# Telegram AI chatbot with OpenAI and PGVector RAG: n8n workflow

> Started by someone opening a chat with it, and works across Google Drive and Postgres. It puts OpenAI behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/telegram-ai-chatbot-with-openai-and-pgvector-rag (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Documents and files](https://millionrounds.com/workflows?category=Documents+and+files#library)

# Telegram AI chatbot with OpenAI and PGVector RAG

Started by someone opening a chat with it, and works across Google Drive and Postgres. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 24 steps, 1 loop or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ftelegram-ai-chatbot-with-openai-and-pgvector-rag)

**24 steps** Large: read it before trusting it with anything live

**0** Branches: places the flow splits

**1** Loop or waits

**2** Services it connects to

## The flow

Starts it 4 Model 11 Logic 6 Service 3

The steps in the order they run, from what starts it.

- 1 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 2 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 3 **File Created** Google Drive trigger *Starts it*
- 4 **File Updated** Google Drive trigger *Starts it*
- 5 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 6 **When chat message received** Chat trigger *Starts it*
- 7 **OpenAI Chat Model3** Lm Chat Open Ai *Model*
- 8 **When Executed by Another Workflow** Execute Workflow trigger *Starts it*
- 9 **Embeddings** Embeddings Open Ai *Model*
- 10 **Chat Memory** Memory Postgres Chat *Model*
- 11 **RAG AI Agent** Agent *Model*
- 12 **Postgres PGVector Store** Vector Store PGVector *Model*
- 13 **Loop Over Items** Split In Batches *Logic*
- 14 **Default Data Loader** Document Default Data Loader *Model*
- 15 **Generate Contextual Text** Chain Llm *Model*
- 16 **TestData** Set *Logic*
- 17 **Docs RAG Tool** Vector Store PGVector *Model*
- 18 **Set File ID** Set *Logic*
- 19 **Get Values** Set *Logic*
- 20 **Delete Old Doc Records** Postgres *Service*
- 21 **Download File** Google Drive *Service*
- 22 **Extract Document Text** Extract From File *Service*
- 23 **Create Chunks From Doc** Code *Logic*
- 24 **Chunks To List** Split Out *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 24, 1 loop or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Drive, Postgres
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Google Drive and Postgres accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 24 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 24 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ftelegram-ai-chatbot-with-openai-and-pgvector-rag)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[Postgres](https://millionrounds.com/workflows?service=Postgres#library)

## Workflows like it

Also documents and files, with the same services where possible, closest in size first.

- [**Automate document ingestion & RAG system with Google Drive** 24 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/automate-document-ingestion-and-rag-system-with-google-drive)
- [**Document Q&A system with OpenAI and Pinecone Vector DB** 24 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/document-q-and-a-system-with-openai-and-pinecone-vector-db)
- [**Review contract clauses against your playbook** 24 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/review-contract-clauses-against-your-playbook)
- [**Chat with Supabase** 23 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/chat-with-supabase)
- [**Document RAG & chat agent: Google Drive to Qdrant with Mistral** 25 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/document-rag-and-chat-agent-google-drive-to-qdrant-with-mist)
- [**Extract timesheet data with Mistral and Gmail** 23 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/extract-timesheet-data-with-mistral-and-gmail)