Invoice OCR from Telegram to SAP with approval

# Extract invoice data from Telegram and send to SAP with approval This automation streamlines the entry of incoming invoices into SAP by processing files sent via Telegram. It uses AI-powered OCR and structured parsing, making it ideal for finance teams in SAP-driven environments. ## Who it´s for - Accountants handling incoming invoices - Finance operators in companies with SAP integration - Procurement managers automating data entry - Businesses using Telegram as a document intake channel ## What the automation does - On receiving a PDF invoice via Telegram, the file is processed using LlamaIndex OCR - Extracted text is parsed by GPT-4o-mini into structured JSON (supplier, RUC, items, totals) - User receives structured data and confirms via Telegram callback_query - On confirmation, data is sent to SAP as a PurchaseInvoice via HTTP API - All processed records are duplicated in Google Sheets for audit and tracking ## What´s included - Ready-to-use n8n workflow - Trigger and handler logic for messages and callbacks - Integrations with Telegram, SAP, Google Sheets, and LlamaIndex API - Basic setup and adaptation guide ## Requirements for setup - n8n instance with access to LangChain and LlamaIndex - Telegram Bot API access - SAP credentials with permissions to create PurchaseInvoice - Google Sheets spreadsheet for logging - OpenAI API key (for GPT-4o-mini) ## Benefits and outcomes - Reduces manual data entry by up to 90% - Minimizes errors in invoice transcription - Enables fast processing of high invoice volumes - Transparent audit trail in Google Sheets - Maintains user control via confirmation step ## Important: template only Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via chat