Chat with your email history using Telegram, Mistral and Pgvector for RAG
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 16 nodes and runs on Telegram events (message) (plus 1 other trigger). Along the way it connects Telegram, Postgres PGVector Store, Embeddings Ollama and OpenAI Chat Model.
How it runs
Trigger: On Telegram events (message) (plus 1 other trigger).
- Generate session id (Edit Fields (Set)): sets or maps fields
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 2 tools (Postgres PGVector Store, Call the SQL composer Workflow); memory: Simple Memory
- Came from Telegram? (If): checks a condition and branches into true / false
- Split text into chunks (Code): runs custom JavaScript code
- Beautify chat response (Edit Fields (Set)): sets 1 field: output
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Escape Markdown (Code): runs custom JavaScript code
- Respond on Telegram in batches (Telegram): uses Telegram
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (14)
- Telegram Trigger
n8n-nodes-base.telegramTrigger - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - If
n8n-nodes-base.if - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Embeddings Ollama
@n8n/n8n-nodes-langchain.embeddingsOllama - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - Telegram
n8n-nodes-base.telegram - No Operation, do nothing
n8n-nodes-base.noOp - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
From the author
Who is this for? Everyone! Did you dream of asking an AI "what hotel did I stay in for holidays last summer?" or "what were my marks last semester like?". Dream no more, as vector similarity searches and this workflow are the foundations to make it possible…