Gemini: parallel calls, tool orchestration, and error recovery. (8h 0m)
• LangSmith: Tracing, Debugging, and Monitoring LLM Apps — Master LangSmith for full observability of LLM applications: tracing, prompt management, and production monitoring. (7h 0m)
• LLM Evals: RAGAS, DeepEval, and Automated Testing — Build automated evaluation pipelines for LLM applications using RAGAS, DeepEval, and custom metrics. (8h 0m)
• Local LLMs: Ollama, vLLM, and Self-Hosted AI — Run large language models locally and on private servers with Ollama, vLLM, LM Studio, and llama.cpp. (11h 0m)
• Multimodal AI: Vision, Audio, and Image Generation APIs — Build multimodal AI applications with GPT-4V, Claude Vision, Gemini, Whisper, and image generation APIs. (10h 0m)
• Practical AI Safety: Alignment, Red-Teaming, and Responsible Deployment — Understand AI safety fundamentals and implement practical safety measures in production AI systems. (9h 0m)
• RAG from Scratch: Complete Retrieval-Augmented Generation — Build RAG pipelines from zero: chunking strategies, embedding models, vector stores, hybrid search, and advanced retrieval patterns. (12h 0m)
• Vector Databases in Production: Chroma, FAISS, pgvector — Compare and deploy vector databases for AI applications: Chroma, FAISS, pgvector, and managed solutions. (9h 0m)

Perché studiare su InsightLearn

Tutti i corsi sono gratuiti in questa fase di validazione della piattaforma: in cambio chiediamo un feedback al termine. Le lezioni si seguono online, al proprio ritmo, con il supporto dell'AI tutor.