🚀 Process YouTube transcripts with Apify, OpenAI & Pinecone database

🚀 YouTube Transcript Indexing Backend for Pinecone 🎥💾

This tutorial explains how to build the backend workflow in n8n that indexes YouTube video transcripts into a Pinecone vector database. Note: This workflow handles the processing and indexing of transcripts only—the retrieval agent (which searches these embeddings) is implemented separately.

---

📋 Workflow Overview

This backend workflow performs the following tasks:

1. Fetch Video Records from Airtable 📥 Retrieves video URLs and related metadata.

2. Scrape YouTube Transcripts Using Apify 🎬 Triggers an Apify actor to scrape transcripts with timestamps from each video.

3. Update Airtable with Transcript Data 🔄 Stores the fetched transcript JSON back in Airtable linked via video ID.