LangChain

A comprehensive guide to RAG - the dominant pattern for building AI applications that answer questions using your own data.

Explore how AI agents autonomously reason, plan, and take actions to accomplish goals.

Understand how LLMs invoke external tools and APIs—including computer use and browser use—to extend capabilities beyond text generation.

Design, version, and evaluate LLM prompts for production — system vs user roles, few-shot, chain-of-thought, and the limits that push you toward RAG, tools, and fine-tuning.

Foundation models, autoregressive and diffusion generation, and the engineering patterns required to ship reliable applications on probabilistic outputs.

Learn how LLMs like GPT, Claude, and Llama process and generate human language at scale.

Discover how AI converts text, images, and data into numerical vectors that capture meaning.

Short-term, long-term, and episodic memory patterns for AI agents that need to remember across sessions.

RAG systems where agents decide what to retrieve, when to search, and how to synthesize multi-step answers.

When to use deterministic LLM workflows vs autonomous agents - and why most production systems are hybrids.

Approval workflows, interrupt/resume patterns, and human review gates that keep production AI agents safe and controllable.

Checkpointing, persistence, retries, and resumable workflows for long-running AI agents that survive failures and interruptions.

Delegation, routing, and specialist-agent handoffs that transfer control and context between agents in a multi-agent system.

Evaluate AI agents on task success, trajectory quality, tool-call accuracy, groundedness, safety, latency, cost, and production traces.

Engineer MCP host–client–server integrations: tools/resources/prompts, Streamable HTTP transports, auth, timeouts, and the 2026-07-28 stateless protocol core—without replacing orchestration or guardrails.

Engineer typed LLM tool intents with schema validation, authorization, timeouts, idempotency, observability, and safe production execution.

Engineer reliable LLM context budgets across instructions, evidence, history, tools, and output—with retrieval, truncation, summarization, and production observability.

Why free-text LLM output fails for machines, constrained decoding vs prompt-only JSON, OpenAI JSON Schema, Pydantic validation, and production patterns with Instructor-style retries.

Improve retrieval by rewriting, expanding, or decomposing user queries before search — including query rewriting, multi-query retrieval, query decomposition, and related transformation techniques.

Purpose-built databases for storing, indexing, and querying embedding vectors at scale — including managed options like Pinecone (Database + Nexus knowledge engine).

How to split documents for RAG - fixed-size, recursive, semantic, and document-aware chunking with production trade-offs.

Measuring retrieval quality - recall@k, MRR, nDCG, and building golden test sets for RAG pipelines.

Structured representations of entities and relationships - the foundation for GraphRAG, enterprise search, and neuro-symbolic AI.

Labeled property graph model - nodes and edges with key-value properties, used by Neo4j and most graph databases.

The declarative query language for property graphs - pattern matching, traversals, and Neo4j queries.

Compare the two dominant knowledge graph models - RDF (W3C standard) and property graphs (Neo4j-style) - and when to use each.

Learn about the Resource Description Framework - the standard for representing knowledge as linked data.

Understand how ontologies define the vocabulary, relationships, and rules for a domain of knowledge.

Explore the Web Ontology Language for defining rich, machine-interpretable ontologies with reasoning capabilities.

Learn how organizations use knowledge graphs to connect data silos and power intelligent applications.

Explore how knowledge graphs enhance RAG pipelines with structured relationships and reasoning.

Discover how knowledge graphs and large language models complement each other - grounding LLMs with structured knowledge.

Practical guidelines for designing, building, and maintaining knowledge graphs in production.

Hub guide to evaluating AI systems — four eval layers, golden sets, LLM-as-judge, CI gates, and why public benchmarks are not product readiness.

Measuring LLM output quality — automated checks, rubrics, LLM-as-judge, human calibration, and CI eval pipelines for generation.

Evaluating RAG systems — faithfulness, answer relevance, context precision/recall, and attributing failures to retrieval vs generation.

Systematically testing prompts — versioning, A/B comparison, format compliance, and regression detection in CI.

Production observability for LLM systems — traces with prompt/completion/tool spans, cost and latency attribution, quality proxies, and PII-safe instrumentation.

Making AI systems fast — TTFT, streaming, parallel retrieval, caching, and routing simple steps to faster model tiers.

Caching for LLM apps — exact response cache, embedding cache, provider prompt/prefix cache, TTL, and stampede control.

Similarity-based response cache — embed queries, return prior answers above a threshold, and manage false-positive risk.

Safety constraints and validation on AI inputs and outputs — content filters, schema checks, and policy enforcement in agent and app pipelines.

Detecting when LLMs fabricate facts — grounding checks, NLI verification, citation validation, and production detection layers.

Why LLMs hallucinate — next-token prediction is not truth-seeking — and how to mitigate with RAG, tools, structured outputs, abstention, detection, and verification.

Reference architecture for modern enterprise AI systems, bringing together retrieval, knowledge graphs, AI agents, LLM gateways, caching, observability, security, and production deployment.

Production RAG architecture — hybrid retrieval, ACL filters, model routing, caching, guardrails, and observability for multi-tenant enterprise systems.

Reference architecture for graph construction, community detection, hybrid retrieval, graph traversal, and query planning.

Reference architecture for grounding, entity resolution, graph traversal, hybrid reasoning, and structured retrieval with LLMs.

Production chatbot architecture — conversation management, retrieval, guardrails, session state, and multi-channel deployment.

System design for AI copilots — context injection, tool use, IDE integration, and enterprise deployment patterns.

Routing strategies across LLM providers and model tiers — cost-aware selection, fallback chains, and capability-based dispatch.

Orchestrating multi-step AI workflows — DAGs, state machines, human-in-the-loop, and durable execution patterns.

Memory architecture for AI agents — short-term context, long-term stores, episodic recall, and vector-backed memory tiers.

Semantic caching architecture — embedding-based cache lookup, TTL policies, invalidation, and cost-latency tradeoffs.

End-to-end production AI stack — model serving, retrieval, agents, observability, and deployment reference architecture.

Structured path from LLM foundations to production AI — RAG, agents, evaluation, observability, and portfolio-ready engineering habits.

A complete guide to building retrieval-augmented generation systems - from embeddings to production.

From RDF basics to enterprise deployments - a structured path to mastering knowledge graphs.

Build autonomous AI agents from scratch - covering tool use, planning, multi-agent systems, and deployment.