πŸš€ On-Device Local n8n RAG Suite: Air-Gapped AI Engineering Copilot & Vector Sync Engines

:rocket: Air-Gapped Local n8n RAG Suite: Dual-Tool AI Copilot & Vector Sync Engines

Standard cloud LLMs frequently hallucinate n8n node schemas, parameters, and expression syntax ($json vs $input). Plus, sending internal workflow logic or credentials to SaaS models creates compliance risks.

I built the n8n Local RAG Suite: an end-to-end, fully air-gapped retrieval-augmented generation architecture running 100% locally on host hardware (Ollama + Qdrant + n8n).


:building_construction: Architecture Overview

       [ Doc Ingestion ]      [ Template Sync ]
       (Daily 3 AM Sync)      (749k Catalog)
               β”‚                      β”‚
               β–Ό                      β–Ό
      [ Qdrant: n8n_docs ]  [ Qdrant: n8n_templates ]
      (14.6k Vectors)       (749k Vectors)
               β”‚                      β”‚
               β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                          β”‚
                          β–Ό
              [ AI Engineering Agent ]
              (qwen2.5:7b-instruct)

:sparkles: Key Highlights

  • ~10ms Smart GitHub SHA Guard: Checks the latest n8n-io/n8n-docs commit SHA against stored Qdrant memory, skipping unnecessary re-indexing if documentation hasn’t changed.
  • Pre-Ingestion Secret Sanitizer: Runs 7 regex security filters to scrub raw credentials, API keys, and emojis before vector storage.
  • Dual-Tool Local RAG Routing: qwen2.5:7b-instruct dynamically routes between official documentation (n8n_docs_retriever) and community workflow patterns (n8n_templates_retriever).

:laptop: Hardware Requirements

  • Local Hardware: Runs on workstation GPUs (tested on RTX 3000 Ada / 8GB VRAM).
  • Ollama Models: qwen2.5:7b-instruct (num_ctx: 16384) + nomic-embed-text.
  • Vector DB: Qdrant (qdrant/qdrant:latest).

:link: Get Started & Full Documentation

Full installation steps, Docker Compose files, metadata schemas, and test cases are available on GitHub. You can also skip the multi-hour template embedding sweep by downloading the pre-indexed 749k vector snapshot directly from Hugging Face.

:backhand_index_pointing_right: GitHub Repository: jdm6457/n8n-rag-suite
:hugs: Instant Qdrant Database Seed: Hugging Face Dataset Snapshot

Would love to hear your feedback or ideas for the planned nine (9) additional phases!

1 Like