Tools: Build a Serverless RAG Engine for $0

Master modern AI architecture with Node.js, Gemini 2.5, and Cloudflare R2 ## Introduction: The Problem with "Toy" RAG Apps ## The $0 Tech Stack ## Step 1: Understanding the Architecture ## Step 2: Zero-Cost Storage with Cloudflare R2 ## Step 3: Contextual Query Rewriting ## Step 4: Hybrid Search with Row-Level Security ## Step 5: Visual RAG - Understanding Images ## Conclusion: Build vs Buy ## 🚀 Want the Full Source Code? 👉 Get the Source Code & Template Here 👉 Read the full tutorial here Most RAG tutorials skip the hard parts that actually matter in production: We are going to solve all of these using a production-proven architecture. Every piece of this stack has a generous free tier: We follow a 4-phase workflow designed for scale: Traditional uploads stream data through your server. If 10 users upload 50MB files simultaneously, your server spikes by 500MB and likely crashes. The Solution: The Reservation Pattern We issue a time-limited Presigned URL. The browser sends the file directly to Cloudflare. If a user asks "Who is the CEO of Tesla?" followed by "What about SpaceX?", a naive vector search for "What about SpaceX?" will fail because it lacks context. We use Gemma 3-12B to rewrite queries in ~200ms: This ensures your vector search actually finds the right documents. Multi-tenancy is the biggest hurdle in RAG. You can't let User A see User B's documents. Instead of filtering in JavaScript (which is slow and buggy), we do it in SQL: This enforces security at the database layer. No accidental data leaks. Traditional RAG is text-only. If you upload a receipt, most systems fail. We use Gemini Vision to describe the image in detail, then embed that description. Now, when you search "How much did I spend at Starbucks?", the system finds the image because of its semantic description. Commercial RAG solutions can cost $1,900+/year. By building this architecture, you save that money while gaining skills in: If you want to save 40+ hours of setup, I’ve packaged this entire production-ready architecture into the Node.js Enterprise Launchpad. It includes the RAG pipeline, Auth, RBAC, Socket.io, and Docker configurations. 👉 Get the Source Code & Template Here Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse CODE_BLOCK: // Backend: Generate the permission const { signedUrl, fileKey, fileId } = await uploadService.generateSignedUrl( fileName, fileType, fileSize, isPublic, req.user ); res.send({ signedUrl, fileKey, fileId }); Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: // Backend: Generate the permission const { signedUrl, fileKey, fileId } = await uploadService.generateSignedUrl( fileName, fileType, fileSize, isPublic, req.user ); res.send({ signedUrl, fileKey, fileId }); CODE_BLOCK: // Backend: Generate the permission const { signedUrl, fileKey, fileId } = await uploadService.generateSignedUrl( fileName, fileType, fileSize, isPublic, req.user ); res.send({ signedUrl, fileKey, fileId }); CODE_BLOCK: // User: "What about SpaceX?" // Gemma Rewrites: "Who is the CEO of SpaceX?" Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: // User: "What about SpaceX?" // Gemma Rewrites: "Who is the CEO of SpaceX?" CODE_BLOCK: // User: "What about SpaceX?" // Gemma Rewrites: "Who is the CEO of SpaceX?" COMMAND_BLOCK: SELECT d.content, d.metadata, f."originalName", (d.embedding <=> ${vectorQuery}::vector) as distance FROM "Document" d LEFT JOIN "File" f ON d."fileId" = f.id WHERE (d."userId" = ${userId} OR f."isPublic" = true) ORDER BY distance ASC LIMIT 5; Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: SELECT d.content, d.metadata, f."originalName", (d.embedding <=> ${vectorQuery}::vector) as distance FROM "Document" d LEFT JOIN "File" f ON d."fileId" = f.id WHERE (d."userId" = ${userId} OR f."isPublic" = true) ORDER BY distance ASC LIMIT 5; COMMAND_BLOCK: SELECT d.content, d.metadata, f."originalName", (d.embedding <=> ${vectorQuery}::vector) as distance FROM "Document" d LEFT JOIN "File" f ON d."fileId" = f.id WHERE (d."userId" = ${userId} OR f."isPublic" = true) ORDER BY distance ASC LIMIT 5; - No security model: Users can access each other's private data. - Naive file handling: Large uploads crash your Node.js server. - Expensive infra: AWS egress fees and managed vector DBs drain your wallet. - Blocking operations: Processing files freezes your entire API. - Cloudflare R2: S3-compatible storage with zero egress fees. - Gemini 2.5 Flash: High-performance LLM with a free tier of 15 requests/minute. - PostgreSQL + pgvector: Battle-tested database with native vector support. - BullMQ: Redis-backed job queue to handle heavy processing in the background. - Direct-to-Cloud Uploads: Browser uploads files directly to R2 using presigned URLs. Your server never touches the raw bytes, preventing memory crashes. - Asynchronous Ingestion: A BullMQ worker handles the "heavy lifting"—downloading, chunking, and embedding—without blocking your API. - Hybrid Retrieval: We use PostgreSQL row-level security so users only search their own data. - Contextual Generation: Gemini generates answers with smart citations (temporary links to the source files). - Distributed systems (BullMQ) - Vector Database optimization (pgvector) - Cloud Security (Presigned URLs) - Standard Price: $20 - Launch Special: $4 (80% OFF)