Pdf RAG agent with Telegram chat & auto-ingestion from Google Drive
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 32 nodes and runs manually, when you click “Execute workflow” (plus 3 other triggers). Along the way it connects Azure OpenAI Chat Model, Embeddings Mistral Cloud, Postgres PGVector Store and Google Drive and 1 more.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 3 other triggers).
- List All File Names (Google Drive): work with file folder
- AI Agent: runs an AI agent, with model: Azure OpenAI Chat Model; 1 tool (Postgres PGVector Store); memory: Simple Memory
- Postgres PGVector Store: stores documents in the Postgres PGVector Store vector store, with embeddings: Embeddings Mistral Cloud; document loader: Default Data Loader
- If: checks a condition and branches into true / false
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- AI Agent: runs an AI agent, with model: Azure OpenAI Chat Model; 1 tool (Postgres PGVector Store); memory: Simple Memory
- If: checks a condition and branches into true / false
- Download Corresponding File (Google Drive): download
- Send a Text Message (Telegram): uses Telegram
- Approve Ingestion (Telegram): send and wait for a reply
…plus 7 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 (16)
- Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Azure OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatAzureOpenAi - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request
n8n-nodes-base.httpRequest - Embeddings Mistral Cloud
@n8n/n8n-nodes-langchain.embeddingsMistralCloud - Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Google Drive
n8n-nodes-base.googleDrive - Manual Trigger
n8n-nodes-base.manualTrigger - Webhook
n8n-nodes-base.webhook - Token Splitter
@n8n/n8n-nodes-langchain.textSplitterTokenSplitter - Telegram Trigger
n8n-nodes-base.telegramTrigger - Telegram
n8n-nodes-base.telegram - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - If
n8n-nodes-base.if
From the author
How it works This workflow creates an intelligent document assistant called "Mookie" that can answer questions based on your uploaded documents. Here's how it operates: - Document Ingestion: The system can automatically load PDF files from Google Drive or…