Data pipeline: guides & tutorials

Large language models (the latest GPT and Claude Sonnet 4.6 models) have two practical limits you hit in production:

1. Stale knowledge: Weights reflect the world only up to their training cutoff.
2. No access to your data: They do not know your internal wikis, repos, or live systems unless you give them a path in.

Retrieval-Augmented Generation (RAG) is the usual fix. Instead of retraining or fine-tuning the model for every document change, RAG takes the user question, looks up relevant passages in an external store of facts (typically a vector database), and asks the LLM to answer using that retrieved text as ground context.

This guide focuses on the part that breaks most often: ingestion—getting web pages into a shape embeddings can use.

n8n is a workflow automation tool that pairs well with Apify because it handles long-running jobs, large JSON payloads, and branching logic without the tight synchronous limits of simpler connectors. This guide covers setup, the official Apify node, webhook patterns for slow Actors, example workflows, and operational tips.

Google Maps is the default directory for local businesses: names, categories, ratings, websites, phones, and coordinates. Google also rate-limits and truncates what you see in the UI—so reliable extraction usually means a hosted browser stack, rotating proxies, and sometimes geographic grid search instead of one giant query.

This tutorial walks through no-code scraping with the Apify Google Maps Scraper and explains the 120-result ceiling, grid partitioning, and optional email enrichment.

Start on Apify (free monthly credits) →