Category
Framework tutorials
Every framework tutorials post on the n4n AI blog — 735 articles across 57 topics.
Topics in framework tutorials
- Building Chatbots with Vercel AI SDK & Next.js15
- LangChain RAG with Vector Databases15
- LangGraph Multi-Agent Workflows15
- LlamaIndex Query Engines for RAG15
- AutoGen Multi-Agent Conversations & Group Chat14
- Choosing an AI Framework by Use Case14
- CrewAI Agent Roles & Task Design14
- CrewAI Real-World Crew Examples14
- Haystack RAG Pipelines14
- LangChain Agents & Tool Calling14
- LangChain Multi-Model Fallback & Routing14
- LangChain.js for Node & TypeScript14
- One Backend, Every Model: Swapping GPT-5, Claude, Gemini & Llama Across Frameworks14
- Open-Source & Local Models in Frameworks (Llama 4, Mistral, DeepSeek, Qwen)14
- Vercel AI SDK Streaming Chat UI (useChat)14
- AutoGen Agent Teams for Research & Automation13
- Framework Tutorials: Customer Support Bots13
- LangChain Expression Language (LCEL) Chains13
- LangChain Getting Started with n4n.ai13
- LlamaIndex Agents & Tool Use13
- LlamaIndex Data Connectors & Ingestion13
- LlamaIndex Getting Started with n4n.ai13
- LlamaIndex Knowledge Graphs & Multi-Doc Indexes13
- Migrating from the Raw OpenAI SDK to a Framework13
- Multi-Agent Framework Showdown: CrewAI vs AutoGen vs LangGraph13
- Multimodal & Voice Apps with AI Frameworks13
- Semantic Kernel for .NET Enterprise Apps13
- Semantic Kernel Planners & Agents13
- Semantic Kernel Plugins & Native Functions13
- Vercel AI SDK Getting Started with n4n.ai13
- Vercel AI SDK Multi-Model Switching13
- Vercel AI SDK Tool & Function Calling13
- AutoGen Code-Executing Agents12
- AutoGen Getting Started with n4n.ai12
- AutoGen Human-in-the-Loop Workflows12
- CrewAI Custom Tools & Integrations12
- CrewAI Getting Started with n4n.ai12
- CrewAI Sequential vs Hierarchical Crews12
- Framework Cost & Latency Optimization Tutorials12
- Framework Tutorials: E-commerce Search & Recommendations12
- Framework Tutorials: Finance & Trading Analysis Agents12
- Framework Tutorials: Legal & Healthcare Document Q&A12
- Haystack 2.0 Agent Pipelines12
- Haystack Document Stores & Retrievers12
- Haystack Evaluation Pipelines12
- Haystack Getting Started with n4n.ai12
- LangChain Document Loaders & Chunking12
- LangChain Memory & Conversational State12
- LangChain Streaming Responses & Callbacks12
- LangChain Structured Output & Parsers12
- LangChain vs LlamaIndex for RAG12
- LlamaIndex Chat Engines & Memory12
- LlamaIndex Retrieval Evaluation & Metrics12
- Semantic Kernel Getting Started with n4n.ai12
- Semantic Kernel Memory & Vector Stores12
- Vercel AI SDK Generative UI with React Server Components12
- Vercel AI SDK on Edge & Serverless Runtimes12
All framework tutorials posts
- A/B testing GPT-4o vs Llama 3.1 405B with Vercel AI SDKHow-toA practical guide to A/B testing GPT-4o against Llama 3.1 405B using Vercel AI SDK with runnable code and verification steps.
- A CrewAI crew for real estate market analysisHow-toBuild a production-ready CrewAI crew that scrapes listings, analyzes comparables, and generates investment reports for real estate market analysis.
- Add voice input to a Next.js chatbot with Vercel AI SDKHow-toAdd voice input to a Next.js chatbot using Vercel AI SDK with Web Speech API — complete steps, runnable code, and verification.
- Adding sentiment detection to a support bot in LangChainHow-toAdd real-time sentiment detection to a LangChain support bot with step-by-step code, from classifier selection to escalation triggers and observability.
- Authentication for a Vercel AI SDK chatbot with NextAuthHow-toAdd authentication to a Vercel AI SDK chatbot using NextAuth.js with step-by-step code examples for protecting API routes and managing session state on the client.
- AutoGen GroupChatManager configuration explainedDefinitionUnderstand AutoGen GroupChatManager configuration — speaker selection, termination conditions, and message routing for multi-agent workflows.
- AutoGen setup checklist for n4n.ai beginnersListicleA practical 8-step checklist for wiring AutoGen to n4n.ai — API keys, client config, routing, fallback, token accounting, and a smoke test you can run today.
- AutoGen vs LangGraph: error handling and retries comparedComparisonA practitioner's comparison of AutoGen and LangGraph error handling, retry strategies, and failure recovery patterns for production multi-agent systems.
- Avoiding role overlap in CrewAI multi-agent designGuidePractical guide to designing distinct agent roles in CrewAI, with patterns for separation, delegation, and avoiding duplicate work.
- Backtesting an LLM trading agent built with LangGraphHow-toBuild a production-grade backtesting harness for LangGraph trading agents with walk-forward validation, slippage modeling, and statistical rigor.
- Best AI agent framework for multi-modal applicationsListicleA practitioner's comparison of seven frameworks for building multi-modal AI agents, with code patterns, architecture trade-offs, and selection criteria for production workloads.
- Build a phone agent with Pipecat, Deepgram, and ElevenLabsHow-toBuild a production-ready phone agent using Pipecat, Deepgram STT, and ElevenLabs TTS with Twilio integration. Complete tutorial with runnable code and verification steps.
- Building a cart-recovery agent with LangGraphTutorialBuild a production-ready cart recovery agent with LangGraph — state machines, conditional routing, checkpointing, and real integration patterns.
- Building a code-executing agent in Haystack 2.0How-toBuild a code-executing agent in Haystack 2.0 with secure sandboxing, tool integration, and production-ready error handling.
- Building a CrewAI crew for social media schedulingHow-toBuild a production-ready CrewAI crew that plans, writes, and schedules social posts end to end — with agents, tasks, tools, and verification steps.
- Building a Discord bot with LangChain.jsHow-toBuild a production-ready Discord bot using LangChain.js with conversation memory, tool calling, and proper error handling.
- Building a financial statement Q&A bot with LlamaIndexTutorialBuild a production-ready financial statement Q&A bot using LlamaIndex with document parsing, vector search, and structured query routing for SEC filings and earnings reports.
- Building a generative stock chart UI with Vercel AI SDKTutorialBuild a generative stock chart UI with Vercel AI SDK using React Server Components, streaming chart components directly from the model.
- Building a multilingual support bot with LlamaIndexTutorialBuild a production-ready multilingual support bot using LlamaIndex with language detection, translation, and RAG over localized knowledge bases.
- Building a price comparison agent across product feedsTutorialBuild a production-ready price comparison agent that ingests multiple product feeds, normalizes messy data, and surfaces the best deals across merchants.
- Building a SQL agent with LangChain and tool callingHow-toBuild a production-ready SQL agent with LangChain using tool calling — step-by-step guide with runnable code, schema handling, and verification.
- Building a weather plugin for Semantic KernelHow-toLearn to build a weather plugin for Semantic Kernel with native functions, dependency injection, and proper error handling in this step-by-step tutorial.
- Chatbot UI design patterns for Next.js and Vercel AI SDKGuidePractical patterns for building production chatbot UIs with Next.js and Vercel AI SDK, covering streaming, tool calls, optimistic updates, and error recovery.
- Choosing between low-code and code-first agent frameworksGuideA practical decision framework for choosing between low-code and code-first AI agent frameworks, with concrete tradeoffs, code examples, and pitfalls to avoid.
- Chroma as a Haystack document store: setup tutorialTutorialStep-by-step tutorial for integrating Chroma as a Haystack document store with runnable code and expected outputs.
- Chunking strategies for Haystack RAG pipelinesGuidePractical guide to chunking strategies for Haystack RAG pipelines with code examples, tradeoffs, and evaluation methods.
- Circuit breaking LLM providers in LangChain appsHow-toImplement circuit breaking and automatic fallback for LLM providers in LangChain with runnable code and verification steps.
- Comparing model outputs side by side with Vercel AI SDKComparisonLearn how to compare model outputs side by side using Vercel AI SDK with practical patterns for multi-model evaluation, streaming, and production routing.
- Configuring environment variables for edge AI SDK functionsHow-toConfigure environment variables for Vercel AI SDK edge functions with step-by-step instructions for local development, preview deployments, and production.
- Connect a database query tool to Vercel AI SDKHow-toLearn to connect a database query tool to Vercel AI SDK with typed tools, streaming responses, and a working Next.js example you can run locally.
- createStreamableUI explained: Vercel AI SDK generative UIDefinitioncreateStreamableUI lets you stream React components from the server as they render, enabling generative UI patterns with the Vercel AI SDK.
- createStreamableValue vs createStreamableUI in AI SDKComparisonCompare createStreamableValue and createStreamableUI in Vercel AI SDK — when to stream data vs components, type safety, serialization, and RSC integration.
- CrewAI agents powered by local Qwen2.5 modelsHow-toRun CrewAI multi-agent workflows locally with Qwen2.5 models using Ollama — complete setup, configuration, and verification steps.
- CrewAI custom tools: adding input validation with PydanticHow-toLearn how to add robust input validation to CrewAI custom tools using Pydantic models, with step-by-step code examples and verification steps.
- CrewAI custom tools: caching results to cut LLM callsHow-toLearn to implement caching in CrewAI custom tools to eliminate redundant LLM calls and cut inference costs with production-ready patterns.
- CrewAI custom tools tutorial: error handling best practicesGuidePractical guide to robust error handling in CrewAI custom tools — retries, fallbacks, structured exceptions, and observability patterns that keep agents running.
- CrewAI custom tools tutorial: file read and write accessTutorialBuild CrewAI custom tools for file read and write operations with complete, runnable code examples and expected outputs.
- CrewAI example: automating recruiting screening callsHow-toBuild a CrewAI crew that screens candidates via phone calls, extracts structured data, and ranks fit — complete with agents, tasks, and verification steps.
- CrewAI hierarchical process: custom manager agents explainedDefinitionUnderstand CrewAI's hierarchical process with custom manager agents — how delegation works, when to customize, and a working pattern you can drop into production.
- CrewAI real-world example: multi-step data pipeline QAHow-toBuild a CrewAI multi-agent system that validates data pipelines end-to-end — schema checks, row-level quality rules, and drift detection with runnable code.
- CrewAI setup tutorial: environment variables explainedTutorialConfigure CrewAI environment variables for API keys, model routing, and provider fallbacks with a complete working example you can run today.
- CrewAI task design: async execution explainedDefinitionUnderstand CrewAI async task execution — how parallel task running works, when to use it, and common pitfalls that break agent workflows.
- CrewAI vs LangGraph: which survives a 20-agent workflowComparisonA practitioner's head-to-head comparison of CrewAI and LangGraph for 20+ agent workflows, covering architecture, scaling, ergonomics, and verdicts by use case.
- Debugging CrewAI hierarchical process delegationHow-toA step-by-step guide to diagnosing and fixing delegation failures in CrewAI hierarchical crews, with logging, instrumentation, and verification techniques.
- Debugging CrewAI n4n.ai connection errorsHow-toStep-by-step guide to diagnose and fix CrewAI connection errors when using n4n.ai as the LLM gateway, with runnable verification scripts.
- Debugging Haystack agent pipelines with tracingGuideA practical guide to instrumenting, reading, and acting on traces in Haystack 2.0 agent pipelines — from setup to common failure patterns.
- Debugging Haystack n4n.ai connection issuesHow-toStep-by-step guide to diagnose and fix Haystack connection issues with n4n.ai, covering auth, endpoints, model routing, and common failure modes.
- Debugging LangChain memory that forgets earlier contextHow-toStep-by-step debugging guide for LangChain memory that drops earlier conversation turns, with runnable code to verify fixes.
- Debugging LangGraph agent loops and infinite cyclesHow-toA step-by-step guide to detecting, reproducing, and fixing infinite loops in LangGraph multi-agent workflows with practical code patterns.
- Debugging LCEL chains with LangSmith tracingHow-toLearn to debug LangChain Expression Language chains using LangSmith tracing with step-by-step setup, runnable code, and verification techniques.
- Debugging LlamaIndex agent tool callsHow-toA step-by-step guide to debugging LlamaIndex agent tool calls with logging, callbacks, and trace inspection.
- Debugging slow first-token latency in LangChain streamsHow-toA step-by-step guide to measuring, isolating, and fixing slow first-token latency in LangChain streaming pipelines with runnable diagnostics.
- Debugging tool call errors in the Vercel AI SDKHow-toA step-by-step guide to diagnosing and fixing tool call failures in the Vercel AI SDK, from schema mismatches to provider quirks.
- Deploying LangGraph apps with LangGraph CloudHow-toA step-by-step guide to deploying LangGraph applications to LangGraph Cloud, covering project setup, configuration, deployment commands, and verification.
- Designing escalation paths in AutoGen agent workflowsGuidePractical patterns for building human escalation paths in AutoGen multi-agent workflows, with code examples and tradeoff analysis.
- Docker code execution setup for AutoGen with n4n.aiHow-toSet up Docker-based code execution for AutoGen agents with secure sandboxing and n4n.ai routing for LLM calls.
- Edge middleware patterns with Vercel AI SDK and n4n.aiGuidePractical patterns for building streaming LLM responses at the edge using Vercel AI SDK middleware with automatic provider fallback and token metering.
- Edge runtime limitations for Vercel AI SDK developersDefinitionUnderstand Vercel AI SDK edge runtime limitations — what works, what breaks, and how to architect around streaming, bundle size, and provider constraints.
- Edge runtime streaming chat with useChat and n4n.aiHow-toBuild a streaming chat UI on Vercel Edge Runtime using useChat and n4n.ai with step-by-step code, routing directives, and fallback handling.
- Error handling in LangChain.js with retry and fallbackHow-toA practical guide to implementing robust error handling, retry logic, and model fallback chains in LangChain.js for production Node.js and TypeScript applications.
- First Semantic Kernel app with n4n.ai and Llama 3.3 70BTutorialBuild your first Semantic Kernel app using n4n.ai's OpenAI-compatible endpoint with Llama 3.3 70B — prerequisites, setup, chat completion, and function calling in 30 minutes.
- Fix LlamaIndex connection errors with n4n.aiHow-toFix LlamaIndex connection errors when using n4n.ai as your LLM gateway with step-by-step troubleshooting and working code examples.
- From raw OpenAI prompts to LlamaIndex query enginesHow-toA step-by-step guide to migrating raw OpenAI SDK calls to LlamaIndex query engines with retrieval, streaming, and production patterns.
- From raw OpenAI streaming to LangChain's streaming APIHow-toStep-by-step guide to migrating from raw OpenAI SDK streaming to LangChain's streaming API with runnable code examples and verification steps.
- Generative UI patterns for multi-step tool calls in AI SDKGuidePractical patterns for building generative UI with multi-step tool calls in Vercel AI SDK, from streaming basics to human-in-the-loop workflows.
- Handling streaming errors in LangChain gracefullyHow-toA step-by-step guide to building resilient LangChain streaming pipelines with proper error handling, retries, and partial response recovery.
- Handling timeouts in AutoGen code execution agentsHow-toLearn how to configure and handle timeouts in AutoGen code execution agents with practical steps, code examples, and verification methods.
- Haystack agent pipeline tutorial: branching and loopsTutorialBuild a Haystack 2.0 agent pipeline with conditional branching and loops for multi-step reasoning and tool use.
- Haystack agent pipeline tutorial with DeepSeek V3TutorialBuild a Haystack 2.0 agent pipeline with DeepSeek V3 — prerequisites, tool integration, streaming, and production patterns with runnable code.
- Haystack document store tutorial: in-memory store basicsTutorialLearn Haystack's InMemoryDocumentStore basics with runnable code — write documents, retrieve with BM25 and embeddings, filter by metadata, and understand when to graduate to persistent stores.
- Haystack document store tutorial: OpenSearch integrationTutorialStep-by-step tutorial for integrating OpenSearch as a Haystack document store with runnable code and expected outputs at each checkpoint.
- Haystack evaluation pipeline tutorial: answer correctnessTutorialBuild a Haystack evaluation pipeline to measure answer correctness with runnable code, from prerequisites to CI integration.
- Haystack evaluation pipeline tutorial: dataset preparationTutorialBuild a Haystack evaluation pipeline from scratch — prepare datasets, define ground truth, and validate your RAG or QA system with runnable code.
- Haystack evaluation pipeline tutorial for retrieval qualityTutorialBuild a production-ready Haystack evaluation pipeline to measure retrieval quality with runnable code and expected outputs at each step.
- Haystack evaluation tutorial: exact match vs semanticComparisonCompare Haystack's exact match and semantic evaluators across capabilities, cost, latency, ergonomics, and limits — with code examples and a clear verdict for each use case.
- Haystack pipelines with self-hosted DeepSeek-V3TutorialBuild a production-ready Haystack RAG pipeline with self-hosted DeepSeek-V3 using vLLM and Ollama, with working code and deployment patterns.
- Haystack RAG pipeline tutorial: enterprise document searchTutorialBuild a production-ready Haystack RAG pipeline for enterprise document search with hybrid retrieval, reranking, and observability.
- Haystack RAG pipeline tutorial: query routingTutorialBuild a Haystack RAG pipeline that classifies queries and routes them to specialized retrievers for better accuracy and lower latency.
- Haystack retriever tutorial: filtering by metadataTutorialA hands-on Haystack retriever metadata filtering tutorial showing how to filter documents by custom metadata fields with runnable code examples and expected outputs.
- Haystack setup tutorial: API keys and environment configTutorialConfigure Haystack API keys and environment for n4n.ai's OpenAI-compatible endpoint with step-by-step code examples and verification checkpoints.
- Healthcare document Q&A: chunking clinical PDFs correctlyHow-toLearn how to chunk clinical PDFs for document Q&A with proper section-aware splitting, table preservation, and metadata tracking for healthcare RAG systems.
- How to add ticket routing to a LangChain support botHow-toLearn to implement ticket routing in a LangChain support bot with classifiers, escalation logic, and integration patterns you can deploy today.
- LangChain AgentExecutor verbose mode explainedDefinitionUnderstand LangChain AgentExecutor verbose mode, what intermediate steps reveal, and how to debug agent reasoning without drowning in output.
- LangChain and Milvus: scaling RAG to millions of documentsGuideA practical guide to scaling LangChain RAG pipelines with Milvus to millions of documents, covering collection design, embedding pipelines, retrieval strategies, and operational pitfalls.
- LangChain CSV and JSON loaders for structured dataHow-toPractical guide to loading CSV and JSON files with LangChain document loaders, including nested structures, custom parsing, and chunking strategies for RAG pipelines.
- LangChain document loaders for Google Drive and S3How-toA step-by-step guide to loading documents from Google Drive and Amazon S3 using LangChain document loaders, with runnable code and verification steps.
- LangChain memory for multi-user chat applicationsGuideBuild production-ready multi-user chat with LangChain memory — isolation strategies, storage backends, and pitfalls that bite at scale.
- LangChain RAG with Redis as the vector storeHow-toBuild a production-ready RAG pipeline using LangChain and Redis as the vector store, with complete code and verification steps.
- LangChain routing with n4n.ai's :floor price suffixTutorialLearn to implement cost-aware model routing in LangChain using the floor price suffix for automatic fallback and budget control.
- LangChain vs LlamaIndex: agent support inside RAGComparisonA practitioner's head-to-head comparison of LangChain and LlamaIndex agent architectures for RAG, with code patterns, trade-offs, and a verdict by use case.
- LangChain vs LlamaIndex: debugging and observability toolsComparisonA practitioner's comparison of LangChain and LlamaIndex debugging and observability tooling — callbacks, tracing, evaluation, and production monitoring.
- LangGraph streaming and interrupting long-running agentsHow-toLearn to implement streaming and human-in-the-loop interrupts in LangGraph agents with runnable code examples for long-running workflows.
- LangGraph's state machine vs AutoGen's conversation loopComparisonCompare LangGraph's state machine architecture against AutoGen's conversation loop for multi-agent systems — code patterns, control flow, debugging, and when to choose each.
- LCEL RunnableLambda: adding custom functions to chainsHow-toLearn to wrap custom Python functions as LCEL RunnableLambda components for composable, streaming-capable LangChain pipelines.
- LlamaIndex batch evaluation runner explainedGuideLearn to run batch evaluations in LlamaIndex with practical code examples, common pitfalls, and tradeoffs for retrieval and generation quality metrics.
- LlamaIndex chat store: Redis vs in-memoryComparisonCompare LlamaIndex chat stores: Redis vs in-memory across persistence, latency, cost, and scaling. Code examples and a clear verdict for each use case.
- LlamaIndex graph store: Neo4j vs NebulaGraphComparisonHead-to-head comparison of Neo4j and NebulaGraph as LlamaIndex graph stores — architecture, integration maturity, scaling, ops, and cost.
- LlamaIndex plus Ollama: indexing docs with DeepSeek-V3TutorialBuild a local-first document indexing pipeline with LlamaIndex, Ollama embeddings, and DeepSeek-V3 via OpenAI-compatible API.
- LlamaIndex query engines vs LangChain retrieversComparisonCompare LlamaIndex query engines and LangChain retrievers for RAG — architecture, control, streaming, and when to pick each.
- LlamaIndex query pipelines vs query enginesComparisonCompare LlamaIndex query pipelines and query engines across capabilities, ergonomics, latency, and ecosystem to pick the right abstraction for your RAG system.
- LlamaIndex Slack connector for chat data ingestionHow-toA step-by-step LlamaIndex Slack connector tutorial showing how to ingest chat data, handle authentication, and build a queryable index from your workspace conversations.
- LlamaIndex tree summarize vs refine response modeComparisonCompare LlamaIndex tree_summarize vs refine response modes for RAG — latency, cost, quality trade-offs, and when to use each.
- LlamaIndex vs LangChain: which scales past a million vectorsComparisonHead-to-head comparison of LlamaIndex and LangChain for RAG at million-vector scale — architecture, latency, cost, and when to pick each.
- Migrating OpenAI SDK retry logic to a framework's defaultsHow-toLearn how to migrate custom OpenAI SDK retry logic to your framework's built-in defaults with step-by-step code examples and verification strategies.
- Migrating raw OpenAI SDK error handling to LangChainHow-toA step-by-step guide to migrating OpenAI SDK error handling patterns to LangChain with runnable code and verification steps.
- Migrating raw OpenAI SDK memory management to LangChainHow-toStep-by-step guide to migrating conversation memory from raw OpenAI SDK to LangChain with runnable code and verification checkpoints.
- Mistral Large in Semantic Kernel: a .NET integration guideGuideA practical guide to integrating Mistral Large with Semantic Kernel in .NET, covering setup, chat completion, streaming, function calling, and common pitfalls.
- Multi-agent AutoGen teams for market research automationHow-toBuild a production-ready AutoGen agent team that automates market research — from competitor scraping to synthesis — with caching, cost controls, and verification steps.
- Multi-agent code review pipeline with LangGraphHow-toBuild a production-ready langgraph multi-agent code review pipeline with static analysis, security scanning, and style enforcement agents.
- Multi-agent debate pattern with AutoGen and n4n.aiTutorialBuild a multi-agent debate system with AutoGen using n4n.ai as the inference gateway, with runnable code and checkpoint outputs.
- Multi-agent pipelines in Haystack 2.0: a tutorialTutorialBuild production-ready multi-agent pipelines in Haystack 2.0 with working code, from prerequisites to deployment patterns.
- Multi-agent workflows in LlamaIndex explainedGuideA practical guide to building multi-agent workflows in LlamaIndex with AgentWorkflow, covering communication patterns, state management, and production pitfalls.
- Multi-document RAG with LlamaIndex RouterQueryEngineTutorialBuild a multi-document RAG system using LlamaIndex RouterQueryEngine with step-by-step code examples and expected outputs.
- Multi-model chat app: Claude, GPT-4o, and Mixtral 8x7BTutorialBuild a production-ready multi-model chat app with Vercel AI SDK that switches between Claude, GPT-4o, and Mixtral 8x7B with streaming, tool calling, and provider fallbacks.
- Multi-model routing in AutoGen: GPT-5 and Llama 4TutorialBuild a multi-model AutoGen workflow that routes between GPT-5 and Llama 4 via a single OpenAI-compatible endpoint, with fallback and per-token metering.
- Multi-step tool calls with Vercel AI SDK's maxStepsHow-toLearn how to configure maxSteps in Vercel AI SDK for multi-step tool calling, with runnable examples and verification steps for production use.
- Multi-tool LangChain agents: search, calculator, and codeHow-toBuild a LangChain multi-tool agent with search, calculator, and code execution tools. Step-by-step tutorial with runnable code and verification steps.
- Multi-turn RAG conversations in LlamaIndexGuideBuild multi-turn RAG conversations in LlamaIndex with chat engines, memory buffers, and context compression — practical patterns for production systems.
- Multimodal agents in LangGraph with GPT-4o visionTutorialBuild a production-ready multimodal agent with LangGraph and GPT-4o vision — handles images, maintains state, and routes dynamically.
- Nested conversations in AutoGen: a practical guideGuideLearn to build nested conversations in AutoGen with working code patterns, context isolation strategies, and pitfalls to avoid when orchestrating multi-agent workflows.
- Next.js App Router generative UI with Vercel AI SDKTutorialBuild generative UI in Next.js App Router using Vercel AI SDK with React Server Components, streaming responses, and tool calling.
- One provider, 240+ models: multi-model AI SDK setupGuideA practical guide to configuring Vercel AI SDK for multi-model routing across 240+ models using a single OpenAI-compatible endpoint, with code examples and production pitfalls.
- Parallel execution in LangChain using LCELHow-toLearn to run independent LCEL chains in parallel using RunnableParallel, RunnablePassthrough, and async patterns to cut latency in production LangChain applications.
- Parallel tool calling in LangChain agentsHow-toLearn to enable and configure parallel tool calling in LangChain agents with runnable code, error handling, and production verification steps.
- Parallel tool calls in the Vercel AI SDK explainedDefinitionHow parallel tool calls work in the Vercel AI SDK, why they reduce latency, and the patterns to use them correctly in production.
- Parse multimodal documents with LlamaIndex and GPT-4oTutorialBuild a production-ready multimodal document parser using LlamaIndex and GPT-4o with code examples for PDFs, images, and mixed-content files.
- Per-request model overrides in the Vercel AI SDKHow-toLearn how to implement per-request model overrides in the Vercel AI SDK with step-by-step code examples for dynamic model switching at runtime.
- Persisting LangChain memory to PostgresHow-toA step-by-step guide to implementing LangChain memory persistence with Postgres, including schema design, custom memory classes, and production-ready patterns.
- Persisting LangGraph state with checkpointersHow-toLearn to persist LangGraph state with checkpointers — from in-memory to Postgres, with runnable code and verification steps.
- Persisting LlamaIndex chat history across sessionsHow-toA practical guide to persisting LlamaIndex chat history across sessions using ChatMemoryBuffer with Redis, Postgres, or file storage — complete with runnable code and verification steps.
- Personalized recommendations with CrewAI agentsTutorialBuild a personalized recommendation engine using CrewAI agents with user profiling, candidate generation, and ranking stages — complete with runnable code and output examples.
- Pipecat vs LiveKit Agents for building voice AI appsComparisonTechnical comparison of Pipecat and LiveKit Agents for voice AI applications, covering architecture, latency, pricing, and when to choose each framework.
- Point AutoGen's base_url at n4n.ai in 5 minutesHow-toConfigure AutoGen to route LLM calls through n4n.ai by setting base_url, with step-by-step code and verification.
- Provider-agnostic agents: swapping models in CrewAI safelyHow-toLearn to swap LLM models in CrewAI without rewriting agents — configure provider-agnostic routing, handle model-specific quirks, and verify behavior across OpenAI, Anthropic, and local models.
- Python environment setup for AutoGen and n4n.aiHow-toSet up a clean Python environment for AutoGen with n4n.ai routing, including virtualenv, dependencies, API keys, and a working multi-agent test script.
- Q&A over patient intake forms with LangChainTutorialBuild a production-ready Q&A system for patient intake forms using LangChain, vector stores, and LLMs with PHI-aware handling.
- Query a knowledge graph in LlamaIndex with n4n.aiHow-toBuild a LlamaIndex knowledge graph query pipeline using n4n.ai as the LLM gateway, with step-by-step code and verification checks.
- Qwen2.5-72B in LangChain: a complete setup guideGuideComplete guide to integrating Qwen2.5-72B with LangChain — local Ollama setup, OpenAI-compatible endpoints, streaming patterns, and production pitfalls.
- RAG on PDFs: LangChain vs LlamaIndex parsers comparedComparisonA hands-on comparison of LangChain and LlamaIndex PDF parsers for RAG, covering extraction quality, chunking, performance, and when to use each.
- Rate limiting a Vercel AI SDK chatbot in Next.jsHow-toImplement rate limiting for a Vercel AI SDK chatbot in Next.js using Upstash Redis with sliding window logic, middleware integration, and client-side retry handling.
- Real-time market data agents with AutoGenTutorialBuild a real-time market data agent with AutoGen — fetch live prices, compute indicators, and orchestrate multi-agent analysis with runnable Python code.
- Real-time progress bars with LangChain streamingHow-toBuild real-time progress bars for LangChain streaming responses using custom callbacks — token counting, async handling, and production patterns.
- Reduce LlamaIndex latency with async query pipelinesHow-toCut LlamaIndex query latency by converting synchronous retrievers and synthesizers to async pipelines with parallel execution and streaming.
- Reduce redundant LLM calls in CrewAI agent loopsHow-toPractical steps to cut redundant LLM calls in CrewAI agent loops using caching, shared memory, and smarter task design.
- Render Markdown and code blocks in an AI SDK chatbotHow-toBuild a Vercel AI SDK chatbot that renders Markdown and highlighted code blocks with streaming support and copy-to-clipboard.
- Rendering tool invocations in useChat's message partsHow-toLearn to render tool invocations in useChat message parts with Vercel AI SDK, including streaming tool calls, results, and UI patterns for chat interfaces.
- Rendering tool results as React components with streamUIHow-toLearn to render tool results as React components with streamUI in the Vercel AI SDK, including server actions, client hydration, and type-safe component mapping.
- Reranking retrieved documents in a LangChain RAG pipelineHow-toLearn how to add reranking to your LangChain RAG pipeline with step-by-step code examples using cross-encoders and Cohere rerank for better retrieval quality.
- Retrieval-augmented generation with LangChain and QdrantHow-toBuild a production-ready RAG pipeline with LangChain and Qdrant — from document ingestion to retrieval and generation, with verification steps at each stage.
- Retry failed LangChain parses with RetryOutputParserHow-toLearn to wrap LangChain parsers with RetryOutputParser so malformed LLM output gets corrected automatically — complete with Pydantic models, prompt templates, and verification steps.
- Risk analysis agents: a LangGraph tutorialTutorialBuild a production-ready risk analysis agent with LangGraph — state machines, conditional routing, and real market data integration.
- Route AutoGen code execution to GPT-5.1 via n4n.aiHow-toRoute AutoGen code-executing agents to GPT-5.1 through n4n.ai with automatic fallback and per-token metering.
- Route LangChain calls between GPT-4o and Claude 3.5How-toLearn to route LangChain calls between GPT-4o and Claude 3.5 with fallback, conditional logic, and a unified gateway.
- Route local models with LiteLLM: Qwen3 and Llama 4How-toConfigure LiteLLM to route requests between local Qwen3 and Llama 4 models with fallback, load balancing, and cost tracking.
- Run Llama 3.3 70B in LangChain via n4n.aiHow-toRun Llama 3.3 70B with LangChain using n4n.ai's OpenAI-compatible endpoint — complete setup, streaming, tool calling, and production hardening.
- Running Claude 3.5 Sonnet in AutoGen through n4n.aiTutorialStep-by-step tutorial for integrating Claude 3.5 Sonnet with AutoGen using n4n.ai as the inference gateway, with complete runnable code and expected outputs.
- Running CrewAI locally with n4n.ai and Claude Sonnet 4.5How-toA step-by-step guide to running CrewAI locally with n4n.ai as the LLM gateway, using Claude Sonnet 4.5 for agent execution.
- Running the same LangGraph agent across four model providersTutorialLearn to run a LangGraph agent across GPT-5, Claude, Gemini, and Llama using a single OpenAI-compatible endpoint with automatic fallback and per-token metering.
- Running Vercel AI SDK on AWS LambdaHow-toDeploy Vercel AI SDK on AWS Lambda with streaming support, proper handler configuration, and production-ready deployment patterns.
- Sandboxing AutoGen code execution with Docker containersHow-toA step-by-step guide to sandboxing AutoGen code execution with Docker containers, including container setup, agent configuration, and verification.
- Scaling AutoGen agent teams for automated data pipelinesGuideA practical guide to scaling AutoGen agent teams for production data pipeline automation, covering architecture patterns, state management, and failure handling.
- SEC filing Q&A with LlamaIndex: a step-by-step tutorialTutorialBuild a production-ready SEC filing Q&A system with LlamaIndex — from ingestion to retrieval to structured answers, with runnable code at every step.
- Self-correcting AutoGen agents that debug their own codeGuideBuild AutoGen agents that execute code, catch errors, and iterate until the output works — with practical patterns for production use.
- Semantic chunking in LangChain with embeddingsHow-toLearn to implement semantic chunking in LangChain using embeddings for better RAG retrieval — step-by-step with runnable code and evaluation techniques.
- Semantic Kernel agent tutorial: adding memory to agentsTutorialA hands-on tutorial for adding persistent memory to Semantic Kernel agents using vector stores and memory skills, with complete runnable code.
- Semantic Kernel agent tutorial: GPT-4o and Claude fallbackTutorialBuild a Semantic Kernel agent with automatic GPT-4o to Claude fallback using n4n.ai's unified endpoint — complete with planner setup, routing directives, and runnable code.
- Semantic Kernel agent tutorial: group chat orchestrationTutorialBuild a multi-agent group chat with Semantic Kernel: define specialized agents, configure orchestration, and run collaborative workflows with working code.
- Semantic Kernel agent tutorial: multi-agent conversationsTutorialBuild multi-agent conversations with Semantic Kernel — step-by-step tutorial covering group chat, agent roles, and orchestration patterns with runnable Python code.
- Semantic Kernel agent tutorial: tool selection strategiesGuideA practical guide to Semantic Kernel agent tool selection strategies covering function choice behaviors, planner integration, metadata design, and failure handling patterns.
- Semantic Kernel enterprise tutorial: content filteringGuideA practical guide to implementing content filtering in Semantic Kernel for enterprise .NET applications, covering built-in filters, custom pipelines, and Azure AI Content Safety integration.
- Semantic Kernel enterprise tutorial: logging and telemetryGuideA practical guide to implementing structured logging and OpenTelemetry in Semantic Kernel for .NET enterprise applications, with code examples and production pitfalls.
- Semantic Kernel enterprise tutorial: multi-tenant setupGuideA practical guide to configuring Semantic Kernel for multi-tenant .NET enterprise applications, covering kernel isolation, tenant resolution, plugin scoping, and observability patterns.
- Semantic Kernel enterprise tutorial: role-based accessGuideImplement role-based access control in Semantic Kernel for .NET enterprise apps with middleware, policies, and plugin-level authorization.
- Semantic Kernel functions tutorial: parameter schemasGuideA practical guide to defining and validating parameter schemas in Semantic Kernel functions, covering JSON Schema, kernel arguments, and common serialization pitfalls.
- Semantic Kernel functions tutorial: prompt vs nativeComparisonA practical head-to-head comparison of Semantic Kernel prompt functions versus native functions with code examples, a decision matrix, and clear guidance on when to use each approach.
- Semantic Kernel functions tutorial: testing plugins locallyGuideA practical guide to testing Semantic Kernel plugins locally with unit tests, integration tests, and debugging strategies that catch issues before deployment.
- Semantic Kernel memory tutorial: chunking documentsGuideA practical guide to chunking documents in Semantic Kernel Memory, covering strategies, code patterns, and tradeoffs for production RAG systems.
- Semantic Kernel memory tutorial: hybrid document searchTutorialBuild hybrid document search with Semantic Kernel Memory — combine vector similarity and keyword matching for better retrieval accuracy.
- Semantic Kernel memory tutorial: recalling conversationsTutorialA hands-on tutorial for implementing conversation memory in Semantic Kernel using vector stores, covering setup, storage, retrieval, and practical patterns for recall.
- Semantic Kernel memory tutorial: semantic text memory basicsTutorialLearn Semantic Kernel's semantic text memory with a hands-on tutorial — setup, storing embeddings, searching, and integrating vector stores.
- Semantic Kernel n4n.ai tutorial: model fallback setupTutorialBuild resilient LLM apps with Semantic Kernel and n4n.ai — configure automatic model fallback, routing directives, and per-token metering in minutes.
- Semantic Kernel n4n.ai tutorial: streaming chat responsesTutorialBuild streaming chat with Semantic Kernel and n4n.ai — prerequisites, setup, and runnable code for real-time responses.
- Semantic Kernel n4n.ai tutorial: your first chat completionTutorialBuild your first Semantic Kernel chat completion with n4n.ai — prerequisites, setup, streaming, and function calling in a working Python project.
- Semantic Kernel native functions tutorial in C#TutorialBuild Semantic Kernel native functions in C# with this step-by-step tutorial — plugins, DI, async patterns, and invocation strategies.
- Semantic Kernel .NET tutorial: ASP.NET Core integrationTutorialBuild a production-ready Semantic Kernel integration in ASP.NET Core with dependency injection, plugins, and streaming responses.
- Semantic Kernel .NET tutorial: Azure deployment walkthroughTutorialDeploy a Semantic Kernel .NET app to Azure with Bicep, Container Apps, and GitHub Actions — complete working code and verification steps.
- Semantic Kernel .NET tutorial: background servicesTutorialBuild a production-ready Semantic Kernel .NET background service with dependency injection, AI plugins, and proper error handling.
- Semantic Kernel .NET tutorial: dependency injection setupTutorialA hands-on tutorial for wiring Semantic Kernel into .NET dependency injection, covering kernel registration, plugin injection, multiple kernel scenarios, and verification patterns.
- Semantic Kernel .NET tutorial: on-prem gateway setupHow-toStep-by-step guide to wiring Semantic Kernel .NET to an on-prem LLM gateway with OpenAI-compatible endpoints, auth, and health checks.
- Semantic Kernel .NET tutorial: retries and timeoutsTutorialLearn to configure retries and timeouts in Semantic Kernel .NET with Polly for resilient LLM calls in production.
- Semantic Kernel .NET tutorial: unit testing kernel functionsTutorialLearn to unit test Semantic Kernel .NET kernel functions with xUnit, Moq, and dependency injection — complete with runnable code and CI-ready patterns.
- Semantic Kernel planner tutorial: automatic planningTutorialBuild a working Semantic Kernel automatic function planner step by step — define plugins, configure the planner, execute plans, and handle real-world edge cases.
- Semantic Kernel planner tutorial: debugging failed plansGuideA practical debugging guide for Semantic Kernel planner failures — ordered steps, code patterns, and common pitfalls engineers hit in production.
- Semantic Kernel planner tutorial: handlebars planner basicsTutorialLearn to build agents with Semantic Kernel's Handlebars planner through a complete, runnable tutorial covering setup, prompt templates, and execution loops.
- Semantic Kernel planner tutorial: sequential vs stepwiseComparisonCompare Semantic Kernel's Sequential and Stepwise planners across capabilities, latency, ergonomics, and failure modes with code examples and a decision matrix.
- Semantic Kernel plugins tutorial: auto function callingTutorialBuild a working Semantic Kernel auto function calling setup with plugins, kernel configuration, and debugging techniques you can run today.
- Semantic Kernel plugins tutorial: chaining functionsTutorialLearn to chain Semantic Kernel functions into pipelines with native plugins, kernel arguments, and automatic parameter passing — runnable code included.
- Semantic Kernel plugins tutorial: function error handlingTutorialLearn semantic kernel native function error handling with practical patterns for retries, fallbacks, and structured error types in plugin development.
- Semantic Kernel plugins tutorial: importing OpenAPI specsTutorialLearn to import OpenAPI specs as Semantic Kernel plugins with runnable Python code, authentication handling, and production-ready patterns.
- Semantic Kernel setup tutorial: API keys and configTutorialStep-by-step Semantic Kernel setup with n4n.ai API keys, including config patterns, provider fallback, and runnable code for chat completion and streaming.
- Semantic Kernel setup tutorial: choosing a model on n4n.aiTutorialSet up Semantic Kernel with n4n.ai in minutes — configure the kernel, pick the right model for your task, and run your first completion with streaming and function calling.
- Semantic Kernel setup tutorial in C# with n4n.aiTutorialSet up Semantic Kernel in C# with n4n.ai — prerequisites, project structure, chat completion, streaming, and function calling with runnable code.
- Semantic Kernel setup tutorial in Python with n4n.aiTutorialStep-by-step Semantic Kernel Python setup with n4n.ai gateway — prerequisites, kernel creation, chat completion, and streaming responses with runnable code.
- Semantic Kernel vector store tutorial: Azure AI Search setupTutorialBuild a production-ready Semantic Kernel vector store with Azure AI Search — prerequisites, index creation, ingestion, and hybrid search with runnable code.
- Semantic Kernel vector store tutorial: Chroma integrationTutorialBuild a Semantic Kernel vector store with Chroma — complete tutorial with prerequisites, runnable code, and expected outputs for engineers implementing RAG pipelines.
- Semantic Kernel vector store tutorial: pgvector setupTutorialStep-by-step tutorial for configuring Semantic Kernel with pgvector in PostgreSQL, covering prerequisites, schema, ingestion, and vector search with runnable code.
- Semantic Kernel vector store tutorial: Redis memory storeTutorialBuild a production-ready Semantic Kernel vector store with Redis. Step-by-step tutorial covering setup, embeddings, search, and filtering with runnable Python code.
- Sequential chat vs group chat in AutoGenComparisonCompare AutoGen sequential chat vs group chat patterns with code examples, a decision matrix, and clear guidance on when to use each multi-agent architecture.
- Sequential CrewAI crews for linear content workflowsHow-toBuild a production-ready content pipeline using CrewAI's sequential process — step-by-step code, agent design, and verification strategies.
- Server actions and streaming UI in the Vercel AI SDKHow-toBuild streaming generative UI with Vercel AI SDK server actions and React Server Components — a complete end-to-end guide with runnable code.
- Serverless function timeouts and Vercel AI SDK streamingHow-toHow to prevent Vercel AI SDK streaming responses from hitting serverless function timeouts on Vercel, AWS Lambda, and Cloudflare Workers with practical configuration and code patterns.
- Serving Llama 4 with vLLM and an OpenAI-compatible APIGuideA practical guide to serving Llama 4 with vLLM behind an OpenAI-compatible API, covering hardware requirements, quantization choices, deployment patterns, and common production pitfalls.
- Set environment variables for LlamaIndex and n4n.aiHow-toConfigure LlamaIndex environment variables for n4n.ai integration with step-by-step setup for local, Docker, and production environments.
- Set up Next.js 14 with Vercel AI SDK and n4n.aiHow-toA step-by-step guide to wiring Next.js 14, Vercel AI SDK, and n4n.ai into a working chat interface with streaming, tool calls, and provider fallback.
- Setting termination conditions in AutoGen group chatsHow-toLearn to configure termination conditions in AutoGen group chats with max rounds, custom functions, and message-based triggers — complete with runnable code and verification steps.
- Slack approvals for AutoGen agents: a practical guideGuideBuild Slack-based human approval workflows for AutoGen agents with a production-ready pattern covering setup, timeouts, retries, and common failure modes.
- Speaker selection strategies in AutoGen GroupChatGuideMaster AutoGen GroupChat speaker selection with practical strategies — built-in methods, custom functions, LLM-based routing, and hybrid approaches for production multi-agent systems.
- Speed up RAG retrieval with LlamaIndex reranking modelsTutorialA hands-on tutorial showing how to integrate LlamaIndex reranking models into RAG pipelines to reduce latency while improving retrieval quality, with runnable code and benchmarks.
- Splitting code files in LangChain for RAG pipelinesHow-toLearn to split code files effectively in LangChain for RAG pipelines using language-aware splitters, with runnable examples and verification steps.
- Stream Claude 3.5 Sonnet replies with useChat and n4n.aiTutorialBuild a streaming chat UI with Vercel AI SDK's useChat hook, routing Claude 3.5 Sonnet requests through n4n.ai's OpenAI-compatible endpoint with automatic fallback.
- Stream RAG responses in LlamaIndex with n4n.aiHow-toLearn to stream RAG responses in LlamaIndex using n4n.ai as the inference gateway with step-by-step code and verification.
- Stream responses in LangGraph to cut perceived latencyHow-toLearn to implement streaming responses in LangGraph with step-by-step code examples that cut perceived latency and improve UX for LLM applications.
- Stream structured output in LangChain with n4n.aiHow-toLearn to stream structured output in LangChain with Pydantic models and JSON parsers, including partial parsing, validation, and production fallback patterns.
- Streaming LangChain agent output to a React frontendHow-toBuild a production-ready streaming pipeline from LangChain agents to React using FastAPI, Server-Sent Events, and proper callback handling.
- Streaming responses in Haystack RAG pipelines with n4n.aiHow-toBuild a Haystack RAG pipeline that streams tokens from n4n.ai with runnable code, error handling, and verification steps.
- Streaming token-by-token responses with useChatHow-toA complete usechat token streaming tutorial showing how to build a token-by-token streaming chat UI with Vercel AI SDK's useChat hook, from backend API to frontend implementation.
- Streaming tool call results with Vercel AI SDKHow-toLearn to stream tool call results in real-time with Vercel AI SDK using useChat, streamText, and tool handlers for responsive UX.
- Structured output on Claude 3.5 Sonnet via LangChainTutorialA hands-on tutorial for getting structured JSON output from Claude 3.5 Sonnet using LangChain's Pydantic parsers and tool calling, with runnable code at every step.
- Structured output with LangChain and Pydantic toolsHow-toBuild reliable structured output pipelines using LangChain tool calling with Pydantic models — complete with validation, error handling, and production patterns.
- Structuring CrewAI tasks with Pydantic output modelsHow-toLearn to enforce structured outputs in CrewAI tasks using Pydantic models with step-by-step code examples and validation patterns.
- Styling a chat UI built with Vercel AI SDK's useChatHow-toA practical guide to styling a streaming chat UI with Vercel AI SDK's useChat hook, covering message bubbles, streaming states, markdown, and responsive layouts.
- Sub-question query engine in LlamaIndex explainedGuideA practical guide to LlamaIndex's SubQuestionQueryEngine — when to use it, how it decomposes complex queries, and production patterns for multi-document RAG.
- Supabase pgvector plus LangChain for RAGHow-toBuild a production RAG pipeline with Supabase pgvector and LangChain — from schema design to retrieval tuning, with runnable code at each step.
- Swapping models mid-conversation with LlamaIndexHow-toLearn to swap models mid-conversation in LlamaIndex with a conversation manager that preserves context, handles provider fallbacks, and routes dynamically across OpenAI, Anthropic, and local models.
- Switch models in LangChain without changing your n4n.ai codeGuideLearn to switch models in LangChain using n4n.ai's routing layer without code changes — runtime directives, fallbacks, and observability patterns.
- Switching LLM providers in LlamaIndex in five minutesHow-toLearn to switch LLM providers in LlamaIndex with a unified endpoint — swap GPT-5, Claude, Gemini, and Llama models in minutes without rewriting your application code.
- Switching models mid-conversation with Vercel AI SDKHow-toLearn how to switch models mid-conversation using Vercel AI SDK with practical code examples for streaming, tool calling, and state management.
- Taking AutoGen human-in-the-loop agents to productionGuideA practical guide to deploying AutoGen human-in-the-loop agents in production, covering state persistence, approval workflows, observability, and scaling patterns.
- Test your n4n.ai LangChain setup with a simple prompt chainHow-toA step-by-step guide to verifying your LangChain integration with n4n.ai using a runnable prompt chain, including dependency setup, client configuration, and success criteria.
- Testing a Vercel AI SDK chatbot end to endHow-toLearn to test a Vercel AI SDK chatbot end-to-end with Playwright, covering streaming responses, tool calls, and CI integration.
- Token-efficient conversation summarization in LangChainGuideLearn practical langchain token efficient summarization patterns for production conversational systems — memory types, custom strategies, and pitfalls to avoid.
- Token limits and chat memory truncation in LlamaIndexGuideA practical guide to handling token limits and chat memory truncation in LlamaIndex with working code patterns and production tradeoffs.
- Tool calling across models: GPT-4o vs Llama 3.1 via n4n.aiComparisonCompare GPT-4o and Llama 3.1 tool calling performance, schema adherence, and integration patterns for production LLM applications.
- Tool calling with Claude 3.5 Sonnet through n4n.aiTutorialBuild a working tool-calling loop with Claude 3.5 Sonnet using Vercel AI SDK and n4n.ai's OpenAI-compatible endpoint, with runnable code at every step.
- Track RAG regression in LlamaIndex with evaluation metricsGuideA practical guide to building regression tests for LlamaIndex RAG pipelines using evaluation metrics, with code examples and common pitfalls.
- Transcribe and summarize calls with Whisper and LangChainHow-toBuild a production-ready pipeline to transcribe audio calls with Whisper and summarize them using LangChain, with code you can run today.
- Trim LangChain prompts with tiktoken to save on tokensHow-toLearn to trim LangChain prompts with tiktoken for token savings — step-by-step guide with runnable code and verification methods.
- Troubleshooting LangChain connection errors with n4n.aiHow-toFix LangChain connection errors with n4n.ai using systematic debugging steps, code examples, and verification checks for reliable LLM integration.
- Tune top-k retrieval in LlamaIndex query enginesHow-toLearn how to tune top-k retrieval in LlamaIndex query engines with a step-by-step guide covering baseline measurement, reranking, hybrid search, and automated evaluation.
- Type-safe LLM responses in LangChain with PydanticGuideBuild type-safe LLM pipelines with LangChain and Pydantic — schemas, parsers, validation, streaming, and the gotchas that bite in production.
- TypeScript setup for Vercel AI SDK and n4n.aiHow-toA step-by-step guide to configuring TypeScript with Vercel AI SDK and n4n.ai for production-ready LLM inference with automatic fallback and usage metering.
- TypeScript types for LangChain.js runnables explainedDefinitionA practical guide to LangChain.js runnable types in TypeScript — what they are, how input/output generics work, and how to compose typed chains without fighting the compiler.
- useChat vs useCompletion in the Vercel AI SDKComparisonA practical comparison of useChat and useCompletion in the Vercel AI SDK, covering when to use each hook for streaming LLM responses in production applications.
- useChat with multiple models: switching mid-conversationHow-toLearn how to switch LLM models mid-conversation with Vercel AI SDK's useChat hook, including routing logic, state management, and provider fallback patterns.
- Using AutoGen's LocalCommandLineCodeExecutor safelyHow-toLearn to run AutoGen's LocalCommandLineCodeExecutor securely with sandboxing, allowlists, resource limits, and monitoring — production-ready patterns for code-executing agents.
- Using Claude 3.5 Sonnet as a judge in Haystack evaluationTutorialStep-by-step tutorial for wiring Claude 3.5 Sonnet as an LLM judge in Haystack evaluation pipelines, with runnable code and expected outputs.
- Using Elasticsearch as a Haystack document storeHow-toA complete elasticsearch haystack document store tutorial with step-by-step setup, indexing, retrieval, and production hardening for engineers building RAG pipelines.
- Using GPT-4o mini in a Haystack agent pipelineTutorialBuild a Haystack 2.0 agent pipeline with GPT-4o mini, including tools, memory, and streaming responses — complete with runnable code and expected outputs.
- Using Llama 3.1 70B in a Haystack RAG pipeline via n4n.aiTutorialBuild a production-ready RAG pipeline with Haystack and Llama 3.1 70B using n4n.ai's OpenAI-compatible endpoint. Includes indexing, retrieval, and generation code with expected outputs.
- Using Qdrant as a Haystack document storeHow-toA step-by-step guide to wiring Qdrant as a Haystack document store, from Docker setup through hybrid retrieval with metadata filtering.
- Vercel AI SDK chatbot with Claude 3.5 Sonnet and n4n.aiTutorialBuild a production-ready chatbot using Vercel AI SDK, Next.js, and Claude 3.5 Sonnet via n4n.ai with streaming, tool calling, and error handling.
- Vercel AI SDK environment variables for n4n.ai API keysHow-toConfigure Vercel AI SDK with n4n.ai API keys using environment variables for local development and production deployments.
- Vercel AI SDK setup checklist for n4n.ai beginnersListicleA practical checklist for wiring Vercel AI SDK to n4n.ai — install, configure, stream, add tools, observe, and handle failures like a pro.
- Vercel AI SDK setup guide for n4n.ai's 240+ modelsGuideA practical guide to configuring Vercel AI SDK with n4n.ai's model catalog, covering provider setup, routing, streaming, and common integration pitfalls.
- Vercel AI SDK setup: Llama 3.1 70B via n4n.aiTutorialBuild a production-ready Vercel AI SDK integration with Llama 3.1 70B using n4n.ai as the inference gateway — complete with streaming, tool calling, and error handling.
- Vercel AI SDK setup with n4n.ai: Claude 3.5 Sonnet exampleTutorialStep-by-step tutorial for wiring Vercel AI SDK to n4n.ai with Claude 3.5 Sonnet, including streaming, tool calls, and error handling.
- Vercel AI SDK toolChoice parameter: forced vs autoComparisonCompare Vercel AI SDK toolChoice modes — auto, required, and forced function — with code examples, a decision table, and use-case verdicts.
- Vercel AI SDK useChat: message history and persistenceHow-toA step-by-step guide to implementing message history and persistence with Vercel AI SDK's useChat hook, covering local storage, server-side persistence, and streaming state recovery.
- Vision-language chat with Claude 3.5 Sonnet in LangChainTutorialBuild a production-ready vision chat application using Claude 3.5 Sonnet and LangChain with streaming, multi-image support, and error handling.
- Visual product search with LangChain and multi-modal modelsTutorialBuild a visual product search system using LangChain and multi-modal embeddings — from image ingestion to vector search with runnable code at each step.
- Visualize a LlamaIndex knowledge graph with pyvisHow-toA step-by-step tutorial for extracting a LlamaIndex knowledge graph and rendering it interactively with pyvis, including code you can run today.
- Voice-to-text pipelines with Deepgram and LlamaIndexTutorialBuild a production-ready voice-to-text pipeline using Deepgram for transcription and LlamaIndex for retrieval-augmented querying over audio content.
- Web scraping documents into LangChain with WebBaseLoaderHow-toA practical guide to scraping web documents into LangChain using WebBaseLoader, covering authentication, JavaScript rendering, custom parsing, and pipeline integration.
- When to use hierarchical process in CrewAI crewsGuideA practical guide to choosing hierarchical over sequential processes in CrewAI, with code patterns, decision criteria, and common pitfalls.
- Which AI framework fits a solo developer's side projectGuideA practical decision framework for solo developers choosing between LangChain, LlamaIndex, Vercel AI SDK, and raw APIs for side projects.
- Which framework to use for a customer-facing support agentGuideA practical guide to selecting the best framework for customer support agent development, covering requirements, tradeoffs, and architecture patterns for production systems.
- Why we moved from the raw OpenAI SDK to LangGraphAnalysisA senior engineer's honest breakdown of migrating from the raw OpenAI SDK to LangGraph — where the SDK breaks down, what LangGraph actually solves, and the tradeoffs you'll live with.
- Writing clear CrewAI task descriptions that agents followHow-toLearn to write CrewAI task descriptions that agents actually follow — step-by-step patterns, code examples, and verification techniques for reliable agent execution.
- Your first Haystack pipeline with n4n.ai and Qwen3TutorialBuild a production-ready Haystack pipeline using n4n.ai's OpenAI-compatible endpoint to serve Qwen3 models, with document retrieval and generation components.
- Compress context in LangChain to reduce token costsTutorialLearn to implement langchain context compression reduce tokens techniques with runnable code, token counting, and production patterns for LLM cost optimization.
- CrewAI example: automated meeting notes and follow-upsHow-toBuild a CrewAI pipeline that transcribes meetings, extracts action items, and drafts follow-up emails — complete with runnable code and verification steps.
- CrewAI finance research: analyst and skeptic agentsTutorialBuild a multi-agent finance research system with CrewAI — analyst and skeptic agents that debate investment theses using real market data.
- CrewAI hierarchical crews for complex research tasksHow-toBuild a CrewAI hierarchical crew for multi-stage research with a manager agent coordinating specialized researchers, analysts, and writers.
- CrewAI hierarchical process tutorial: manager LLM setupTutorialBuild a CrewAI hierarchical crew with a manager LLM — prerequisites, agent definitions, task delegation, and runnable code with expected outputs.
- CrewAI n4n.ai setup: choosing models per agentHow-toConfigure CrewAI agents with different models via n4n.ai — step-by-step setup with code, routing directives, and verification.
- CrewAI real-world example: financial report summarizationHow-toBuild a CrewAI financial report summarization pipeline with agents for extraction, analysis, and narrative generation — runnable code included.
- CrewAI real-world example: legal contract reviewHow-toBuild a CrewAI pipeline that extracts, classifies, and flags risky clauses in legal contracts with runnable code and verification steps.
- CrewAI role design: writing effective agent backstoriesHow-toLearn practical crewai agent backstory writing tips with step-by-step examples, runnable code, and a verification checklist for production agents.
- CrewAI sequential process tutorial with n4n.ai modelsTutorialBuild a CrewAI sequential process pipeline using n4n.ai models with step-by-step code, from prerequisites to a working multi-agent workflow.
- CrewAI setup tutorial: API keys, models, and configTutorialA hands-on tutorial for configuring CrewAI with API keys, model selection, and YAML configuration — from prerequisites to a working multi-agent crew.
- CrewAI support bot: agents for tier-1 and tier-2 ticketsTutorialBuild a CrewAI support bot that routes and resolves tier-1 and tier-2 tickets with specialized agents, using real code and observable checkpoints.
- CrewAI task design tutorial: context sharing between tasksTutorialLearn how to share context between CrewAI tasks with practical code examples, covering output passing, memory, and callback patterns for multi-agent workflows.
- CrewAI vs AutoGen vs LangGraph for a coding agentGuideA practical comparison of CrewAI, AutoGen, and LangGraph for building coding agents, with code examples and architectural tradeoffs.
- CrewAI vs AutoGen: which supports human-in-the-loop betterComparisonCompare CrewAI and AutoGen on human-in-the-loop patterns: interruption, approval flows, state replay, tool confirmation, and observability.
- CrewAI vs LangGraph: roles vs graphs for agent orchestrationComparisonA practitioner's comparison of CrewAI's role-based agents versus LangGraph's graph-based orchestration, with code examples and a clear verdict by use case.
- Custom baseURL setup: Vercel AI SDK meets n4n.aiHow-toConfigure Vercel AI SDK to route requests through n4n.ai with a custom baseURL, including provider fallback, streaming, and usage metering.
- Custom data loaders in LlamaIndex: a how-to guideHow-toBuild custom LlamaIndex data loaders to ingest any data source — step-by-step implementation with runnable code and verification.
- Custom LangChain callbacks for token usage trackingHow-toBuild a production-ready LangChain custom callback handler for token usage tracking with streaming support, cost calculation, and structured logging.
- Customer support bot: LlamaIndex plus a vector databaseTutorialBuild a production-ready customer support bot with LlamaIndex and a vector database — complete with document ingestion, retrieval, and streaming responses.
- Cut inference costs with vLLM continuous batchingGuideLearn how vLLM continuous batching reduces inference cost by maximizing GPU utilization, with practical setup, tuning, and measurement steps.
- Debugging LangChain agent tool selection errorsHow-toA step-by-step guide to diagnosing and fixing LangChain agent tool selection failures, from schema mismatches to prompt confusion.
- DeepSeek-R1 reasoning chains in LangGraph: a walkthroughTutorialBuild a DeepSeek-R1 reasoning chain in LangGraph with streaming, state management, and fallback handling — complete runnable code included.
- Deploy a Vercel AI SDK chatbot to productionHow-toA step-by-step guide to deploying a Vercel AI SDK chatbot to production with Next.js, covering API routes, streaming, edge runtime, and observability.
- Deploying a LangChain.js app to VercelHow-toA step-by-step guide to deploying a LangChain.js application to Vercel with serverless functions, environment configuration, and streaming responses.
- Deploying a Vercel AI SDK app with n4n.ai on the edgeHow-toDeploy a Vercel AI SDK streaming chat app to the edge runtime using n4n.ai as the model gateway, with runnable code and verification steps.
- Designing CrewAI agent roles for a content pipelineHow-toA step-by-step guide to designing CrewAI agent roles and tasks for a production content pipeline, with runnable code and verification checkpoints.
- Dynamic model selection at request time in Vercel AI SDKHow-toLearn to implement vercel ai sdk dynamic model selection at request time with runtime routing, provider fallbacks, and per-request model overrides.
- E-commerce hybrid search: keyword plus vector in LangChainTutorialBuild production-ready hybrid search for e-commerce using LangChain — combine BM25 keyword matching with vector embeddings, add cross-encoder reranking, and evaluate with real metrics.
- E-commerce search: filtering and reranking in LlamaIndexTutorialBuild production e-commerce search with LlamaIndex: metadata filtering, hybrid retrieval, and cross-encoder reranking for relevant product results.
- Earnings call analysis with LlamaIndex and RAGTutorialBuild a production-ready earnings call analysis pipeline with LlamaIndex and RAG — from transcript ingestion to structured financial extraction.
- Edge vs Node.js runtime for Vercel AI SDK streamingComparisonA head-to-head comparison of Edge and Node.js runtimes for Vercel AI SDK streaming, covering capabilities, costs, latency, ergonomics, and limits with a clear verdict by use case.
- Entity memory in LangChain: tracking facts across turnsGuideA practical guide to implementing LangChain entity memory for tracking facts across conversation turns, with code examples and production considerations.
- Error handling and fallbacks in LCEL chainsGuidePractical guide to implementing robust error handling, retries, and fallback strategies in LangChain Expression Language chains for production LLM applications.
- Evaluate LlamaIndex RAG with Claude as judge on n4n.aiTutorialBuild a LlamaIndex RAG evaluation pipeline using Claude as an LLM judge, with runnable code for retrieval and generation metrics.
- Evaluating a support bot's accuracy before you ship itGuideA practical framework for measuring support bot accuracy with test sets, automated judges, and regression gates before production deployment.
- Extract entities and relations with LlamaIndex KG indexHow-toLearn to build a knowledge graph from unstructured text using LlamaIndex's KG index with entity and relation extraction, including querying and verification steps.
- FAISS vector search in LangChain for local RAG prototypesHow-toBuild a local RAG prototype with LangChain and FAISS — complete setup, indexing, retrieval, and generation steps with runnable code.
- Fine-tune Llama 4 Scout with Hugging Face TransformersTutorialA step-by-step guide to fine-tuning Llama 4 Scout with Hugging Face Transformers, covering LoRA, quantization, and distributed training.
- Fix malformed JSON in LangChain with OutputFixingParserHow-toLearn to fix malformed JSON from LLMs using LangChain's OutputFixingParser with practical code examples and production patterns.
- From openai.ChatCompletion to LlamaIndex: what changesGuideA practical migration guide for engineers moving from raw OpenAI ChatCompletion calls to LlamaIndex, covering client setup, streaming, tool calling, and common pitfalls.
- From raw OpenAI SDK to AutoGen: adding multi-agent supportHow-toA step-by-step guide to migrating from raw OpenAI SDK calls to AutoGen for multi-agent workflows, with runnable code and verification checkpoints.
- Generate matplotlib charts with AutoGen code agentsHow-toA step-by-step guide to building AutoGen agents that write, execute, and iterate on matplotlib visualization code with Docker sandboxing.
- Generative UI weather widget with Vercel AI SDKTutorialBuild a generative UI weather widget with Vercel AI SDK using React Server Components, streaming tool calls, and server-side rendering for real-time weather data.
- Generative UI with Claude 3.5 Sonnet via n4n.ai and RSCTutorialBuild generative UI with Claude 3.5 Sonnet using n4n.ai as the inference gateway and React Server Components for streaming, type-safe component rendering.
- Handling loading and error states in useChatHow-toComplete guide to handling loading and error states in Vercel AI SDK's useChat hook with practical patterns for production chat UIs.
- Handling rate limit fallback across models in AI SDKHow-toA step-by-step guide to implementing automatic model fallback on rate limits using the Vercel AI SDK, with runnable code and verification strategies.
- Haystack agent pipeline tutorial for customer supportTutorialBuild a production-ready Haystack 2.0 agent pipeline for customer support with tool calling, RAG, and structured outputs — complete with runnable code and checkpoint outputs.
- Haystack agent pipeline tutorial with web search toolsTutorialBuild a Haystack 2.x agent pipeline with web search tools — prerequisites, runnable code, and production patterns for reliable tool use.
- Haystack document store tutorial: Weaviate setup guideTutorialComplete hands-on tutorial for setting up Haystack with Weaviate as a document store, from prerequisites through indexing and retrieval with runnable code.
- Haystack evaluation pipeline tutorial: faithfulness metricsTutorialBuild a Haystack evaluation pipeline to measure RAG faithfulness with runnable code, from dataset prep to metric interpretation.
- Haystack evaluation pipeline tutorial with context relevanceTutorialBuild a Haystack evaluation pipeline that measures context relevance for RAG systems, with runnable code and expected outputs at each step.
- Haystack n4n.ai setup: choosing embedding modelsHow-toA step-by-step guide to configuring Haystack with n4n.ai for embedding models, covering model selection, pipeline wiring, and verification.
- Haystack n4n.ai setup: configuring the OpenAIGeneratorHow-toConfigure Haystack's OpenAIGenerator to route requests through n4n.ai with model fallback, usage metering, and provider-agnostic code.
- Haystack n4n.ai setup: switching models without code changesHow-toConfigure Haystack to route requests through n4n.ai so you can swap LLMs by changing a config value — no pipeline rewrites required.
- Haystack PGVector document store tutorialTutorialBuild a production-ready Haystack PGVector document store with Postgres, including hybrid search, metadata filtering, and index tuning.
- Haystack PromptBuilder tutorial for RAG pipelinesTutorialBuild a production-ready RAG pipeline with Haystack's PromptBuilder — from basic templates to advanced conditional logic, with runnable code at every step.
- Haystack RAG pipeline tutorial: from PDF to answerTutorialBuild a production-ready Haystack RAG pipeline that extracts text from PDFs, indexes it, and answers questions with citations — complete with runnable code and expected outputs.
- Haystack RAG pipeline tutorial with hybrid retrievalTutorialBuild a production-ready Haystack RAG pipeline with hybrid retrieval combining BM25 and dense embeddings for better search relevance.
- Haystack RAG with Claude 3.5 Sonnet through n4n.aiTutorialBuild a production-ready Haystack RAG pipeline using Claude 3.5 Sonnet via n4n.ai with document indexing, retrieval, and generation steps.
- Haystack ReAct agent tutorial: search and calculateTutorialBuild a Haystack 2.0 ReAct agent with search and calculator tools — complete runnable code, prerequisites, and expected outputs.
- Haystack retriever tutorial: BM25 vs embedding retrievalComparisonCompare BM25 and embedding retrievers in Haystack across latency, cost, accuracy, and operational complexity with code examples and a verdict by use case.
- Haystack setup tutorial: document stores explainedDefinitionA practical guide to Haystack document stores — what they are, how they work, and how to choose the right one for your RAG pipeline.
- Human-in-the-loop conversations with AutoGenHow-toA practical guide to implementing human-in-the-loop conversations with AutoGen, covering user proxy agents, approval workflows, and state persistence for production multi-agent systems.
- Human review checkpoints in AutoGen GroupChatHow-toLearn to add human review checkpoints to AutoGen GroupChat workflows with step-by-step code examples and verification strategies.
- Hybrid knowledge graph and vector retrieval in LlamaIndexTutorialBuild a production-ready hybrid retrieval system combining knowledge graphs and vector search in LlamaIndex with runnable code and evaluation benchmarks.
- Hybrid search in LangChain: combining BM25 and embeddingsGuideA practical guide to implementing hybrid search in LangChain by combining BM25 keyword search with dense vector embeddings for better retrieval accuracy.
- Hybrid search query engine in LlamaIndex tutorialTutorialBuild a production-ready hybrid search query engine in LlamaIndex combining vector similarity and BM25 keyword search with runnable code and tuning guidance.
- Incremental ingestion in LlamaIndex with document hashesHow-toLearn to implement incremental ingestion in LlamaIndex using document hashes to avoid reprocessing unchanged files and reduce embedding costs.
- Ingest a Postgres database into LlamaIndexHow-toA step-by-step guide to ingesting Postgres data into LlamaIndex using SQLDatabase and VectorStoreIndex, with runnable code and verification steps.
- Install and configure LlamaIndex for n4n.aiHow-toA step-by-step guide to installing LlamaIndex and wiring it to n4n.ai for LLM inference, with runnable code and verification steps.
- Install langchain-openai and route requests through n4n.aiHow-toInstall langchain-openai, configure the base URL to n4n.ai, and verify requests route through the gateway with automatic fallback and usage metering.
- Integrate Mistral Small 3.1 into a LlamaIndex RAG pipelineTutorialBuild a production-ready RAG pipeline with Mistral Small 3.1 and LlamaIndex, including document ingestion, retrieval, and generation with runnable code.
- Integrating CrewAI agents with a REST API toolHow-toBuild a CrewAI custom tool that calls a REST API, with authentication, error handling, and structured output parsing for production use.
- Integrating CrewAI with LangChain toolsHow-toLearn to wrap LangChain tools for CrewAI agents with a complete, runnable example — from custom tool definition to multi-agent execution.
- Knowledge graph RAG with LlamaIndex and Neo4jTutorialBuild a production-ready knowledge graph RAG pipeline using LlamaIndex and Neo4j with step-by-step code, from schema design to hybrid retrieval.
- LangChain agents vs function calling: which to useComparisonA practical comparison of LangChain agents versus native function calling for engineers choosing the right tool orchestration approach.
- LangChain astream_events explained with examplesDefinitionLangChain's astream_events method explained with working code examples — how the event stream works, when to use it over astream/astream_log, and common pitfalls.
- LangChain callbacks: logging every step of a chainGuideA practical guide to implementing LangChain callbacks for logging every step of a chain, with code examples and common pitfalls.
- LangChain ConversationBufferWindowMemory tutorialTutorialA hands-on tutorial for LangChain ConversationBufferWindowMemory with runnable code, expected outputs, and production patterns for managing conversational context windows.
- LangChain create_tool_calling_agent explainedDefinitionA practical breakdown of LangChain's create_tool_calling_agent — what it does, how it wires models to tools, and the pitfalls that trip up production teams.
- LangChain document loaders for Notion and ConfluenceHow-toA practical guide to loading Notion and Confluence content into LangChain with working code, chunking strategies, and verification steps.
- LangChain environment variables for n4n.ai base URL and keyHow-toConfigure LangChain to route requests through n4n.ai using environment variables for base URL and API key, with verification steps and troubleshooting.
- LangChain fallback chains for provider outagesGuideBuild resilient LLM applications with LangChain fallback chains that automatically route around provider outages and rate limits.
- LangChain function calling on Claude 3.5 SonnetHow-toA step-by-step guide to implementing LangChain function calling with Claude 3.5 Sonnet, covering tool definition, agent setup, and production patterns.
- LangChain.js LCEL chains in TypeScriptHow-toBuild production-ready LCEL chains in TypeScript with streaming, branching, and error handling — runnable code at every step.
- LangChain.js memory management for Node chat appsGuidePractical guide to LangChain.js memory management in Node chat apps — buffer, summary, and vector stores with code patterns and tradeoffs.
- LangChain.js RAG tutorial with Chroma and NodeTutorialBuild a production-ready RAG pipeline with LangChain.js, Chroma, and Node.js — complete with document loading, embedding, retrieval, and streaming answers.
- LangChain.js streaming responses in an Express APIHow-toBuild a production-ready Express API with LangChain.js streaming responses, including error handling, token usage tracking, and client-side consumption patterns.
- LangChain.js vs LangChain Python: key differencesComparisonA practitioner's head-to-head comparison of LangChain.js and LangChain Python across capabilities, ergonomics, ecosystem, and production trade-offs.
- LangChain memory with Redis for multi-session chatbotsHow-toBuild production-ready multi-session chatbots using LangChain memory with Redis — complete setup, code patterns, and verification steps.
- LangChain output parsers: Pydantic vs JSON vs XMLComparisonCompare LangChain output parsers — Pydantic, JSON, and XML — across validation, ergonomics, streaming, and failure modes to pick the right one for your LLM pipeline.
- LangChain PydanticOutputParser: a complete guideGuideA practical guide to LangChain's PydanticOutputParser with code examples, common pitfalls, and production patterns for reliable structured LLM output.
- LangChain RAG evaluation with RAGAS and n4n.aiHow-toA step-by-step guide to evaluating LangChain RAG pipelines with RAGAS, including synthetic dataset generation, metric selection, and CI integration.
- LangChain RAG with Weaviate: a step-by-step guideGuideBuild production-ready RAG with LangChain and Weaviate — from ingestion to retrieval, with code, pitfalls, and scaling tradeoffs.
- LangChain retry vs fallback: which strategy to useComparisonCompare LangChain retry and fallback strategies across capabilities, cost, latency, ergonomics, and limits with a clear verdict for each use case.
- LangChain streaming vs batch responses: latency comparedAnalysisA practical comparison of LangChain streaming vs batch latency with code examples, callback overhead analysis, and production guidance for engineers.
- LangChain summary memory with n4n.ai for long chatsHow-toImplement LangChain summary memory with n4n.ai to handle long conversations without token overflow, including fallback routing and usage metering.
- LangChain tool calling with Llama 3.3 70B on n4n.aiHow-toBuild a LangChain agent that calls tools with Llama 3.3 70B via n4n.ai — complete setup, code, and verification steps.
- LangChain vs LlamaIndex: chunking and indexing strategiesComparisonA practical comparison of LangChain and LlamaIndex chunking and indexing approaches for RAG systems, with code examples and a decision framework.
- LangChain vs LlamaIndex: which handles hybrid search betterComparisonA practitioner's head-to-head comparison of LangChain and LlamaIndex for hybrid search, covering retrieval APIs, reranking, ergonomics, and when to choose each.
- LangGraph conditional edges: routing between agentsDefinitionLangGraph conditional edges enable dynamic agent routing based on state — here's how they work, when to use them, and a production-ready example.
- LangGraph human-in-the-loop workflowsGuideBuild production-ready langgraph human in the loop workflows with interrupt handling, state persistence, and approval patterns that scale.
- LangGraph vs AutoGen: which handles agent state betterComparisonCompare LangGraph and AutoGen on agent state management — graph-based checkpoints vs conversational context, with code patterns and a clear verdict by use case.
- LangGraph vs LangChain agents: when to use eachComparisonA practical comparison of LangGraph and LangChain agents across architecture, control flow, debugging, and production readiness — with a clear verdict for each use case.
- LangGraph with Claude 3.5 Sonnet and GPT-4o in one graphHow-toBuild a LangGraph workflow that routes tasks between Claude 3.5 Sonnet and GPT-4o based on capability, with runnable code and verification steps.
- LCEL RunnableBranch: conditional logic in chainsDefinitionLCEL RunnableBranch lets you route inputs to different chains based on conditions — here's how it works, when to use it, and a production-ready example.
- LCEL RunnableParallel for multi-step LangChain pipelinesHow-toBuild multi-step LangChain pipelines with LCEL RunnableParallel — parallel branches, shared state, error handling, and verification steps.
- Legal document search with LangChain and hybrid retrievalTutorialBuild a production-ready legal document search system using LangChain with hybrid retrieval combining dense embeddings and BM25 sparse vectors.
- LlamaIndex agent memory and state managementGuideA practical guide to implementing memory and state management in LlamaIndex agents, covering chat buffers, vector memory, persistence patterns, and common production pitfalls.
- LlamaIndex agents vs LangChain agents comparedComparisonA practitioner's head-to-head comparison of LlamaIndex and LangChain agent architectures, tool use patterns, memory models, and ecosystem trade-offs — with a clear verdict by use case.
- LlamaIndex agents with Claude 3.5 Sonnet on n4n.aiTutorialBuild a LlamaIndex agent with Claude 3.5 Sonnet using n4n.ai's OpenAI-compatible endpoint — complete with tool use, streaming, and fallback handling.
- LlamaIndex AgentWorkflow for multi-step tasksTutorialBuild multi-step LLM agents with LlamaIndex AgentWorkflow — prerequisites, step-by-step implementation, and runnable code for production workflows.
- LlamaIndex base URL and auth setup for n4n.aiGuideConfigure LlamaIndex to route requests through n4n.ai with correct base URL, API key handling, and fallback behavior for production workloads.
- LlamaIndex chat engine with n4n.ai and Claude modelsTutorialBuild a production-ready LlamaIndex chat engine using n4n.ai's OpenAI-compatible endpoint to access Claude models with automatic fallback and token metering.
- LlamaIndex chat engine with streaming responsesHow-toBuild a LlamaIndex chat engine with streaming responses — step-by-step setup, memory integration, and verification.
- LlamaIndex chat memory buffer: how it worksGuideA practical guide to LlamaIndex's ChatMemoryBuffer — how token limits work, when to use summarization, and common pitfalls in production chat applications.
- LlamaIndex ComposableGraph for multi-document indexesTutorialBuild a LlamaIndex ComposableGraph to query across multiple document indexes with a hands-on tutorial covering setup, index composition, and routing strategies.
- LlamaIndex CondenseQuestion engine for chat-based RAGTutorialBuild a chat-based RAG system using LlamaIndex's CondenseQuestion engine with step-by-step code and expected outputs.
- LlamaIndex correctness evaluation for RAG answersGuideLearn how to evaluate RAG answer correctness with LlamaIndex — from basic LLM-as-judge to custom criteria, with code and common pitfalls.
- LlamaIndex document summary index for large corporaGuideBuild a LlamaIndex document summary index for large corpora with practical configuration, query patterns, and production pitfalls.
- LlamaIndex FaithfulnessEvaluator vs RelevancyEvaluatorComparisonCompare LlamaIndex FaithfulnessEvaluator and RelevancyEvaluator across capabilities, cost, latency, and failure modes to pick the right RAG metric.
- LlamaIndex Google Drive connector setupHow-toA complete LlamaIndex Google Drive connector tutorial with authentication, document loading, and verification steps for production RAG pipelines.
- LlamaIndex ingestion caching to cut embedding costsHow-toA step-by-step guide to implementing LlamaIndex ingestion caching with persistent storage, cache invalidation strategies, and cost verification techniques.
- LlamaIndex knowledge graph vs vector index comparedComparisonA practitioner's head-to-head comparison of LlamaIndex knowledge graphs and vector indexes across capabilities, cost, latency, ergonomics, and limits — with a clear verdict by use case.
- LlamaIndex LLM vs embedding model setup on n4n.aiGuideConfigure LlamaIndex to use separate LLM and embedding models through n4n.ai's OpenAI-compatible endpoint with automatic fallback and per-token metering.
- LlamaIndex OpenAIAgent with n4n.ai function callingTutorialBuild a LlamaIndex OpenAIAgent that routes function calls through n4n.ai with automatic provider fallback and per-token metering.
- LlamaIndex OpenAILike class with n4n.ai modelsTutorialHands-on tutorial for using LlamaIndex's OpenAILike class with n4n.ai's OpenAI-compatible endpoint, covering chat, streaming, embeddings, and RAG.
- LlamaIndex PropertyGraphIndex with Claude on n4n.aiTutorialBuild a knowledge graph with LlamaIndex PropertyGraphIndex using Claude via n4n.ai — complete runnable code from extraction to querying.
- LlamaIndex query engine with Claude 3.5 Sonnet on n4n.aiTutorialBuild a production-ready RAG pipeline using LlamaIndex query engines with Claude 3.5 Sonnet via n4n.ai's OpenAI-compatible endpoint.
- LlamaIndex QueryEngineTool: turning RAG into a toolGuideLearn to wrap LlamaIndex query engines as tools for agents, with working patterns for multi-index routing, metadata filtering, and error handling.
- LlamaIndex response modes: compact, refine, tree summarizeComparisonCompare LlamaIndex response modes — compact, refine, tree_summarize — across latency, cost, quality, and token limits with a decision guide for RAG query engines.
- LlamaIndex retrieval evaluation dataset generationHow-toGenerate synthetic evaluation datasets for LlamaIndex retrieval systems using LLMs, with runnable code for question generation, relevance labeling, and dataset validation.
- LlamaIndex retrieval evaluation: precision vs recallComparisonA practical comparison of precision vs recall evaluation in LlamaIndex retrieval systems, with code examples and a decision framework for choosing the right metric.
- LlamaIndex RouterQueryEngine for multi-source RAGTutorialBuild a production-ready multi-source RAG system using LlamaIndex RouterQueryEngine with step-by-step code and real output examples.
- LlamaIndex Settings.llm configuration with n4n.aiHow-toConfigure LlamaIndex Settings.llm to route requests through n4n.ai with automatic fallback, per-token metering, and OpenAI-compatible endpoints.
- LlamaIndex SimpleChatEngine vs ContextChatEngineComparisonTechnical comparison of LlamaIndex SimpleChatEngine and ContextChatEngine — capabilities, trade-offs, and when to use each.
- LlamaIndex SQL query engine for structured dataTutorialBuild a production-ready LlamaIndex SQL query engine for structured data with step-by-step code, from schema setup to natural language queries.
- LlamaIndex TypeScript setup with n4n.aiTutorialA hands-on tutorial for building a LlamaIndex TypeScript RAG pipeline using n4n.ai as the LLM gateway, with runnable code at every step.
- LlamaIndex vs LangChain: retrieval quality on 10,000 docsComparisonHead-to-head retrieval quality benchmark of LlamaIndex and LangChain on 10,000 documents with concrete metrics, code patterns, and a clear verdict by use case.
- LlamaIndex web page ingestion with SimpleWebPageReaderHow-toA step-by-step guide to ingesting web pages with LlamaIndex SimpleWebPageReader, covering installation, multi-URL handling, HTML cleaning, chunking, and verification.
- Load balance LLM calls in LangChain with n4n.aiHow-toA practical guide to implementing LLM load balancing and fallback in LangChain using n4n.ai's unified endpoint for multi-model routing.
- Load Notion pages into LlamaIndex with NotionPageReaderHow-toLearn to ingest Notion pages into LlamaIndex using NotionPageReader with authentication, filtering, and incremental sync patterns.
- Loading PDFs into LangChain with PyPDFLoaderHow-toLearn to load PDFs into LangChain using PyPDFLoader with step-by-step code examples, metadata extraction, text splitting, and error handling for production use.
- Lower per-token costs with LiteLLM request batchingHow-toLearn how to implement LiteLLM request batching to cut per-token costs with step-by-step code examples and verification methods.
- Measure faithfulness in LlamaIndex RAG with n4n.aiHow-toLearn to measure faithfulness in LlamaIndex RAG pipelines with a complete end-to-end tutorial including code, evaluation setup, and result interpretation.
- Migrating a RAG app from LlamaIndex to LangChainHow-toA step-by-step guide to migrating a production RAG application from LlamaIndex to LangChain with runnable code and verification checkpoints.
- Migrating a raw OpenAI chatbot to CrewAI agentsHow-toLearn how to migrate an OpenAI chatbot to CrewAI agents with step-by-step code examples, covering agent design, task decomposition, state management, and verification.
- Migrating LangChain memory to the message history APIHow-toStep-by-step guide to migrating deprecated LangChain memory classes to the modern BaseChatMessageHistory API with runnable code and verification steps.
- Migrating legacy LangChain chains to LCELHow-toStep-by-step guide to migrating legacy LangChain chains to LCEL with runnable code examples and verification strategies.
- Migrating raw OpenAI function calling to LangChain toolsHow-toStep-by-step guide to migrate raw OpenAI function calling to LangChain tools with runnable code and verification steps.
- Tool calling in LangChain with GPT-4o via n4n.aiHow-toA step-by-step guide to implementing tool calling with LangChain and GPT-4o using n4n.ai as the inference gateway, including runnable code and verification steps.
- 2026 multi-agent frameworks: CrewAI, AutoGen, LangGraphListicleEngineer-focused breakdown of multi-agent frameworks 2026 crewai autogen langgraph: CrewAI, AutoGen, and LangGraph with code and trade-offs for building production LLM systems.
- A/B testing GPT-5 against Claude Opus in LangChainHow-toLearn how to a/b test gpt-5 vs claude in langchain with traffic splitting, token metering, and evaluation harness in a step-by-step guide.
- A CrewAI crew for automated SEO content auditsHow-toStep-by-step crewai seo content audit example: build a multi-agent crew that fetches URLs, analyzes on-page SEO, and outputs actionable fix lists with code.
- A CrewAI crew for e-commerce product description writingHow-toStep-by-step crewai product description writing example: build a CrewAI crew that turns e-commerce specs into polished listings with fallback LLM routing.
- A CrewAI crew that automates competitor researchHow-toStep-by-step guide to build a CrewAI competitor research automation example with multi-agent crews, runnable Python code, and verification tips.
- A product Q&A chatbot from your catalog with LangChainTutorialBuild a product Q&A chatbot from your catalog with LangChain using RAG. Step-by-step tutorial with runnable code for ecommerce retrieval and chat.
- A research assistant built with CrewAI, AutoGen, LangGraphTutorialHands-on tutorial to build research assistant crewai autogen langgraph. Runnable multi-agent code for CrewAI, AutoGen, and LangGraph with sample output.
- A support agent that hands off to a human in LangGraphTutorialStep-by-step LangGraph tutorial: build a support agent that triages requests and hands off to a human via interrupt, with runnable code and expected output.
- Add a human approval gate to AutoGen tool callsHow-toStep-by-step guide to adding a human approval gate to AutoGen tool calls using a Python function wrapper, with runnable code examples and verification steps for safe agents.
- Add conversational memory to a LangChain chatbotHow-toStep-by-step guide to add conversational memory to a LangChain chatbot using buffer and summary memory, with runnable Python code and verification tips.
- Add file uploads to a Vercel AI SDK chatbotHow-toLearn how to add file uploads to a Vercel AI SDK chatbot in Next.js. Step-by-step guide for handling attachments, multimodal messages, and verification.
- Add long-term memory to a LlamaIndex chat engineHow-toLearn how to add persistent cross-session memory to a LlamaIndex chat engine with Redis in this hands-on llamaindex long-term memory chat engine tutorial.
- Add persistent chat history to a Next.js AI SDK chatbotHow-toLearn how to add persistent chat history to a Next.js AI SDK chatbot using Drizzle and Postgres, with step-by-step code and verification tips.
- Add stop and regenerate buttons to your useChat UIHow-toStep-by-step useChat stop regenerate button tutorial for Vercel AI SDK: add stop and regenerate controls to your streaming chat UI with runnable React code.
- Adding a RAG agent to an AutoGen group chatHow-toPractical walkthrough for engineers adding a RAG agent to an AutoGen group chat: wire retrievers, configure agents, run end-to-end, and verify.
- AI-powered product recommendations with LangChainTutorialHands-on tutorial: build AI-powered product recommendations with LangChain using a vector store and LLM chain, from catalog embedding to ranked output.
- Analyze images and PDFs with Gemini 2.0 in LangChainTutorialHands-on tutorial: build multimodal pipelines with Gemini 2.0 and LangChain to analyze images and PDFs locally, with runnable code and expected outputs.
- Authenticate LangChain requests with an n4n.ai API keyHow-toStep-by-step guide to langchain n4n.ai api key authentication: configure ChatOpenAI with the gateway base URL, set your key, and verify requests.
- Auto-route LangChain to the cheapest model with n4n.aiHow-toA practical langchain cheapest model routing tutorial: wire LangChain to an OpenAI-compatible gateway, auto-select low-cost models, and verify token usage.
- AutoGen agent team tutorial: planner, coder, critic rolesTutorialHands-on AutoGen tutorial: build a multi-agent team with planner, coder, and critic roles using group chat to plan, write, and review Python code.
- AutoGen agent teams for report generation and QAHow-toStep-by-step guide to building an AutoGen multi-agent pipeline that researches, drafts, and QA-checks reports with OpenAI-compatible LLM endpoints.
- AutoGen agent teams: termination conditions explainedTutorialA hands-on autogen agent team termination condition tutorial: learn how to control multi-agent loops with clear exit signals and custom predicates.
- AutoGen agent teams tutorial: building a research crewTutorialHands-on autogen agent team research tutorial: build a multi-agent research crew with AutoGen, step-by-step code, and real output checkpoints.
- AutoGen ALWAYS vs TERMINATE vs NEVER input modesComparisonCompare AutoGen human_input_mode ALWAYS vs TERMINATE vs NEVER across cost, latency, ergonomics, and limits, with table and use-case verdicts.
- AutoGen AssistantAgent plus code executor, step by stepHow-toStep-by-step autogen assistantagent code executor tutorial: configure AssistantAgent with a local code executor, run multi-turn coding tasks safely.
- AutoGen code execution tutorial: prompt to PythonTutorialStep-by-step autogen code execution tutorial python: build AutoGen agents that generate, run, and debug Python code locally with full runnable examples.
- AutoGen code execution vs function calling explainedComparisonA practical head-to-head comparison of AutoGen code execution vs function calling across cost, latency, ergonomics, and limits, with a verdict.
- AutoGen config_list basics for n4n.ai's 240+ modelsGuideLearn to build an AutoGen config_list for n4n.ai's 240+ models: endpoint setup, fallback, cache hints, and pitfalls from real deployments.
- AutoGen Docker code executor: a secure setup guideHow-toStep-by-step guide to a hardened AutoGen Docker code executor setup: isolate agent-generated Python in a container, with runnable configs and verification.
- AutoGen GroupChat tutorial: orchestrating multiple agentsTutorialHands-on autogen groupchat tutorial multiple agents: build a multi-agent coding and review pipeline with GroupChat, speaker control, and safe code exec.
- AutoGen GroupChat vs SelectorGroupChat: which to useComparisonA practitioner's head-to-head comparison of AutoGen GroupChat vs SelectorGroupChat across capabilities, cost, latency, ergonomics, and limits for engineers building multi-agent systems.
- AutoGen human-in-the-loop for high-stakes code executionGuideA practical guide to implementing autogen human in the loop code execution safety for high-stakes workflows, with patterns, code, and pitfalls.
- AutoGen human-in-the-loop: pausing agents for reviewHow-toLearn how to implement autogen pause agent for human review workflows with practical code, step-by-step setup, and verification tips for engineers.
- AutoGen human-in-the-loop tutorial for agent approvalsTutorialStep-by-step autogen human in the loop tutorial for agent approvals: build guarded tools, configure UserProxyAgent, and run sign-off flows with code.
- AutoGen human-in-the-loop with Claude Opus 4.5 via n4n.aiHow-toStep-by-step guide to building AutoGen human-in-the-loop workflows with Claude Opus 4.5 through the n4n.ai gateway, including runnable code and verification.
- AutoGen RoundRobinGroupChat explained with an exampleDefinitionRoundRobinGroupChat runs agents in fixed order for predictable multi-agent loops in AutoGen. This autogen roundrobingroupchat tutorial shows code and pitfalls.
- AutoGen SelectorGroupChat: dynamic speaker selectionDefinitionAutoGen SelectorGroupChat speaker selection uses an LLM to dynamically route multi-agent conversations. Learn how it works, with code and pitfalls for building robust agent teams.
- AutoGen setup guide: AssistantAgent and UserProxyAgentGuideStep-by-step Autogen AssistantAgent UserProxyAgent setup guide with working code, config tips, and pitfalls for engineers building multi-agent LLM workflows.
- AutoGen Studio setup with n4n.ai as the model providerHow-toStep-by-step guide to autogen studio setup n4n.ai provider as an OpenAI-compatible model endpoint, from install to verified run with code.
- AutoGen tutorial: a support agent that checks order statusTutorialBuild a multi-agent AutoGen support agent that checks order status via a REST API. Step-by-step tutorial with runnable Python code and expected output for engineers.
- AutoGen vs CrewAI: which is easier to debug in productionComparisonA practitioner's comparison of AutoGen vs CrewAI debugging production tradeoffs across control flow, observability, cost, and latency—with a verdict.
- Automatic model fallback in LiteLLM to cut GPT-4 spendHow-toImplement LiteLLM automatic model fallback to route around GPT-4 limits and slash inference costs. Step-by-step proxy config and code.
- Automatic model fallback with Vercel AI SDK and n4n.aiHow-toStep-by-step guide to vercel ai sdk automatic model fallback n4n.ai: build resilient LLM calls with client-side switching and gateway failover patterns.
- Automatic provider failover in LangChain with n4n.aiHow-toLearn how to implement automatic provider failover in LangChain using a unified LLM gateway, with runnable code and verification steps for resilient apps.
- Automating literature reviews with AutoGen agent teamsHow-toLearn how to build a multi-agent AutoGen pipeline that automates literature reviews: search arXiv, summarize papers, and synthesize findings with minimal code.
- Avoiding cold starts in serverless Vercel AI SDK appsHow-toPractical steps to eliminate vercel ai sdk serverless cold starts in production: keep functions warm, trim deps, and route via a gateway.
- Benchmark LlamaIndex retrievers with recall at kHow-toA practical llamaindex retriever benchmark recall at k tutorial: create ground-truth eval sets, run retrieval, and compute recall@k in Python.
- Benchmarking edge vs serverless latency in Vercel AI SDKAnalysisA hands-on analysis of Vercel AI SDK latency on Edge vs Serverless runtimes, with real code, tradeoffs, and a decisive recommendation for production LLM apps.
- Best agent framework for enterprise workflow automationListicleA practitioner's comparison of five agent frameworks for enterprise workflow automation, covering LangGraph, Temporal, Prefect, Semantic Kernel, and CrewAI.
- Best AI agent framework for chatbots in 2026ListicleA hands-on comparison of the best AI agent framework for chatbots in 2026, with code and tradeoffs for LangGraph, AutoGen, CrewAI, Semantic Kernel, and OpenAI Agents.
- Best AI agent framework for coding assistantsListicleA practitioner's comparison of the best AI agent frameworks for coding assistants, scored on repo context, tooling, and multi-agent control.
- Best AI agent framework for startups shipping an MVPListicleA pragmatic comparison of the best ai agent framework for startup mvp options—LangChain, LlamaIndex, AutoGen, CrewAI, and Pydantic AI—with code.
- Best AI framework for data analysis and SQL agentsListiclePractical comparison of the best AI frameworks for SQL agents: LangChain, LlamaIndex, DSPy, Vanna, Haystack, and custom Python with code and tradeoffs.
- Best AI framework for voice and real-time agentsListicleA practitioner's comparison of the best AI frameworks for voice and real-time agents, covering LiveKit, Pipecat, Vapi, Retell, and OpenAI Realtime.
- Best framework for agents that call external APIs and toolsListicleA practical comparison of the best framework for tool-calling agents, weighing LangChain, LlamaIndex, AutoGen, CrewAI, and Pydantic AI for API integration.
- Best framework for RAG: LangChain, LlamaIndex, or HaystackComparisonA practitioner's head-to-head comparison of LangChain, LlamaIndex, and Haystack for RAG across capabilities, cost, latency, and ergonomics.
- Build a chatbot with LlamaIndex CondensePlusContextTutorialStep-by-step llamaindex condensepluscontext chatbot tutorial: build a context-aware chat engine with LlamaIndex, handle conversation history, and run it.
- Build a citation-aware query engine in LlamaIndexTutorialHands-on llamaindex citation query engine tutorial: build a RAG pipeline with LlamaIndex that returns answers annotated with verifiable source citations.
- Build a customer support bot with LangChainTutorialHands-on tutorial to build customer support bot LangChain with RAG, Chroma, and conversation memory for engineers. Step-by-step code and expected output.
- Build a customer support chatbot with GPT-4o and n4n.aiTutorialStep-by-step tutorial to build a streaming customer support chatbot with GPT-4o using Next.js, Vercel AI SDK, and n4n.ai's OpenAI-compatible gateway.
- Build a data analysis agent with AutoGen code executionHow-toLearn how to build an autogen data analysis agent code execution workflow that generates and runs Python to explore CSV data with guarded local execution.
- Build a full-stack chatbot with Next.js and Vercel AI SDKTutorialFull-stack step-by-step guide to build chatbot next.js vercel ai sdk tutorial: scaffold app, stream responses, and wire a typed UI with useChat for production.
- Build a generative UI chat with n4n.ai and RSCTutorialHands-on generative ui chat n4n.ai rsc tutorial: build a streaming RSC chat with Vercel AI SDK and the n4n.ai OpenAI-compatible endpoint for LLM apps.
- Build a knowledge graph index in LlamaIndexTutorialHands-on llamaindex knowledge graph index tutorial: extract triplets from text with LlamaIndex, inspect the graph store, and run relationship queries.
- Build a LangChain agent with custom tool callingHow-toA step-by-step guide to langchain agent custom tool calling: define tools, wire a reasoning loop, verify with Python code and pytest for production use.
- Build a LangChain extraction chain with Pydantic v2TutorialHands-on langchain extraction chain pydantic v2 tutorial: build a structured output pipeline with Pydantic v2 and LangChain, with runnable code.
- Build a LangChain fallback chain for rate limitsTutorialStep-by-step langchain fallback chain rate limits tutorial: build a multi-model LLM fallback chain in Python that handles 429s and degradations.
- Build a LlamaIndex ReAct agent with n4n.aiTutorialStep-by-step llamaindex react agent tutorial: build a ReAct agent with custom tools using LlamaIndex and an OpenAI-compatible LLM gateway with runnable code.
- Build a model picker dropdown with Vercel AI SDKHow-toLearn how to build a vercel ai sdk model picker dropdown that switches LLMs at runtime with a clean React UI, streaming, and usage metering step by step.
- Build a multi-agent workflow with LangGraphHow-toA practical langgraph multi-agent workflow tutorial: build a supervisor-routed system of specialized agents with LangGraph, from setup to verified run.
- Build a Next.js chat app with useChat and n4n.aiTutorialStep-by-step useChat Next.js chat app tutorial using n4n.ai as OpenAI-compatible backend with Vercel AI SDK streaming and fallback.
- Build a Next.js chatbot with LangChain.jsHow-toStep-by-step guide to building a langchain.js nextjs chatbot with streaming responses, tool calling, and a production-ready API route in TypeScript.
- Build a planner, coder, and critic team with AutoGenTutorialBuild an autogen planner coder critic agent team with AutoGen group chat: hands-on tutorial splitting design, coding, and review into specialized agents.
- Build a RAG chatbot with LangChain, LanceDB, and n4n.aiHow-toA practical end-to-end tutorial for engineers: build a LangChain LanceDB n4n.ai RAG chatbot with vector search and OpenAI-compatible LLM calls.
- Build a RAG chatbot with Vercel AI SDK and n4n.aiTutorialHands-on rag chatbot vercel ai sdk n4n.ai tutorial: build a streaming RAG chatbot in Next.js using Vercel AI SDK and an OpenAI-compatible LLM gateway.
- Build a RAG pipeline with Haystack 2.0 and n4n.aiTutorialHands-on tutorial to build rag pipeline haystack 2.0 n4n.ai using Haystack 2.0 and an OpenAI-compatible endpoint, with runnable code and expected output.
- Build a RAG pipeline with LangChain and PineconeHow-toBuild a langchain pinecone rag pipeline from scratch: install deps, chunk docs, embed to Pinecone, query with LangChain retrieval chains, and verify.
- Build a RAG query engine in LlamaIndex with n4n.aiTutorialStep-by-step llamaindex rag query engine tutorial: install LlamaIndex, load docs, configure LLM via n4n.ai, build vector index, and run queries.
- Build a research agent in LlamaIndex with n4n.aiTutorialLearn to build a LlamaIndex research agent that queries external APIs and local data, using n4n.ai as an OpenAI-compatible LLM gateway.
- Build a streaming chat UI with Vercel AI SDK's useChatTutorialLearn to build a streaming chat UI with the Vercel AI SDK useChat hook in Next.js, from API route to live token streaming in a runnable tutorial.
- Build a streaming chatbot UI with LangChain and FastAPIHow-toStep-by-step guide to build a langchain fastapi streaming chatbot ui using async callbacks, Server-Sent Events, and a minimal JS frontend for real-time tokens.
- Build a voice assistant with Pipecat and GPT-4o RealtimeHow-toStep-by-step pipecat gpt-4o realtime voice assistant tutorial: build a low-latency voice agent with Pipecat and OpenAI Realtime, from install to verification.
- Build a voice bot with Vapi and Twilio integrationHow-toStep-by-step vapi twilio voice bot integration tutorial: connect Vapi assistants to Twilio telephony and a custom LLM endpoint in production.
- Build a weather tool with Vercel AI SDK function callingTutorialHands-on tutorial: build a vercel ai sdk weather tool example with function calling, Open-Meteo, and TypeScript. Runnable code and expected output included.
- Build an AutoGen research team with n4n.ai routingHow-toBuild a multi-agent research pipeline with AutoGen and route LLM calls through n4n.ai for fallback and 240+ models via one OpenAI-compatible endpoint.
- Build code-executing AutoGen agents with n4n.aiHow-toBuild code-executing AutoGen agents with n4n.ai as the LLM gateway: install, configure, run Python via UserProxyAgent, and verify execution.
- Build your first LCEL chain in LangChainHow-toHands-on tutorial to build first LCEL chain LangChain with runnable Python code: install, prompt, model, parser, stream, fallback, and verify.
- Build your first LlamaIndex app with n4n.aiTutorialHands-on llamaindex first app n4n.ai tutorial: configure LlamaIndex with n4n.ai's OpenAI-compatible gateway and build a local RAG query app in Python.
- Building a case law research assistant with LlamaIndexTutorialStep-by-step tutorial to build a case law research assistant with LlamaIndex: load opinions, index with metadata, query citations, and deploy a research agent.
- Building a citation-aware RAG pipeline in HaystackHow-toStep-by-step guide to building a citation-aware RAG pipeline in Haystack that returns sourced answers with document references and confidence.
- Building a clinical notes Q&A system with LlamaIndexTutorialStep-by-step tutorial for building a clinical notes Q&A system with LlamaIndex, from indexing HL7/CDA docs to querying with grounded answers.
- Building a compliance-checking agent for legal contractsTutorialHands-on tutorial to build a compliance checking agent for legal contracts using Python and an OpenAI-compatible LLM gateway, with runnable code.
- Building a CrewAI crew for customer support triageHow-toStep-by-step guide to building a CrewAI crew for customer support triage with runnable code, routing logic, and verification tips for engineers.
- Building a CrewAI crew for lead qualificationHow-toStep-by-step guide to building a CrewAI crew that qualifies sales leads with specialized agents, including runnable code and verification tips for engineers.
- Building a CrewAI tool for retrieval-augmented generationHow-toStep-by-step crewai rag tool tutorial: build a custom RAG tool for CrewAI agents using Chroma vector store and OpenAI-compatible APIs.
- Building a CrewAI tool that queries a SQL databaseHow-toThis crewai sql database tool tutorial shows how to build a safe SQL query tool for CrewAI agents, with runnable code and end-to-end verification.
- Building a crypto market analysis agent with LangChainTutorialHands-on tutorial to build a crypto market analysis agent LangChain that fetches live CoinGecko data and uses LLM tool-calling to produce insights.
- Building a customer support agent team with AutoGenTutorialHands-on tutorial for building an autogen customer support agent team with AutoGen group chat, including runnable Python code, config, and output examples.
- Building a customer support agent with Semantic KernelHow-toStep-by-step guide to build customer support agent semantic kernel apps with Python: plugins, stepwise planner, and resilient model routing. Includes runnable code.
- Building a customer support bot with LlamaIndexTutorialStep-by-step llamaindex customer support chatbot tutorial: index docs, wire a context chat engine with memory, and run a local support bot with Python.
- Building a customer support graph with LangGraphHow-toBuild a langgraph customer support agent with stateful routing, retrieval, and escalation. Step-by-step Python code for a production-ready support workflow.
- Building a database query plugin for Semantic KernelHow-toLearn how to build database query plugin Semantic Kernel native functions in Python, covering schema introspection, safe SQL execution, and end-to-end verification.
- Building a fallback chain across GPT-5, Claude, and GeminiTutorialBuild a hands-on llm fallback chain gpt-5 claude gemini in Python with provider SDKs, manual retries, timeouts, and error isolation across models.
- Building a financial news summarization agent with LangChainTutorialStep-by-step tutorial to build a financial news summarization agent LangChain that pulls headlines, scores relevance, and generates concise briefs.
- Building a find-similar-products feature with LlamaIndexTutorialHands-on tutorial: implement a find similar products LlamaIndex feature for e-commerce using vector embeddings, metadata filters, and persistence.
- Building a hierarchical agent team in LangGraphHow-toLearn how to build a LangGraph hierarchical agent team with a supervisor and worker agents. Step-by-step code for orchestrating multi-agent workflows.
- Building a hierarchical CrewAI crew with a manager agentHow-toHands-on tutorial for building a CrewAI hierarchical crew manager agent that delegates tasks, with runnable code and verification steps.
- Building a hybrid retriever in Haystack 2.0How-toHands-on hybrid retriever Haystack 2.0 tutorial: wire BM25 and embedding retrievers into one pipeline with rank fusion, then verify results locally.
- Building a legal document Q&A bot with LlamaIndexTutorialStep-by-step tutorial to build a legal document qa bot llamaindex using RAG, from PDF ingestion to cited answers with production-grade LLM fallback.
- Building a local RAG app with Mistral 7B and OllamaHow-toBuild a fully local RAG application using Mistral 7B and Ollama: install models, ingest documents, embed with nomic, retrieve, and generate offline.
- Building a medical literature Q&A agent in LangGraphTutorialHands-on LangGraph tutorial: build a medical literature QA agent for healthcare with document retrieval, LLM answers, and OpenAI-compatible model routing.
- Building a multi-document summary index in LlamaIndexTutorialHands-on llamaindex document summary index tutorial: build a multi-document summary index from scratch, query across docs, and inspect per-doc summaries.
- Building a multi-hop RAG pipeline in Haystack 2.0How-toStep-by-step guide to building a multi-hop RAG pipeline in Haystack 2.0 that retrieves, rewrites queries, and synthesizes answers across two passes.
- Building a multi-tool agent with Vercel AI SDK and n4n.aiTutorialHands-on tutorial to build a Vercel AI SDK multi-tool agent on n4n.ai's OpenAI-compatible gateway, with runnable TypeScript, tool calling, and step logs.
- Building a multi-tool Haystack agent pipelineHow-toA hands-on multi-tool Haystack 2.0 agent pipeline tutorial: define tools, wire an Agent into a Pipeline, run it, and verify tool orchestration.
- Building a multi-turn chatbot with Vercel AI SDK's useChatTutorialHands-on tutorial to build a vercel ai sdk multi-turn chatbot usechat in Next.js: scaffold route, wire client, stream, persist, and verify context.
- Building a multi-turn support bot in LangGraph with memoryTutorialA hands-on tutorial for building a multi-turn LangGraph customer support bot with durable conversation memory via checkpointers, including runnable Python code and expected output.
- Building a portfolio analysis agent with LangGraphTutorialHands-on tutorial: build a portfolio analysis agent with LangGraph step by step: fetch prices, compute risk metrics, and generate LLM-backed reports.
- Building a RAG chain entirely in LCELHow-toStep-by-step lcel rag chain tutorial: load docs, embed with FAISS, and compose retrieval and generation into one LangChain Expression Language chain. Runnable code included.
- Building a RAG evaluation pipeline in LlamaIndexTutorialA hands-on llamaindex rag evaluation pipeline tutorial: build retrieval and response eval with LlamaIndex, pytest, and OpenAI-compatible APIs.
- Building a RAG pipeline with Haystack and n4n.aiHow-toStep-by-step guide to building a Haystack RAG pipeline with n4n.ai as the OpenAI-compatible LLM gateway, covering install, indexing, retrieval, and verified queries.
- Building a ReAct-style agent in Semantic KernelHow-toHands-on react-style agent semantic kernel tutorial: implement a ReAct reasoning loop with FunctionCallingStepwisePlanner, custom plugins, and step-by-step verification.
- Building a regression test suite for Haystack pipelinesHow-toPractical steps to build a regression test suite for Haystack pipelines that catches retrieval and generation drift using pytest, snapshots, and evaluators in CI.
- Building a Semantic Kernel plugin from scratchHow-toStep-by-step guide to build semantic kernel plugin from scratch in C#: define native functions, semantic functions, wire up LLM, and verify with tests.
- Building a shopping assistant agent with LangGraphTutorialBuild a shopping assistant agent langgraph in this hands-on tutorial: product search, recommendation reasoning, and tool-calling with LangGraph.
- Building a Slack support bot with LangChain and RAGTutorialStep-by-step tutorial to build a Slack support bot with LangChain and RAG over your docs, including runnable code and expected output checkpoints.
- Building a stock research agent with LangChainTutorialHands-on tutorial: build a stock research agent LangChain that fetches live prices, financials, and news with tool calling and conversation memory.
- Building a support agent in CrewAI that escalates to a humanTutorialA hands-on practical guide to building a CrewAI support agent with human escalation logic, runnable Python code, and resilient LLM routing.
- Building a tool-calling agent in Haystack 2.0How-toA hands-on haystack 2.0 tool-calling agent tutorial: define tools, configure a chat generator, build a pipeline, and verify function calls end to end.
- Building a trading signal agent with CrewAITutorialBuild a multi-agent trading signal agent with CrewAI that pulls market data, analyzes trends, and emits risk-aware buy/sell signals. Step-by-step tutorial.
- Building a web-research AutoGen team with tool useHow-toA practical step-by-step tutorial for building an autogen web research agent team tool use with live web tools, verifiable output, and OpenAI-compatible models.
- Building a web search agent with LangChain and TavilyHow-toBuild a LangChain web search agent with Tavily and tool calling. Step-by-step setup, runnable code, and verification for production use.
- Building an agent with Semantic Kernel's Agent FrameworkHow-toA hands-on semantic kernel agent framework tutorial: build a task-completing agent with planners, plugins, and OpenAI-compatible endpoints.
- Building an audit trail for legal and healthcare LLM answersHow-toStep-by-step guide to building an audit trail for legal and healthcare LLM answers: capture prompts, responses, sources, and prove compliance.
- Building an AutoGen agent that asks before it actsHow-toLearn how to build an autogen agent ask before acting pattern with human-in-the-loop approval using AutoGen's callable tools and a console input gate.
- Building an enterprise chatbot with Semantic Kernel and .NETHow-toStep-by-step enterprise chatbot semantic kernel .net tutorial: scaffold .NET 8 API, connect OpenAI-compatible LLM gateway, add plugins, memory, guardrails.
- Building an LLM-as-judge evaluator in Haystack 2.0How-toStep-by-step guide to building an llm-as-judge evaluator haystack 2.0 pipeline for scoring RAG answers with runnable code and verification.
- Building long-term memory for Semantic Kernel agentsHow-toA hands-on long-term memory semantic kernel agents tutorial: wire vector stores, embeddings, and retrieval into Semantic Kernel agents for persistent context.
- Building semantic product search with LlamaIndexTutorialStep-by-step tutorial to build semantic product search with LlamaIndex using local embeddings, metadata filters, and persistence for e-commerce catalogs.
- Cache embeddings in LlamaIndex to reduce OpenAI API spendTutorialLearn how to implement a LlamaIndex embedding cache to avoid duplicate OpenAI embedding calls, cut token spend, and speed up RAG pipelines.
- Call 240+ models from LangChain through n4n.aiGuideStep-by-step LangChain guide to routing 240+ models via one OpenAI-compatible gateway, with fallback, metering, and cache-control patterns.
- Chatbot system prompts: a Vercel AI SDK guideGuideA practical guide to designing and implementing Vercel AI SDK chatbot system prompts in Next.js, with code, pitfalls, and tradeoffs for production.
- Choosing a framework for multi-step research agentsGuideA practical guide to selecting the best framework for research agents that perform multi-step tasks, covering state, tools, and tradeoffs.
- Choosing an AI framework for document processing at scaleGuideA practitioner's path to picking the best ai framework for document processing at scale: workload profiling, extraction vs RAG, idempotent batches, and inference fallback.
- Choosing the right chunk size for LangChain RAG appsGuidePractical guide to selecting chunk size for LangChain RAG apps: tradeoffs, code samples, and an ordered path to tune retrieval and context windows.
- Chunk overlap in LangChain: how much is too muchGuidePractical guide to langchain chunk overlap tuning: how to set chunk_size and overlap to balance RAG retrieval quality, token cost, and latency.
- Chunking strategies for LangChain RAG pipelinesGuideA practical guide to langchain rag chunking strategies: fixed-size, semantic, and recursive splitting with code, tradeoffs, and common pitfalls.
- Chunking strategies for LlamaIndex document ingestionGuideStep-by-step llamaindex chunking strategies tutorial: token, sentence, markdown, and semantic splitters with code, pitfalls, and a production checklist.
- Chunking strategies in LangChain: fixed size vs semanticComparisonA practitioner's head-to-head comparison of langchain chunking fixed size vs semantic across cost, latency, ergonomics, and limits, with code and a clear verdict.
- Claude 4.5 vs GPT-5 vs Gemini 2.5 on one LangChain promptComparisonHead-to-head LangChain test of Claude 4.5 vs GPT-5 vs Gemini 2.5 on one prompt: capabilities, cost, latency, ergonomics, limits, and which to choose.
- Code generation and execution agents in AutoGenHow-toStep-by-step guide to building autogen code generation execution agents with AutoGen: configure LLM, run local code executor, verify output, and scale to group chat.
- Comparing CrewAI process types by cost and latencyComparisonHead-to-head CrewAI process type cost latency comparison: sequential vs hierarchical crews across cost, speed, ergonomics, and real-world limits.
- Comparing Haystack document stores for production RAGComparisonA head-to-head comparison of Haystack document stores for production RAG: Elasticsearch, OpenSearch, Pinecone, Weaviate, Qdrant, Milvus, and Chroma.
- Comparing models with Haystack evaluation pipelinesComparisonPractical guide to using Haystack evaluation pipelines to compare models head-to-head on cost, latency, and quality with reproducible code.
- Comparing Pinecone and Chroma for LangChain RAG appsComparisonHead-to-head comparison of Pinecone vs Chroma for LangChain RAG apps across cost, latency, ergonomics, and limits, with a verdict per use case.
- Comparing vector stores for Semantic Kernel memoryComparisonA practitioner's head-to-head comparison of vector stores for Semantic Kernel memory across cost, latency, ergonomics, and limits, with a verdict.
- Composing prompt, model, and parser with LCELHow-toLearn how to lcel compose prompt model parser into a single runnable LangChain chain with code, deployment notes, and verification steps for engineers.
- Configure @ai-sdk/openai for n4n.ai in 5 minutesHow-toA practical walkthrough to configure ai-sdk openai provider for n4n.ai using the Vercel AI SDK, including env setup, code, and success checks.
- Configure ChatOpenAI for the n4n.ai unified API endpointHow-toPractical walkthrough to configure ChatOpenAI for the n4n.ai endpoint: set base URL, API key, model routing, and verify a live LangChain call.
- Configure LlamaIndex to use n4n.ai as the LLMHow-toStep-by-step llamaindex configure n4n.ai llm tutorial: point LlamaIndex at the OpenAI-compatible n4n.ai gateway and run a verified query in minutes.
- Configure OAI_CONFIG_LIST for AutoGen with n4n.aiHow-toStep-by-step guide to configuring AutoGen's OAI_CONFIG_LIST for n4n.ai, including runnable JSON and Python examples plus verification steps for engineers.
- Configuring CrewAI's LLM class for n4n.ai endpointsHow-toPractical walkthrough for crewai llm class n4n.ai endpoint config: install, authenticate, instantiate LLM, build a crew, and verify model routing works.
- Configuring Semantic Kernel's OpenAI connector for n4n.aiHow-toStep-by-step guide to point Microsoft Semantic Kernel's OpenAI connector at n4n.ai's OpenAI-compatible gateway, with runnable Python code and verification tips.
- Connect LangChain.js to n4n.ai with the OpenAI packageHow-toStep-by-step guide to connecting LangChain.js to n4n.ai using the OpenAI package, with runnable Node.js code for chat, streaming, and model routing.
- Connect LangChain to n4n.ai using the OpenAI SDK formatHow-toStep-by-step guide to connect LangChain to n4n.ai using the OpenAI SDK format. Configure ChatOpenAI, stream tokens, route models, and verify usage.
- Connect LlamaIndex agents to external APIsHow-toStep-by-step llamaindex agents external api tutorial: build LlamaIndex agents that call real HTTP APIs as tools, with runnable Python code and verification.
- Connect Vercel AI SDK to n4n.ai's OpenAI-compatible APIHow-toStep-by-step guide to connect Vercel AI SDK to n4n.ai API via the OpenAI-compatible endpoint, covering auth, model routing, streaming, and verification.
- Connecting Haystack to n4n.ai with a custom generatorHow-toLearn how to build a Haystack custom generator for n4n.ai to route pipelines through an OpenAI-compatible gateway with fallback and per-token metering.
- Connecting Haystack to Pinecone for vector retrievalHow-toStep-by-step haystack pinecone document store tutorial: install deps, configure Pinecone, embed docs, build a retriever, and verify vector search in Haystack 2.x.
- Connecting Semantic Kernel to Qdrant for vector memoryHow-toStep-by-step semantic kernel qdrant vector memory tutorial: wire SK memory to Qdrant, configure embeddings, store and query vectors with runnable code.
- Continuous evaluation for Haystack pipelines in CIGuideA practical guide to continuous evaluation of Haystack pipelines in CI: metrics, golden datasets, wiring, thresholds, and pitfalls for LLM quality gates.
- Contract review with LangChain: extracting clausesTutorialA hands-on tutorial for contract review LangChain clause extraction: build a pipeline to parse legal PDFs, classify clauses, and export structured JSON.
- Coordinating AutoGen agent teams across GPT-5.1 and Gemini 3How-toHands-on tutorial for engineers coordinating an AutoGen agent team across GPT-5.1 and Gemini 3, with runnable Python code and success checks.
- Cost-aware model routing in Vercel AI SDK appsGuideStep-by-step vercel ai sdk cost-aware model routing: route by task complexity, unify metering via gateway, and avoid common cost traps in production.
- Cost optimization: cheap models per agent with n4n.aiGuidePractical guide to autogen cost optimization cheap models n4n.ai: assign per-agent model tiers, configure gateway, measure token usage in multi-agent flows
- CrewAI agent roles: assigning the right LLM per roleTutorialLearn how to configure CrewAI llm per agent role assignment with runnable code, routing different models to planner, researcher, and writer agents in production.
- CrewAI agent roles: specialist vs generalist designComparisonCompare CrewAI specialist vs generalist agent roles across cost, latency, ergonomics, with a table and verdict for which to use when.
- CrewAI agent roles: tools, memory, and delegation settingsGuideHands-on guide to CrewAI agent roles: configure tools, memory, and delegation settings with Python examples, plus pitfalls and a sane default setup.
- CrewAI agent roles tutorial: goal, backstory, and toolsTutorialHands-on CrewAI tutorial: define agent roles, goals, backstories, and tools step by step to build a working multi-agent crew with runnable Python code.
- CrewAI agent roles tutorial: manager and worker patternsTutorialBuild a working CrewAI hierarchical crew with manager and worker agents. Step-by-step code, prerequisites, and expected output for the manager worker pattern.
- CrewAI and n4n.ai: your first agent in 10 minutesHow-toHands-on crewai n4n.ai first agent tutorial: install CrewAI, point it at the n4n.ai OpenAI-compatible gateway, and run a multi-agent crew in 10 minutes.
- CrewAI BaseTool class explained with a working exampleDefinitionLearn the CrewAI BaseTool class with a working example. Understand its structure, why it matters for agents, and avoid common custom tool mistakes.
- CrewAI custom tools tutorial: building your first toolTutorialHands-on CrewAI tutorial: step by step build, test, and integrate your first custom tool with a live agent, including runnable code and expected output.
- CrewAI custom tools tutorial: web search with SerperTutorialHands-on tutorial: build a crewai serper web search tool from scratch with the Serper API, wrap it for CrewAI agents, and run a live search crew.
- CrewAI example: a crew that drafts and reviews codeHow-toBuild a CrewAI code review crew example that drafts and critiques Python functions. Step-by-step setup, runnable code, and verification tips.
- CrewAI Process.sequential vs Process.hierarchical: a guideComparisonEngineering comparison of CrewAI Process.sequential vs Process.hierarchical across cost, latency, ergonomics, and limits, with a use-case verdict.
- CrewAI quickstart: agents, tasks, and n4n.ai routingTutorialHands-on CrewAI tutorial: build a multi-agent crew and route LLM calls through one OpenAI-compatible gateway with fallback and per-token metering.
- CrewAI real-world example: automated blog writing crewHow-toBuild a working CrewAI blog writing crew example with researcher, writer, and editor agents using OpenAI-compatible LLMs and verify the output locally.
- CrewAI sequential process tutorial: step-by-step tasksTutorialHands-on CrewAI sequential process tutorial: build a linear multi-agent pipeline with tasks that run in order, including runnable code and output.
- CrewAI sequential vs hierarchical process explainedComparisonA practitioner's head-to-head comparison of CrewAI sequential vs hierarchical process across cost, latency, ergonomics, and limits, with a verdict.
- CrewAI setup tutorial: connecting n4n.ai as your LLMHow-toStep-by-step guide to point CrewAI at an OpenAI-compatible inference gateway, configure the LLM client, run a multi-agent crew, and verify token usage.
- CrewAI task design tutorial: chaining task outputsTutorialHands-on CrewAI tutorial: chain task outputs to build multi-step agent workflows. Learn to use Task context, structured outputs, and avoid common pitfalls.
- CrewAI vs AutoGen vs LangGraph: frameworks comparedComparisonHead-to-head crewai vs autogen vs langgraph comparison on capabilities, cost, latency, ergonomics, ecosystem, and limits, with a use-case verdict.
- CrewAI vs AutoGen vs LangGraph: latency and costAnalysisA practitioner's analysis of crewai vs autogen vs langgraph latency cost, covering orchestration overhead, token growth, and decisive tradeoffs for production.
- CrewAI vs AutoGen vs LangGraph: which scales to productionAnalysisA practitioner's analysis of crewai vs autogen vs langgraph production scaling, weighing state management, fault tolerance, and operability to pick a framework.
- Cut LangChain costs with semantic caching via GPTCacheHow-toStep-by-step guide to langchain semantic caching gptcache cost reduction: deploy a semantic cache layer to slash LLM token spend and p95 latency.
- Define tools with Zod schemas in the Vercel AI SDKHow-toLearn how to define tools with Zod schemas in the Vercel AI SDK for type-safe function calling. Step-by-step guide with runnable TypeScript code.
- Deploy a Vercel AI SDK app to Cloudflare WorkersHow-toA practical walkthrough of vercel ai sdk cloudflare workers deployment: scaffold an edge AI app, configure the provider, ship to Workers, and verify.
- Deploy DeepSeek-V3 with vLLM behind a LangChain agentHow-toStep-by-step tutorial: deploy DeepSeek-V3 with vLLM and connect it to a LangChain agent on self-hosted local hardware via OpenAI-compatible API.
- Designing CrewAI tasks: context, output, and expected formatGuidePractical guide to CrewAI task design: structure context, define expected output formats, and avoid common pitfalls when building multi-agent crews.
- E-commerce chatbot: from search to checkout with LangChainTutorialHands-on ecommerce chatbot search to checkout langchain tutorial: build semantic search, tool-calling agent, cart and checkout with runnable Python code.
- Evaluate LlamaIndex retrieval with hit rate and MRRTutorialHands-on llamaindex retrieval evaluation hit rate mrr tutorial: build a vector index, define a dataset, and measure retriever quality with code.
- Evaluating RAG pipelines in Haystack with n4n.ai modelsGuideStep-by-step guide to evaluate RAG pipeline Haystack n4n.ai models with Haystack 2.x, covering setup, evaluation harness, and model swapping pitfalls.
- Force JSON mode in LangChain using n4n.ai modelsHow-toLearn to force JSON mode in LangChain via the n4n.ai OpenAI-compatible gateway, with runnable code for structured output and validation across 240+ models.
- Function calling with GPT-4o via Vercel AI SDK and n4n.aiTutorialStep-by-step tutorial for gpt-4o function calling with Vercel AI SDK via n4n.ai gateway, including runnable code and expected output.
- Generative UI with Vercel AI SDK and React Server ComponentsTutorialPractical vercel ai sdk generative ui rsc tutorial: build streaming React Server Components that render UI from LLM tool calls with runnable code.
- Getting started with AutoGen and n4n.aiTutorialHands-on autogen n4n.ai getting started tutorial: wire Microsoft AutoGen to an OpenAI-compatible gateway, run multi-agent tasks, and track token usage.
- Getting started with CrewAI and n4n.aiTutorialA hands-on tutorial to crewai n4n.ai getting started: install CrewAI, point it at the OpenAI-compatible gateway, and run a multi-agent workflow.
- Getting started with Haystack and n4n.aiTutorialLearn getting started with Haystack and n4n.ai: install the framework, configure the OpenAI-compatible endpoint, and build a chat pipeline.
- Getting started with LangChain.js and TypeScriptGuideA practical, opinionated guide to langchain.js typescript getting started: project setup, first chains, streaming, pitfalls, and provider fallback.
- Getting started with LlamaIndex and n4n.aiTutorialA hands-on llamaindex n4n.ai setup tutorial: configure LlamaIndex to use the n4n.ai OpenAI-compatible gateway for LLM and embeddings in minutes.
- Getting started with Semantic Kernel and n4n.aiGuideStep-by-step setup for getting started with Semantic Kernel and n4n.ai, including Python code, configuration pitfalls, token metering, and routing across 240+ models.
- Getting started with Vercel AI SDK and n4n.aiTutorialPractical step-by-step tutorial to build a streaming chat app with Vercel AI SDK and n4n.ai's OpenAI-compatible gateway, from scaffold to working UI.
- Give a LlamaIndex agent custom Python toolsHow-toA practical llamaindex custom tools tutorial: build Python functions, wrap them as tools, and wire them into a LlamaIndex agent that calls them reliably.
- Haystack agent pipeline tutorial: n4n.ai function callingTutorialBuild a Haystack 2.0 agent pipeline with function calling via the n4n.ai OpenAI-compatible gateway. Step-by-step code, tools, and expected output.
- Haystack setup tutorial: connecting n4n.ai generatorsHow-toStep-by-step guide to configure Haystack's OpenAIChatGenerator with n4n.ai's OpenAI-compatible endpoint, including code, verification, and production tips.
- HIPAA-aware document Q&A: a LangChain tutorialTutorialHands-on tutorial for building a HIPAA-aware document Q&A system with LangChain: vector search, PHI redaction, and compliant LLM routing for healthcare teams.
- How to avoid vendor lock-in with LangChain or LlamaIndexGuidePractical steps to avoid llm vendor lock-in langchain llamaindex by routing both frameworks through one OpenAI-compatible gateway with code.
- How to connect Haystack to n4n.ai's OpenAI-compatible APIHow-toA practical guide to connect Haystack to n4n.ai's OpenAI-compatible API, configure generators, and ship a RAG pipeline with built-in fallback.
- How to swap GPT-5 for Claude Opus 4.5 in LangChainHow-toLearn how to swap GPT-5 for Claude Opus 4.5 in LangChain using native Anthropic SDK or an OpenAI-compatible gateway, with code and verification steps.
- Ingest PDFs into LlamaIndex with n4n.ai embeddingsHow-toA step-by-step llamaindex pdf ingestion n4n.ai tutorial: wire LlamaIndex to an OpenAI-compatible embeddings endpoint and index PDFs into a vector store.
- Install AutoGen and connect it to n4n.ai's APIHow-toStep-by-step guide to install AutoGen and connect n4n.ai API: set up Python, configure OpenAI-compatible endpoint, run multi-agent chat, verify.
- Install CrewAI and run your first crew with n4n.aiHow-toPractical walkthrough to install CrewAI and run your first crew using the n4n.ai OpenAI-compatible endpoint, with runnable code and verification steps.
- Install Haystack 2.0 and run your first pipelineHow-toA practical walkthrough to install Haystack 2.0 and build a runnable RAG pipeline, from environment setup to verifying output with real code.
- Integrating CrewAI with n4n.ai's function calling modelsHow-toStep-by-step guide to wiring CrewAI agents to n4n.ai's OpenAI-compatible function calling models, with runnable code for custom tools and verification.
- LangChain document loaders: PDF, HTML, and MarkdownGuidePractical guide to langchain document loaders pdf html markdown: install, load each format with code, dodge pitfalls, and chunk for retrieval.
- LangChain Expression Language: a beginner's guideGuideA practical langchain expression language beginner guide: build composable LLM chains with LCEL, avoid common pitfalls, and ship faster.
- LangChain function calling for data extractionTutorialHands-on langchain function calling structured extraction tutorial: use Pydantic and with_structured_output to parse text into typed objects.
- LangChain.js quickstart: your first chat chain in NodeTutorialA hands-on langchain.js quickstart node chat chain tutorial: build a runnable Node.js chat chain with LangChain.js, from setup to streaming responses.
- LangChain.js tool calling with GPT-4o via n4n.aiHow-toHands-on tutorial for LangChain.js tool calling with GPT-4o via n4n.ai: wire OpenAI-compatible models to LangChain tools in Node with working TypeScript code.
- LangChain memory types explained: buffer vs summaryDefinitionA practical definition of LangChain memory types buffer vs summary: how buffer and summary memory work, code samples, and when to use each for engineers building LLM chat systems.
- LangChain plus n4n.ai: your first chat completion callTutorialThis langchain n4n.ai chat completion tutorial walks through a runnable LangChain setup against an OpenAI-compatible gateway with streaming and usage metering.
- LangChain quickstart: n4n.ai as your model providerGuideStep-by-step LangChain quickstart: use n4n.ai as your model provider via one OpenAI-compatible endpoint, route 240+ models, and manage fallback and caching.
- LangChain RAG tutorial: Chroma plus n4n.ai modelsTutorialBuild a retrieval-augmented generation pipeline with LangChain and Chroma using n4n.ai models via an OpenAI-compatible endpoint. Hands-on tutorial with runnable code.
- LangChain ReAct agents: a hands-on tutorialTutorialHands-on langchain react agent tutorial: build a ReAct agent with tools, step-by-step code, and expected outputs using LangChain's current API.
- LangChain RecursiveCharacterTextSplitter explainedDefinitionA precise technical breakdown of LangChain's RecursiveCharacterTextSplitter: how its hierarchical separator recursion works, key params, and common pitfalls.
- LangChain RunnableWithFallbacks explainedTutorialHands-on langchain runnablewithfallbacks tutorial: build resilient multi-model LLM chains with graceful degradation using LangChain's RunnableWithFallbacks and runnable code.
- LangChain RunnableWithMessageHistory tutorialTutorialHands-on langchain runnablewithmessagehistory tutorial: build stateful LCEL conversational chains with custom memory backends and OpenAI-compatible APIs.
- LangChain streaming with Claude 3.5 Sonnet via n4n.aiHow-toPractical steps to implement langchain streaming claude 3.5 sonnet n4n.ai: install deps, point ChatOpenAI at gateway, write callbacks, verify tokens.
- LangChain streaming with n4n.ai and Server-Sent EventsHow-toStep-by-step guide to langchain streaming n4n.ai sse with FastAPI and EventSource, covering config, SSE wiring, error handling, and verification.
- LangChain vs LlamaIndex: cost per query on GPT-5 and ClaudeAnalysisEngineering analysis of langchain vs llamaindex rag cost per query on GPT-5 and Claude: where token waste hides in retrieval and how to cut it.
- LangChain vs LlamaIndex for RAG: how to choose in 2026ComparisonA pragmatic 2026 engineering comparison of LangChain and LlamaIndex for RAG across capabilities, cost, latency, ergonomics, and ecosystem to help you choose.
- LangChain with_structured_output explained step by stepTutorialHands-on langchain with_structured_output tutorial: define Pydantic schemas, bind to chat models, parse LLM responses, and avoid common pitfalls.
- LangGraph state machines explained with a code exampleDefinitionA precise LangGraph state machine explained: how graph-based agent orchestration works, with a runnable Python example and common pitfalls to avoid.
- LangGraph supervisor pattern: coordinating multiple agentsGuidePractical guide to the LangGraph supervisor pattern for multi-agent systems: architecture, code, pitfalls, and tradeoffs for production orchestration.
- LCEL pipe syntax explained with real examplesDefinitionLCEL pipe syntax explained: how LangChain's | operator composes runnables into chains, with working Python examples, debugging tips, and fixes for common mistakes.
- LCEL with n4n.ai: routing between GPT-4o and Llama 3.3How-toStep-by-step guide to implementing lcel n4n.ai model routing gpt-4o llama with LangChain Expression Language for cost-efficient and resilient LLM inference.
- LlamaIndex chat engines explained: context vs condenseComparisonCompare LlamaIndex ContextChatEngine and CondenseChatEngine in this llamaindex chat engine tutorial: cost, latency, ergonomics, and verdicts.
- LlamaIndex data connectors: a complete overviewGuideA practical llamaindex data connectors overview tutorial: build ingestion pipelines from local files, APIs, and databases with real code and pitfalls.
- LlamaIndex FunctionAgent tool calling explainedGuideA practical llamaindex functionagent tool calling tutorial: build agents with function tools, handle schemas, streaming, and avoid common pitfalls.
- LlamaIndex ingestion pipeline explained step by stepGuideA practical llamaindex ingestion pipeline tutorial: build a robust data connector and transformation flow with code, pitfalls, and tradeoffs for engineers.
- LlamaIndex PropertyGraphIndex explainedGuidePractical llamaindex propertygraphindex tutorial: build, persist, and query knowledge graphs from docs with hybrid retrieval, plus pitfalls and tradeoffs.
- LlamaIndex quickstart: n4n.ai API key setupTutorialStep-by-step llamaindex n4n.ai api key setup tutorial: configure LlamaIndex with the n4n.ai OpenAI-compatible endpoint and run a query in minutes.
- LlamaIndex RelevancyEvaluator explainedGuideA hands-on llamaindex relevancyevaluator tutorial covering setup, minimal code, output schema, judge model tradeoffs, and common pitfalls when evaluating RAG retrieval quality.
- LlamaIndex SimpleDirectoryReader for local file ingestionTutorialHands-on llamaindex simpledirectoryreader tutorial: load local files into LlamaIndex, filter by type, add metadata, and split into nodes with runnable code.
- LlamaIndex tutorial: a support bot for your help docsTutorialBuild a RAG-powered llamaindex support bot help docs pipeline with Python, from indexing to query, using OpenAI-compatible LLMs and embeddings.
- LlamaIndex VectorStoreIndex query engine explainedGuideA practical llamaindex vectorstoreindex query engine tutorial: build the index, configure models, tune retrieval, run RAG queries, and avoid common pitfalls.
- Migrating a raw OpenAI SDK app to support multiple providersHow-toLearn how to migrate openai sdk app to multi-provider support with concrete steps, runnable code, and verification tips for backend engineers.
- Migrating the raw OpenAI SDK to LangChain step by stepHow-toStep-by-step guide to migrate OpenAI SDK code to LangChain without rewrites. Swap clients, adopt chains, and verify behavior with runnable examples.
- Mix GPT-4o and Claude 3.5 Sonnet per agent via n4n.aiHow-toLearn to autogen mix gpt-4o claude 3.5 sonnet agents n4n.ai: configure per-agent models in AutoGen via a single OpenAI-compatible gateway endpoint.
- Multi-agent research assistant using LangGraph and n4n.aiHow-toBuild a langgraph n4n.ai multi-agent research assistant with LangGraph: step-by-step setup, runnable code, and verification for engineers shipping LLM systems.
- Multi-model fallback in LangChain with n4n.aiGuideA practical langchain multi-model fallback tutorial: wire LangChain to an OpenAI-compatible gateway, configure ordered fallbacks, and handle real failure modes.
- Multi-model switching in Vercel AI SDK using n4n.ai routingTutorialLearn how to implement vercel ai sdk multi-model switching n4n.ai routing with fallback, per-token metering, and client routing directives in a runnable tutorial.
- Multi-provider apps: GPT-5, Claude, Gemini, and Llama 4ComparisonA head-to-head comparison of GPT-5, Claude, Gemini, and Llama 4 for multi-provider LLM framework integration across cost, latency, and ergonomics.
- Multimodal RAG in LlamaIndex with GPT-4o and imagesTutorialBuild a working multimodal RAG pipeline in LlamaIndex with GPT-4o and images. Step-by-step code for indexing and querying visual documents.
- Ollama vs vLLM for serving Llama 4 in production appsComparisonPractical comparison of Ollama vs vLLM for serving Llama 4 in production: capabilities, cost, latency, ergonomics, limits, and which to choose.
- One API, every model: routing GPT-5 and Gemini in LangGraphGuidePractical guide to route GPT-5 and Gemini in LangGraph: build a multi-provider agent with conditional routing, unified gateways, and avoid common pitfalls.
- One endpoint for GPT-5, Claude, Gemini, and LlamaGuidePractical guide to routing GPT-5, Claude, Gemini, and Llama through one OpenAI-compatible endpoint: client setup, model IDs, fallback, and cost control.
- One LangChain client for OpenAI, Anthropic, and n4n.aiGuideA practical langchain multi-provider setup tutorial for routing OpenAI, Anthropic, and n4n.ai through one client, with code and production pitfalls.
- Point LangChain at n4n.ai instead of the OpenAI APIHow-toLearn how to point LangChain at n4n.ai instead of the OpenAI API with a drop-in base URL change, keeping your code intact while accessing 240+ models.
- Prompt caching in LangChain: cut Claude costs by 90%TutorialHands-on LangChain tutorial: use Anthropic prompt caching with Claude to slash input token costs by 90%. Step-by-step code, usage metrics, and gotchas.
- RAG pipeline: LangChain vs LlamaIndex step by stepTutorialStep-by-step tutorial to build RAG pipeline LangChain vs LlamaIndex with runnable code, comparing retrieval and generation tradeoffs for engineers.
- Real-time voice apps with LiveKit Agents and WhisperHow-toStep-by-step guide to building a production-ready real-time voice app with LiveKit Agents and Whisper STT, including LLM wiring and TTS.
- Redacting PHI before it reaches your LLM in LangChainHow-toStep-by-step guide to implement a redact phi langchain llm pattern that removes protected health information from healthcare docs before LLM calls.
- Route LangChain requests by cost using n4n.aiHow-toLearn to build a cost-aware LangChain router that selects models per request via a unified OpenAI-compatible gateway in this hands-on tutorial.
- Run Llama 4 Maverick locally with Ollama and LangChainHow-toPractical steps to run Llama 4 Maverick with Ollama and LangChain locally, from Ollama install to verified streaming chat in Python.
- Running Vercel AI SDK on the Edge runtimeHow-toA practical vercel ai sdk edge runtime tutorial: deploy streaming LLM routes on Vercel Edge with fetch-based providers, real code, and verification steps.
- Semantic Kernel agent tutorial with n4n.ai function callingTutorialHands-on tutorial: build a Semantic Kernel ChatCompletionAgent that calls Python functions via the n4n.ai OpenAI-compatible gateway. Step-by-step code.
- Semantic Kernel enterprise tutorial: n4n.ai cost trackingGuidePractical guide to implementing semantic kernel enterprise cost tracking with per-token metering on an OpenAI-compatible gateway for .NET enterprise apps.
- Semantic Kernel memory tutorial: embeddings with n4n.aiTutorialHands-on Python tutorial for Semantic Kernel memory: configure embeddings via n4n.ai's OpenAI-compatible endpoint, build an in-memory vector store, query.
- Semantic Kernel plugins tutorial: n4n.ai function callingTutorialBuild semantic kernel plugins function calling n4n.ai: a hands-on Python tutorial to wire native functions to an OpenAI-compatible gateway with runnable code.
- Semantic Kernel plugins tutorial: writing native functionsTutorialHands-on semantic kernel plugins native functions tutorial: build Python native function plugins, register them, invoke from kernel or LLM, with runnable code.
- Semantic Kernel setup tutorial: connecting to n4n.aiTutorialHands-on Python guide to a semantic kernel n4n.ai setup tutorial: connect Semantic Kernel to the OpenAI-compatible gateway with runnable code.
- Set up LangChain with n4n.ai in under 10 minutesHow-toLearn how to set up LangChain with n4n.ai using its OpenAI-compatible endpoint, with runnable code, config, and verification steps.
- Speech-to-speech apps with the OpenAI Realtime APIGuideA practical openai realtime api speech-to-speech tutorial: build low-latency voice apps with WebSockets, handle audio, and avoid common pitfalls.
- Stream LangChain responses token by tokenHow-toA practical langchain stream tokens tutorial: wire up token-by-token streaming from LLMs to your app with callbacks, async generators, and verification steps.
- Streaming responses from Vercel Edge Functions with AI SDKHow-toLearn how to implement vercel edge functions ai sdk streaming end to end, from project setup to streaming completions on the edge runtime.
- Structured output in LangChain with Pydantic and n4n.aiGuideStep-by-step langchain structured output pydantic tutorial: bind typed schemas to LLM calls, validate responses, and handle provider failures in production.
- Swapping OpenAI for n4n.ai in a Haystack RAG pipelineHow-toA practical how-to for engineers to swap OpenAI for n4n.ai in a Haystack RAG pipeline using OpenAI-compatible endpoints, with runnable code and verification steps.
- Switch between GPT-4o and Claude 3.5 Sonnet in Vercel AI SDKHow-toPractical walkthrough to vercel ai sdk switch gpt-4o claude 3.5 sonnet dynamically, with install steps, Next.js route code, and verification.
- Switch LlamaIndex from OpenAI to n4n.aiHow-toHands-on steps to migrate LlamaIndex from OpenAI to any OpenAI-compatible API, with code for LLM, embeddings, and success checks.
- Switching CrewAI from OpenAI to n4n.ai in one lineHow-toStep-by-step guide to the crewai switch openai to n4n.ai via one env var change, including runnable code and verification steps.
- Switching Semantic Kernel from Azure OpenAI to n4n.aiHow-toA practical migration tutorial for engineers: repoint Semantic Kernel's OpenAI connector to n4n.ai, verify model behavior, and drop Azure-specific dependencies.
- useChat hook tutorial: stream GPT-4o responses via n4n.aiTutorialHands-on tutorial: build a streaming chat UI with the useChat hook and GPT-4o via n4n.ai's OpenAI-compatible API using the Vercel AI SDK.
- UserProxyAgent human_input_mode explained with examplesDefinitionExplains autogen userproxyagent human_input_mode: the ALWAYS, TERMINATE, NEVER settings, how the conversation loop uses them, with runnable examples.
- Using pgvector with LangChain for production RAGGuidePractical guide to building langchain pgvector production rag systems: schema, ingestion, tuning, and pitfalls for serving real traffic on Postgres.
- Vercel AI SDK quickstart: call GPT-4o through n4n.aiTutorialHands-on Vercel AI SDK GPT-4o quickstart using n4n.ai's OpenAI-compatible endpoint, with install steps, runnable TS code, and output.
- Vercel AI SDK's streamUI: rendering components from GPT-4oTutorialHands-on tutorial: use Vercel AI SDK streamUI with GPT-4o to render React components from model tool calls. Step-by-step setup, code, and output.
- Vercel AI SDK tool calling: a complete walkthroughTutorialA practical vercel ai sdk tool calling tutorial: step by step, build a typed tool-calling agent with streaming, error handling, and provider fallback in Node.
- Vercel AI SDK useChat with n4n.ai: full walkthroughTutorialHands-on vercel ai sdk usechat n4n.ai walkthrough: build a streaming Next.js chat UI on an OpenAI-compatible gateway with fallback and per-token metering.
- When to migrate off the raw OpenAI SDK (and when not to)GuideA practical decision guide for engineers weighing when to migrate off the raw OpenAI SDK to a framework or abstraction, with code and pitfalls.
- Why hardcoding one LLM provider breaks your framework appAnalysisHardcoding a single LLM provider creates vendor lock-in and reliability gaps. Learn why abstraction and multi-provider routing beat hardcoded API calls.
- Your first AutoGen agent using GPT-4o via n4n.aiTutorialBuild an AutoGen agent running GPT-4o through the n4n.ai OpenAI-compatible gateway. Step-by-step setup, runnable code, and expected output.
- Your first generateText call with Vercel AI SDK on n4n.aiTutorialStep-by-step vercel ai sdk generatetext n4n.ai tutorial: set up Vercel AI SDK, point it at an OpenAI-compatible gateway, and run your first call.