Build a Telegram Q&A bot with Linkup web search, GPT-4.1 & Mistral voice

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Create a Telegram bot that answers questions using AI powered web search from Linkup and an LLM agent (GPT 4.1). This template handles both text and voice messages (voice transcribed via a Mistral ...

Best for

Support Chatbot automation workflows
AI Chatbot automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.telegramtrigger, n8n-nodes-base.if, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.memorybufferwindow, n8n-nodes-base.stickynote, n8n-nodes-base.telegram, n8n-nodes-base.switch, @n8n/n8n-nodes-langchain.lmchatopenai

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Guillaume Duvernay.

Original n8n.io source

1.1 Workflow description

Title: Build a Telegram Q&A bot with Linkup web search, GPT-4.1 & Mistral voice
Workflow name: Build a Telegram Q&A bot with Linkup web search, GPT-4.1 & Mistral voice

Create a Telegram bot that answers questions using AI-powered web search from Linkup and an LLM agent (GPT-4.1).

This template handles both text and voice messages (voice transcribed via a Mistral model by default), routes queries through an agent that can call a Linkup tool to fetch up-to-date information from the web, and returns concise, Telegram-friendly replies. A security switch lets you restrict use to a single Telegram username for private testing, or remove the filter to make the bot public.

Who is this for?

Anyone needing quick answers: Build a personal assistant that can look up current events, facts, and general knowledge on the web.
Support & ops teams: Provide quick, web-sourced answers to user questions without leaving Telegram.
Developers & automation engineers: Use this as a reference for integrating agents, transcription, and web search tools inside n8n.
No-code builders: Quickly deploy a chat interface that uses Linkup for accurate, source-backed answers from the web.

What it does / What problem does this solve?

Provides accurate, source-backed answers: Routes queries to Linkup so replies are grounded in up-to-date web search results instead of the LLM's static knowledge.
Handles voice & text transparently: Accepts Telegram voice messages, transcribes them (via the Mistral API node by default), and treats transcripts the same as typed text.
Simple agent + tool architecture: Uses a LangChain AI Agent with a Web search tool to separate reasoning from information retrieval.
Privacy control: Includes a Myself? filter to restrict access to a specific Telegram username for safe testing.

How it works

Trigger: Telegram Trigger receives incoming messages (text or voice).
Route: Message Router detects voice vs text. Voice files are fetched with Get Audio File.
Transcribe: Mistral transcribe receives the audio file and returns a transcript; the transcript or text is normalized into preset_user_message and consolidated in Consolidate user message.
Agent: AI Agent (GPT-4.1-mini configured) runs with a system prompt that instructs it to call the Web search tool when up-to-date knowledge is required.
Respond: The agent output is sent back to the user via Telegram answer.

How to set up

Create a Linkup account: Sign up at https://linkup.so to get your API key. They offer a free tier with monthly credits.
Add credentials in n8n: Configure Telegram API, OpenAI (or your LLM provider), and Mistral Cloud credentials in n8n.
Configure Linkup tool: In the Web search node, find the "Headers" section. In the Authorization header, replace Bearer <your-linkup-api-key> with your actual Linkup API Key.
Set Telegram privacy (optional): Edit the Myself? If node and replace <Replace with your Telegram username> with your username to restrict access. Remove the node to allow public use.
Adjust transcription (optional): Swap the Mistral transcribe HTTP node for another provider (OpenAI, Whisper, etc.).
Connect LLM: In OpenAI Chat Model node, add your OpenAI API key (or configure another LLM node) and ensure the AI Agent node references this model.
Activate workflow: Activate the workflow and test by messaging your bot in Telegram.

Requirements

An n8n instance (cloud or self-hosted)
A Telegram Bot token added in n8n credentials
A Linkup account and API Key
An LLM provider account (OpenAI or equivalent) for the OpenAI Chat Model node
A Mistral API key (or other transcription provider) for voice transcription

How to take it further

Add provenance & sources: Parse Linkup responses and include short citations or source links in the agent replies.
Rich replies: Use Telegram media (images, files) or inline keyboards to create follow-up actions (open web pages, request feedback, escalate to humans).
Multi-user access control: Replace the single-username filter with a list or role-based access system (Airtable or Google Sheets lookup) to allow multiple trusted users.
Logging & analytics: Save queries and agent responses to Airtable or Google Sheets for monitoring, quality checks, and prompt improvement.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Telegram Trigger

Type / Role: n8n-nodes-base.telegramTrigger - telegramTrigger
Config choices: Version 1.1

Block 2 - Myself?

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 3 - AI Agent

Type / Role: @n8n/n8n-nodes-langchain.agent - agent
Config choices: Version 1.8

Block 4 - Simple Memory

Type / Role: @n8n/n8n-nodes-langchain.memoryBufferWindow - memoryBufferWindow
Config choices: Version 1.3

Block 5 - Sticky Note5

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - Get Audio File

Type / Role: n8n-nodes-base.telegram - telegram
Config choices: Version 1.2

Block 7 - Message Router

Type / Role: n8n-nodes-base.switch - switch
Config choices: Version 3.2

Block 8 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 9 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 10 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 11 - OpenAI Chat Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices: Version 1.2

Block 12 - Telegram answer

Type / Role: n8n-nodes-base.telegram - telegram
Config choices: Version 1.2

Block 13 - Sticky Note6

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 14 - Sticky Note7

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 15 - Sticky Note8

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 16 - Prepare message from audio

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 17 - Prepare message from text

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 18 - Consolidate user message

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 19 - Sticky Note3

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 20 - Web search

Type / Role: n8n-nodes-base.httpRequestTool - httpRequestTool
Config choices: Version 4.2

Block 21 - Mistral transcribe

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

3. Summary Table

Workflow	Build a Telegram Q&A bot with Linkup web search, GPT-4.1 & Mistral voice
Complexity	advanced
Nodes	21
Categories	Support Chatbot, AI Chatbot
Author	Guillaume Duvernay
Published	18 Oct 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/9871/9871.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Support Chatbot workflows AI Chatbot workflows

Frequently asked questions

What does Build a Telegram Q&A bot with Linkup web search, GPT-4.1 & Mistral voice do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Support Chatbot, AI Chatbot use case.

Guillaume Duvernay

23 workflows

Nodes

n8n-nodes-base.telegramtrigger n8n-nodes-base.if @n8n/n8n-nodes-langchain.agent @n8n/n8n-nodes-langchain.memorybufferwindow n8n-nodes-base.stickynote n8n-nodes-base.telegram n8n-nodes-base.switch @n8n/n8n-nodes-langchain.lmchatopenai

Complexity

advanced

Published 18 Oct 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/9871/9871.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Route RAG customer support across WhatsApp and Outlook with Pinecone and OpenRouter

## Quick overview A production-ready 3-workflow system that handles customer support across WhatsApp and Email using RAG-powered AI. Automatically routes queries, detects escalation intent, logs handoffs to Google Sheets, alerts your team via Slack, and lets agents resolve cases with a single slash command. ## How it works 1. A form trigger accepts PDF, DOCX, and TXT documents, chunks them with a token splitter, embeds them using Google Gemini, and stores them in your Pinecone vector store to build the AI knowledge base. 2. Incoming messages from WhatsApp Business Cloud API and Microsoft Outlook are each normalized into a unified contact format — capturing channel, contact ID, name, and message text — before merging into a single pipeline. 3. Every message is checked against a Google Sheets handoff tracker. If the contact is currently assigned to a human agent, the message is forwarded directly to Slack without any AI involvement. 4. For active (non-handoff) contacts, the AI Support Agent queries Pinecone via RAG, pulls context from a sliding conversation memory window, and returns a structured JSON output containing a reply and a handoff_requested flag. 5. If the AI detects escalation intent or has no answer, it sets handoff_requested: true — the contact is logged to Google Sheets, AI goes silent for that contact, and a detailed alert is posted to your Slack support channel. 6. Answers are routed back through the originating channel — WhatsApp replies via Business Cloud API, email replies via Microsoft Outlook — keeping every conversation native to its platform. 7. Support agents run /resolve [contact_id] in Slack to close a handoff. The workflow validates the input, updates the Google Sheets row with agent name and timestamp, re-enables AI for that contact, and confirms resolution in the Slack channel. ## Setup 1. Pinecone + Embeddings: Create a Pinecone index and add your Pinecone credential to the "Insert into Vector Store" and "Knowledge Base" nodes. Set your Google Gemini API credential on both Embeddings nodes (one in Workflow 1, one in Workflow 2). 2. WhatsApp: Connect your WhatsApp Business Cloud API credential to the WhatsApp Trigger node. Replace YOUR_WHATSAPP_PHONE_NUMBER_ID in both Send WhatsApp Message nodes. 3. Email: Add your Microsoft Outlook OAuth2 credential to the Outlook Trigger and the Send Email Answer node. 4. Handoff Sheet: Create a Google Sheet with a tab named Handoffs and these column headers exactly: contact_id | channel | contact_name | status | handoff_since | resolved_by | resolved_at. Set your Google Sheets credential and paste your Sheet ID into all four Google Sheets nodes across Workflows 2 and 3. 5. Slack: Create a Slack bot app, add it to your support channel, and set the credential in all three Slack nodes. Update the channel name if yours differs from #support-handoff. 6. AI Model: Add your OpenRouter (or OpenAI) API key to the Chat Model node. Swap the model slug in node settings as needed. 7. Slash Command: Activate Workflow 3 first to generate its production webhook URL. Then in your Slack app settings go to Slash Commands → Create New → set command to /resolve → paste the webhook URL → reinstall app to workspace. 8. Activate order: Workflow 1 (KB ingestion) → Workflow 3 (resolve handler) → Workflow 2 (main support flow). ## Requirements - n8n (self-hosted or cloud) - WhatsApp Business Cloud API account (Meta Developer App) - Microsoft 365 / Outlook account - Pinecone account - Google Gemini API key - OpenRouter or OpenAI API key or Any other LLM - Google Sheets - Slack workspace with a custom bot app ## Customization - Edit the system prompt in the AI Support Agent node to match your brand voice, support scope, and escalation rules - Swap Google Gemini Embeddings for OpenAI Embeddings — just replace the Embeddings node and ensure your Pinecone index dimensions match - dd more channels (Telegram, Instagram DM, etc.) by normalizing their payloads into the same contact format and feeding them into the Merge node - Adjust conversation memory window (default: 8 messages) in the Conversation Memory node - Trigger the resolve webhook from your CRM or helpdesk instead of Slack if preferred ## Additional info All three workflows must be active simultaneously for the system to function Handoff state is persisted in Google Sheets and survives n8n restarts or server reboots Once a contact enters handoff, the AI is completely silent for that contact — no accidental double-responses Document metadata (filename, uploader name, timestamp) is stored alongside vectors in Pinecone for full traceability Default chunk settings: 500 tokens / 100 overlap — tune in the Token Splitter node based on your document style Contact / Support 🔗 n8n Templates: n8n.io/creators/salmanmehboob 💼 LinkedIn: linkedin.com/in/salman-mehboob-pro 📧 Email: [email protected] 💬 WhatsApp: +92 306 746 6499

View

Answer hotel guest messages with GPT-4o mini, Slack, and Google Sheets

## Quick Overview This workflow receives guest messages via a webhook, uses OpenAI (GPT-4o-mini) to generate multilingual hotel support replies with an escalation flag, notifies the front desk in Slack when needed, logs the interaction to Google Sheets, and returns a JSON acknowledgement to the messaging gateway. ## How it works 1. Receives an inbound guest message through a webhook from a WhatsApp/Viber gateway. 2. Normalizes the incoming payload into a consistent structure (guest ID, channel, guest name, and message text). 3. Uses OpenAI (GPT-4o-mini) to generate a short reply in the guest’s language based on the built-in hotel information and outputs structured JSON with language, reply, category, and an escalate flag. 4. If the message needs human attention, posts the guest details and message to a Slack front-desk channel. 5. Routes the reply based on the reported channel and sends the generated reply text to Slack. 6. Appends the conversation data to Google Sheets and responds to the gateway with a JSON status including the detected language and whether it was escalated. ## Setup 1. Configure the inbound webhook URL in your WhatsApp/Viber gateway so it sends a payload containing at least channel, from, and text/message fields. 2. Add OpenAI API credentials for the GPT-4o-mini model. 3. Add Slack OAuth2 credentials and set the target channels for front-desk notifications and reply delivery. 4. Add Google Sheets OAuth2 credentials and update the spreadsheet/document ID and sheet tab used for logging.

View

Answer support questions from a knowledge base with OpenAI GPT-4o-mini

## Quick Overview This workflow powers a support chat experience that uses an OpenAI RAG agent with in-memory vector search to answer questions from a knowledge base, and includes a manual ingestion flow that fetches an external FAQ document, splits it into chunks, embeds it with OpenAI, and stores it for retrieval. ## How it works 1. Triggers when a new chat message is received. 2. Uses an OpenAI chat model with conversation memory to generate a support reply while following the system support guidelines. 3. Creates OpenAI embeddings for the user’s query and searches an in-memory vector knowledge base for the top matching snippets. 4. Uses the retrieved knowledge base content as a tool to ground the final answer and returns the response to the chat. 5. When run manually, fetches FAQ content from a specified URL via HTTP. 6. Splits the fetched text into chunks, converts it into documents, generates OpenAI embeddings, and inserts the vectors into the in-memory knowledge base for future queries. ## Setup 1. Add OpenAI credentials for both chat completions (GPT-4o-mini) and embeddings. 2. Update the source URL in the HTTP Request step (currently https://example.com/help-center/faq.txt) to point to your real FAQ/knowledge base content. 3. Run the manual ingestion flow once to populate the in-memory knowledge base before testing the chat trigger.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Build a Telegram Q&A bot with Linkup web search, GPT-4.1 & Mistral voice

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

Who is this for?

What it does / What problem does this solve?

How it works

How to set up

Requirements

How to take it further

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - Telegram Trigger

Block 2 - Myself?

Block 3 - AI Agent

Block 4 - Simple Memory

Block 5 - Sticky Note5

Block 6 - Get Audio File

Block 7 - Message Router

Block 8 - Sticky Note

Block 9 - Sticky Note1

Block 10 - Sticky Note2

Block 11 - OpenAI Chat Model

Block 12 - Telegram answer

Block 13 - Sticky Note6

Block 14 - Sticky Note7

Block 15 - Sticky Note8

Block 16 - Prepare message from audio

Block 17 - Prepare message from text

Block 18 - Consolidate user message

Block 19 - Sticky Note3

Block 20 - Web search

Block 21 - Mistral transcribe

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions