Tutorial: guides & tutorials

Chatbase ships two REST API versions. API v1 is the original integration path; API v2 is a modern redesign with structured error codes, cursor-based pagination, Server-Sent Events (SSE) streaming, and a cleaner response contract. This guide covers v2 exclusively — it is the forward path for all new integrations in 2026. By the end, you will know how to authenticate, send streaming chat messages, paginate through conversation history, handle rate limits, and feed fresh website content scraped with Apify into your Chatbase knowledge base.

Prerequisites: API v2 requires a Standard plan or above. Free and Hobby accounts cannot use the API. Check the pricing guide to evaluate upgrading.

Wispr Flow won't write code for you. Say "write a function that fetches JSON from a URL" and it types those words literally — no code generation, no autocomplete. What it does is eliminate the friction of typing everything that surrounds your code: the comments, the commit messages, the PR descriptions, the Slack threads, the documentation, the emails.

For developers, that's a substantial portion of the workday. And dictating it is meaningfully faster than typing it.

This guide covers the practical ways developers use Wispr Flow, how to configure it for a technical workflow, and where it genuinely helps versus where you shouldn't expect it to.

Many RAG (Retrieval-Augmented Generation) projects fail in production not because the technology doesn't work, but because teams skip the hard parts: chunking strategy, embedding model selection, retrieval quality measurement, and stale data management. Validate each step on your own corpus — field names, SDK versions, and Actor outputs change over time.

The pipeline: crawl websites → chunk intelligently → embed → store in vector DB → retrieve with reranking → generate answers with citations.

TL;DR:

Prerequisites:

• Python 3.10+ or Node.js 18+
• Apify account (sign up)
• Vector database (Qdrant Cloud free tier or self-hosted)
• LLM API key (Claude, GPT-4, or self-hosted Ollama)

Andrej Karpathy coined "vibe coding" in early 2025 — the practice of describing what you want to an AI and letting it generate the code, barely reading the output, and just running it until it works. By April 2026, developers are using Claude Code to go from idea to deployed, revenue-ready SaaS MVP in days, not months.

This guide provides the practical framework: what actually works, what breaks, and the phase-by-phase approach that turns "vibes" into a product people pay for.

TL;DR:

Prerequisites:

• Claude Code installed with Claude Pro ($20/mo) or Max ($100/mo)
• GitHub account
• Vercel account (free tier)
• Supabase account (free tier)
• Comfortable reading and editing code (TypeScript/JavaScript), working with CLI tools, and following API documentation. You don't need to write complex algorithms from scratch — Claude Code handles most generation — but you should be able to review and adjust the code it produces.

The Model Context Protocol (MCP) is the USB-C for AI: a single open standard that connects AI applications to tools, data sources, and workflows. Originated by Anthropic in late 2024 and now an open, community-maintained standard, MCP is supported across a wide range of clients (Claude Desktop and Claude Code, ChatGPT, VS Code, Cursor, and others). The specification covers two transports (local stdio and remote Streamable HTTP, which supersedes the older HTTP+SSE transport), server-side tools, resources, and prompts, and an OAuth 2.1-based authorization flow for remote servers. The public server ecosystem is large and growing fast, spanning official Anthropic servers, vendor servers, and community projects.

If you do not already use Claude, you can try Claude free for a week and follow along with every example in this handbook. The guide covers MCP server development end-to-end, from your first server to production deployment with authentication.

TL;DR:

Prerequisites:

• Node.js 18+ or Python 3.10+
• Claude Desktop or Claude Code installed
• Basic understanding of APIs and JSON

Quick answer​

The best YouTube transcript scraper on Apify in 2026 is YouTube Transcript Scraper — Captions & AI Fallback. It pulls native captions when YouTube has them, falls back to built-in Whisper AI when it doesn't, and returns a transcript_llm field ready for RAG pipelines — no external API key required. Native transcripts cost $0.001 each.

What is a YouTube transcript scraper?​

A YouTube transcript scraper extracts the spoken text from YouTube videos — either from existing captions or by transcribing the audio when captions are unavailable. The YouTube Data API v3 does not provide transcript data. A dedicated scraper reads the same public caption infrastructure used by the YouTube player's "Open transcript" panel, without requiring a Google Cloud project or API key.

The underused RAG corpus​

Most RAG pipelines ingest PDFs, web pages, and documentation. Few teams tap into YouTube — and that is a significant gap. YouTube hosts decades of expert spoken content across every domain: medical lectures, financial analysis, engineering walkthroughs, legal commentary, academic conference talks. This content does not exist as text anywhere else.

A Google Trends scraper pulls structured interest data from Google Trends—search-term popularity over time, geography, and related queries—without copying numbers by hand from the UI. On Apify, the maintained Google Trends Scraper runs in the cloud so you can export CSV / JSON and plug results into SEO dashboards, content calendars, or competitive research.

An Apify Actor is a serverless scraper or automation packaged for cloud execution. You write standard Node.js code, push it to Apify, and it runs on demand — with built-in proxies, storage, scheduling, and API access included.

This tutorial takes you from an empty folder to a deployed, runnable Actor in about 20 minutes.

Freshness note: Steps verified with Apify CLI 3.x and Apify SDK 3.x (March 2026).