Save, search, and summarize Telegram links with Google Sheets and Supabase

by Anan ✓ · 25 views · created 2026-07-22 · Personal Productivity, AI RAG

What this workflow does

This AI workflow has 50 nodes and runs manually, when you click “Execute workflow” (plus 2 other triggers). Along the way it connects Telegram, Google Sheets, HTTP Request and Embeddings Google Gemini and 3 more. It also calls n8n.anan.dev over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 2 other triggers).

1. Create Link Library Spreadsheet (Google Sheets): work with spreadsheet
2. Clean URL (Edit Fields (Set)): sets 2 fields: url, note
3. New chat? (If): checks a condition and branches into true / false
4. Seed Columns (Edit Fields (Set)): sets 10 fields: ID, URL, Title…
5. Generate ID (Crypto): hashes or encrypts values
6. Clear memory (Chat Memory Manager): uses Chat Memory Manager, with memory: Memory
7. Get Message Basics (Edit Fields (Set)): sets 2 fields: rawText, chatId
8. Write Headers (Google Sheets): append
9. Read Page (Jina) (HTTP Request): calls an HTTP API
10. Notify memory cleared (Telegram): send rich message

…plus 25 more steps. See the full node list below.

Services it uses

TelegramGoogle SheetsHTTP RequestEmbeddings Google GeminiSupabase Vector StoreSupabaseOpenAI Chat Model

HTTP calls to: n8n.anan.dev

Before you upgrade to n8n 3.0

Nodes used (27)

• Telegram Triggern8n-nodes-base.telegramTrigger
• Edit Fields (Set)n8n-nodes-base.set
• Ifn8n-nodes-base.if
• AI Agent@n8n/n8n-nodes-langchain.agent
• Google Sheets Tooln8n-nodes-base.googleSheetsTool
• Telegramn8n-nodes-base.telegram
• HTTP Requestn8n-nodes-base.httpRequest
• Google Sheetsn8n-nodes-base.googleSheets
• Aggregaten8n-nodes-base.aggregate
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Webhookn8n-nodes-base.webhook
• Http Request Tooln8n-nodes-base.httpRequestTool
• Embeddings Google Gemini@n8n/n8n-nodes-langchain.embeddingsGoogleGemini
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Recursive Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
• Chat Memory Manager@n8n/n8n-nodes-langchain.memoryManager
• Remove Duplicatesn8n-nodes-base.removeDuplicates
• Crypton8n-nodes-base.crypto
• Supabase Vector Store@n8n/n8n-nodes-langchain.vectorStoreSupabase
• Limitn8n-nodes-base.limit
• Manual Triggern8n-nodes-base.manualTrigger
• No Operation, do nothingn8n-nodes-base.noOp
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow
• Supabasen8n-nodes-base.supabase
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi

From the author

Quick overview This workflow turns a Telegram bot into a “second brain” link library by saving shared URLs to Google Sheets, generating titles/summaries/categories with Google Gemini, and indexing full-page content in Supabase (pgvector) for semantic search.…

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