Sync website crawl deltas into Qdrant with Apify and OpenAI embeddings

Quick overview

This workflow triggers on a completed Apify Website Content Crawler run, syncs the crawl dataset into a Qdrant collection using OpenAI embeddings, then compares vector counts and parses the Apify run logs to report what chunks were added, refreshed, or deleted.

How it works

1. Triggers when an Apify Website Content Crawler actor run finishes.
2. Calls the Qdrant Collections API to read the current point count in the target collection as a pre-sync baseline.
3. Starts an Apify Qdrant Integration actor run to upsert the crawl dataset into Qdrant, generating embeddings with OpenAI and applying delta updates plus deletion of expired chunks.
4. Waits 30 seconds to allow the Qdrant sync to finish settling.
5. Calls the Qdrant Collections API again to read the post-sync point count.
6. Fetches the Apify actor run logs and outputs a freshness report with vectors-before/after and the counts of chunks added, refreshed, and deleted.

Setup

1. Create and select an Apify API credential for the Apify Trigger, the sync run request, and the log request.
2. Set environment variables QDRANT_API_KEY and OPENAI_API_KEY, and allow env access in nodes (for example by setting N8N_BLOCK_ENV_ACCESS_IN_NODE=false if required by your n8n deployment).
3. Replace https://YOUR-CLUSTER.qdrant.io:6333 with your Qdrant endpoint in all Qdrant URLs and in the sync request body, and ensure the docs collection name matches your intended collection (or allow auto-create).
4. Ensure the Apify Website Content Crawler actor is available in your Apify account and run it once so the trigger can be configured and tested.