Process Thai documents with TyphoonOCR & AI to Google Sheets (multi-page PDF)
Ready for 3.0What this workflow does
This AI workflow has 14 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenRouter Chat Model and Google Sheets.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Load PDFs from doc Folder (Read/Write Files from Disk): reads a file from disk
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Read/Write Files from Disk: writes a file to disk
- Set_Input_Path (Code): runs custom JavaScript code
- Split PDF page (Execute Command): runs a shell command on the n8n host
- Read Splite PDF Page (Read/Write Files from Disk): reads a file from disk
- Extract Text with Typhoon OCR (Execute Command): runs a shell command on the n8n host
- Aggregate: combines items into one
- Structure Text to JSON with LLM (Basic LLM Chain): sends a prompt to an LLM, with model: OpenRouter Chat Model
- Parse JSON to Sheet Format (Code): runs custom JavaScript code
…plus 2 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (9)
- Manual Trigger
n8n-nodes-base.manualTrigger - Execute Command
n8n-nodes-base.executeCommand - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Code
n8n-nodes-base.code - Aggregate
n8n-nodes-base.aggregate - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Google Sheets
n8n-nodes-base.googleSheets
From the author
⚠️ Note: This template requires a community node and works only on self-hosted n8n installations. It uses the Typhoon OCR Python package, pdfseparate from poppler-utils, and custom command execution. Make sure to install all required dependencies locally. ---…