# AI-powered Telegram news broadcaster with Gemini and MongoDB: n8n workflow

> Started by a clock, and works across MongoDB, RSS and Telegram. It hands the judgement calls to Gemini.

Source: https://millionrounds.com/workflow/ai-powered-telegram-news-broadcaster-with-gemini-and-mongodb (Millionrounds; every figure on the page links to its filing or article)

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

# AI-powered Telegram news broadcaster with Gemini and MongoDB

Started by a clock, and works across MongoDB, RSS and Telegram. It hands the judgement calls to Gemini. 29 steps: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-powered-telegram-news-broadcaster-with-gemini-and-mongodb)

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

**0** Branches: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 2 Model 9 Logic 9 Service 9

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

- 1 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 2 **RSS Feed Trigger** Rss Feed Read trigger *Starts it*
- 3 **Structured Output Parser** Output Parser Structured *Model*
- 4 **Schedule Trigger** Schedule trigger *Starts it*
- 5 **Google Gemini Chat Model1** Lm Chat Google Gemini *Model*
- 6 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 7 **Google Gemini Chat Model2** Lm Chat Google Gemini *Model*
- 8 **Basic LLM Chain** Chain Llm *Model*
- 9 **Config** Set *Logic*
- 10 **Report config** Set *Logic*
- 11 **Summarization Chain** Chain Summarization *Model*
- 12 **Default Data Loader** Document Default Data Loader *Model*
- 13 **Basic LLM Chain1** Chain Llm *Model*
- 14 **Article** Merge *Logic*
- 15 **Find News in db** Mongo Db *Service*
- 16 **Get day news** Mongo Db *Service*
- 17 **Format report** Set *Logic*
- 18 **Send to telegram1** Telegram *Service*
- 19 **Generate content** Code *Logic*
- 20 **Filter exist news** Code *Logic*
- 21 **Save day report** Mongo Db *Service*
- 22 **Get account info** Http Request *Service*
- 23 **Get full article** Http Request *Service*
- 24 **Create article** Http Request *Service*
- 25 **Extract article** Html *Logic*
- 26 **Extract img** Html *Logic*
- 27 **Send to telegram** Telegram *Service*
- 28 **Edit to save** Set *Logic*
- 29 **Save news** Mongo Db *Service*

## How it's built

- **Starts on:** A clock
- **Steps:** 29
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** MongoDB, RSS, Telegram
- **Model:** Gemini

## Questions

What does it need to run?

An n8n account, plus your own MongoDB, RSS and Telegram accounts, and a key for Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on a clock.

Does it use AI?

Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 29 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 29 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%2Fai-powered-telegram-news-broadcaster-with-gemini-and-mongodb)
- **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.

[MongoDB](https://millionrounds.com/workflows?service=MongoDB#library)[RSS](https://millionrounds.com/workflows?service=RSS#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also research and reporting, with the same services where possible, closest in size first.

- [**Collect viral Instagram AI art with OpenAI and Telegram** 28 steps · calls a model · Apify, Google Sheets](https://millionrounds.com/workflow/collect-viral-instagram-ai-art-with-openai-and-telegram)
- [**Competitive & market intelligence scanner with OpenAI** 28 steps · calls a model · Google Sheets, RSS](https://millionrounds.com/workflow/competitive-and-market-intelligence-scanner-with-openai)
- [**Crypto market analysis with Chart-img and BrowserAI** 27 steps · calls a model · Telegram](https://millionrounds.com/workflow/crypto-market-analysis-with-chart-img-and-browserai)
- [**Generate visual summary & knowledge graph insights for your email** 27 steps · calls a model · Gmail, Telegram](https://millionrounds.com/workflow/generate-visual-summary-and-knowledge-graph-insights-for-you)
- [**Send weekly parent progress reports with Google Sheets** 27 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/send-weekly-parent-progress-reports-with-google-sheets)
- [**Automate multi-website Google Analytics reports with OpenAI** 25 steps · calls a model · Email, Gmail](https://millionrounds.com/workflow/automate-multi-website-google-analytics-reports-with-openai)