Portfolio / RAG Document Automation

RAG Document Automation

Drafts a structured document from your own files and live data, then hands it to a person for sign-off.

5× faster · 95% output alignment

n8nBigQueryRAG

The problem

Each document meant pulling information from several places by hand and then writing it up. It took 2 to 4 hours a time, and the results varied from one writer to the next.

What I built

I built a pipeline that finds the relevant passages in the team’s own files, adds the latest figures from the database, and writes a structured draft for a person to check. It runs in n8n, with Supabase for the search and BigQuery for the live data.

Results

2–4hrsSaved per doc cycle
RAGVector + BigQuery in one flow

Built with

n8nSupabase · pgvectorGoogle BigQueryPineconeGemini EmbeddingsLLM · Prompt Engineering

Diagram

See the workflow diagram →

What you see here

The demo runs on made-up sample data. Real records, internal methods and anything confidential are left out.

Want something like this?

Tell me about the process you want off your plate. The brief takes about three minutes, and the project is priced before I start.

Start a Brief