This weekend I experimented with a different way to build RAG. Instead of the typical setup: - Generate embeddings - Store in Pinecone / Supabase - Manage vector DB infra - Handle indexing + costs I tested Gemini File Search API directly inside n8n. And honestly… it simplified the entire pipeline. 🔧 What I Actually Built Inside n8n, I used just 4 HTTP requests: 1. Create a file store 2. Upload a document 3. Move the file into the store 4. Query Gemini That’s it. Gemini handled: - Chunking - Embeddings - Indexing - Retrieval No external vector database.No embedding model setup. 💰 Why This Is Interesting - Storage is free - No hourly DB cost - Indexing is $0.15 per 1M tokens For small projects, internal tools, or MVPs — this is extremely cost-efficient. ⚠️ Important Limitations I Noticed This is not magic. - No automatic version control (re-upload = duplicate data) - Chunk-based retrieval struggles with full-document reasoning - OCR works, but messy documents still need preprocessing - Data is processed on Google servers (privacy considerations apply) So architecture thinking still matters. My Take For: - Internal AI assistants - Automation workflows - Startup prototypes - Personal tools This is a powerful alternative to traditional vector DB setups. I wouldn’t blindly replace enterprise-grade systems yet — but for builders, this is very interesting. If anyone here is experimenting with Gemini File Search or building RAG in n8n, I’d love to compare notes 👇 Happy to share the workflow structure if there’s interest.

Most “lead tools” tap out after 1 suburb or a handful of results. And if you try to scale? You either hit Google’s API limits… or your wallet takes the L. $5 here, $12 there — just to scrape data that’s already public. So I stopped relying on APIs. Stopped buying databases. Stopped praying someone else did the scraping right. And I built this instead 👇 ✅ Enter a business type (like "plumber" or "dentist") ✅ Enter a city (like "Los Angeles") ✅ The system auto-generates 30+ hyper-local Google Maps search terms: • plumber+in+hollywood • plumber+in+echo+park • plumber+in+downtown • plumber+near+koreatown • ...it goes deep. Like, “every-corner-of-the-city” deep. Then it gets to work: — Scrapes websites from Google Maps — Filters out junk & Google-owned links — Deduplicates and cleans the list — Extracts valid emails from the homepages using Regex — Delivers a clean sheet of contacts and sites No scraping headaches. No wasted API credits. No manual copy-paste ever again. Perfect if you sell: → Web design → SEO → Paid ads → Local services → B2B outreach to SMBs Basically, if your ideal client is on Google Maps... this system turns their map pin into a real lead. I’ve used it to pull 1,000+ niche businesses per city. No limits. No bloat.