Record transactions & generate budget reports with Gemini AI, Telegram & Firefly III
Ready for 3.0What this workflow does
This AI workflow has 17 nodes and runs on Telegram events (message). Along the way it connects Telegram, Google Gemini and Google Gemini Chat Model.
How it runs
Trigger: On Telegram events (message).
- Switch: routes items into 4 branches
- Get image from server (Telegram): work with file
- Get file from server (Telegram): work with file
- Get Remaining Budget (HTTP Request): calls an HTTP API
- Analyze the image or pdf (Google Gemini): work with document
- Parse JSON (Code): runs custom JavaScript code
- Parse details & add category (AI Agent): runs an AI agent, with model: Analyzer Scraper; output parser: Parse Output
- Pull required fields (Edit Fields (Set)): sets 4 fields: Bucket, Budget, Spent…
- Make it pretty (Code): runs custom JavaScript code
- Make CSV (Convert to File): converts data to a file
…plus 4 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 (12)
- Telegram
n8n-nodes-base.telegram - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Switch
n8n-nodes-base.switch - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Edit Fields (Set)
n8n-nodes-base.set - Convert to File
n8n-nodes-base.convertToFile - Telegram Trigger
n8n-nodes-base.telegramTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured
From the author
Who this is for Anybody using Firefly III, especially home/self-hosted users, who want to add some level of automation to their transaction tracking, either in addition to or because they can't or don't want to use the dataimporter How it works - posting…