Analyse tender PDFs with LlamaParse, Gemini, Supabase and WhatsApp chat

by Divyanshu Gupta ✓ · 937 views · created 2026-07-03 · Document Extraction, AI RAG

What this workflow does

This AI workflow has 21 nodes and runs when someone submits an n8n form (“Upload Tender Document”) (plus 1 other trigger). Along the way it connects Google Sheets, Anthropic, Supabase and WhatsApp Business Cloud and 1 more. It also calls generativelanguage.googleapis.com over HTTP.

How it runs

Trigger: When someone submits an n8n form (“Upload Tender Document”) (plus 1 other trigger).

1. Generate Doc ID (Code): runs custom JavaScript code
2. Extract Question (Code): runs custom JavaScript code
3. Parse a document (Llama Parse Platform): uses Llama Parse Platform
4. Split a file (Llama Parse Platform): work with splitting
5. Extract structured data from a document (Llama Parse Platform): work with extracting
6. Gemini — Embed Question (HTTP Request): calls generativelanguage.googleapis.com (POST)
7. Merge: merges the data from its input branches
8. Normalize + Bid Score (Code): runs custom JavaScript code
9. Vector Search (HTTP Request): calls an HTTP API (POST)
10. Prepare RAG Payload (Code): runs custom JavaScript code

…plus 9 more steps. See the full node list below.

Services it uses

Google SheetsAnthropicSupabaseWhatsApp Business CloudLlamacloud (community)

HTTP calls to: generativelanguage.googleapis.com

Before you upgrade to n8n 3.0

Nodes used (11)

• n8n Form Triggern8n-nodes-base.formTrigger
• Coden8n-nodes-base.code
• Llama Parse Platform@llamaindex/n8n-nodes-llamacloud.llamaParsePlatform
• Mergen8n-nodes-base.merge
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• HTTP Requestn8n-nodes-base.httpRequest
• Google Sheetsn8n-nodes-base.googleSheets
• Anthropic@n8n/n8n-nodes-langchain.anthropic
• Supabasen8n-nodes-base.supabase
• WhatsApp Triggern8n-nodes-base.whatsAppTrigger
• WhatsApp Business Cloudn8n-nodes-base.whatsApp

From the author

Quick overview This workflow lets you upload a tender/RFT PDF via an n8n form, extracts key fields into Google Sheets using LlamaParse, and makes the document chat-searchable by embedding section chunks with Google Gemini and storing them in Supabase for…

View the original on n8n.io → Check your own copy