Telegram AI Langchain bot

Build an intelligent Telegram bot that leverages the power of AI to respond to user queries and generate images on demand. This workflow connects Telegram for user interaction with OpenAI's advanced language models and DALL-E 3 for creative image generation. Users send messages to the bot via Telegram, which are then processed by an AI Agent powered by OpenAI's Chat Model and Window Buffer Memory, allowing for conversational context. If a user requests an image, the AI Agent triggers a sub-workflow that uses the DALL-E 3 Tool and an HTTP Request node to generate the image, which is then sent back to the user through Telegram. This automation is perfect for content creators looking to quickly generate visual assets, businesses offering interactive AI support, or individuals wanting a fun, AI-powered assistant directly within their Telegram chats, saving significant time and effort in content creation and customer engagement.
12 nodesmanual trigger122 views0 copiesSocial Media
TelegramOpenAI

Workflow JSON

{"id": "ax8PJlp1UDb6EGFt", "meta": {"instanceId": "fb924c73af8f703905bc09c9ee8076f48c17b596ed05b18c0ff86915ef8a7c4a"}, "name": "Telegram AI Langchain bot", "tags": [], "nodes": [{"id": "e275f31f-6a5f-4444-8bf7-6c003a8e53df", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [1100, 600], "parameters": {"model": "gpt-4-1106-preview", "options": {"temperature": 0.7, "frequencyPenalty": 0.2}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "f25a6666-ff23-4372-afd0-4920a99aab6a", "name": "Window Buffer Memory", "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow", "position": [1220, 600], "parameters": {"sessionKey": "=chat_with_{{ $('Listen for incoming events').first().json.message.chat.id }}", "contextWindowLength": 10}, "typeVersion": 1}, {"id": "96faef5d-0349-47fe-a7cf-150953490e90", "name": "Telegram", "type": "n8n-nodes-base.telegram", "onError": "continueErrorOutput", "position": [1500, 380], "parameters": {"text": "={{ $json.output }}", "chatId": "={{ $('Listen for incoming events').first().json.message.from.id }}", "additionalFields": {"parse_mode": "HTML", "appendAttribution": false}}, "credentials": {"telegramApi": {"id": "", "name": "[Your telegramApi]"}}, "typeVersion": 1.1}, {"id": "5ad43039-aaa6-43cd-9b0f-1d02f4d9c4ff", "name": "Correct errors", "type": "n8n-nodes-base.telegram", "position": [1700, 380], "parameters": {"text": "={{ $('AI Agent').item.json.output.replace(/&/g, \"&amp;\").replace(/>/g, \"&gt;\").replace(/</g, \"&lt;\").replace(/\"/g, \"&quot;\") }}", "chatId": "={{ $('Listen for incoming events').first().json.message.from.id }}", "additionalFields": {"parse_mode": "HTML", "appendAttribution": false}}, "credentials": {"telegramApi": {"id": "", "name": "[Your telegramApi]"}}, "typeVersion": 1.1}, {"id": "0349a250-966a-4064-970a-8bcfba1647ad", "name": "Execute Workflow Trigger", "type": "n8n-nodes-base.executeWorkflowTrigger", "position": [940, 900], "parameters": {}, "typeVersion": 1}, {"id": "69a45c1f-838f-49ce-9b89-75db6a8b876f", "name": "Listen for incoming events", "type": "n8n-nodes-base.telegramTrigger", "position": [940, 380], "webhookId": "322dce18-f93e-4f86-b9b1-3305519b7834", "parameters": {"updates": ["message"], "additionalFields": {}}, "credentials": {"telegramApi": {"id": "", "name": "[Your telegramApi]"}}, "typeVersion": 1}, {"id": "2f5d5f25-9870-40d6-ad42-52750e62de63", "name": "Send back an image", "type": "n8n-nodes-base.telegram", "position": [1300, 900], "parameters": {"file": "={{ $json.data[0].url }}", "chatId": "={{ $('Execute Workflow Trigger').first().json.chat_id }}", "operation": "sendPhoto", "additionalFields": {"parse_mode": "HTML"}}, "credentials": {"telegramApi": {"id": "", "name": "[Your telegramApi]"}}, "typeVersion": 1.1}, {"id": "50b43dbf-39e3-4d00-8e47-01e8c193cd1a", "name": "add response field", "type": "n8n-nodes-base.set", "position": [1480, 900], "parameters": {"fields": {"values": [{"name": "response", "stringValue": "Success"}]}, "options": {}}, "typeVersion": 3.2}, {"id": "171bee83-c8e1-4af3-9d1c-12cb6ede4943", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [900, 840], "parameters": {"width": 752.0361990950231, "height": 247.42081447963798, "content": "## Generate an image with Dall-E 3 and send it via Telegram"}, "typeVersion": 1}, {"id": "4d81d201-70bf-4c80-9689-4b65851ad770", "name": "Dall-E 3 Tool", "type": "@n8n/n8n-nodes-langchain.toolWorkflow", "position": [1360, 600], "parameters": {"name": "Draw_Dalle_image", "fields": {"values": [{"name": "chat_id", "stringValue": "={{ $('Listen for incoming events').first().json.message.chat.id }}"}]}, "workflowId": "={{ $workflow.id }}", "description": "Call this tool to request a Dall-E 3 model, when the user asks to draw something. Please send the user request for an image as an inline query string."}, "typeVersion": 1}, {"id": "39d532d3-8c96-4722-9cb0-cad92ff39e94", "name": "Generate image in Dall-E 3", "type": "n8n-nodes-base.httpRequest", "position": [1120, 900], "parameters": {"url": "https://api.openai.com/v1/images/generations", "method": "POST", "options": {}, "sendBody": true, "authentication": "predefinedCredentialType", "bodyParameters": {"parameters": [{"name": "model", "value": "dall-e-3"}, {"name": "prompt", "value": "={{ $json.query }}"}, {"name": "n", "value": 1}, {"name": "size", "value": "1024x1024"}]}, "nodeCredentialType": "openAiApi"}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 4.1}, {"id": "e5aa496d-55d3-456b-82bb-fe10a06c7338", "name": "AI Agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [1140, 380], "parameters": {"text": "={{ $json.message.text }}", "options": {"humanMessage": "TOOLS\n------\nAssistant can ask the user to use tools to look up information that may be helpful in answering the users original question. The tools the human can use are:\n\n{tools}\n\n{format_instructions}\n\nUSER'S INPUT\n--------------------\nHere is the user's input (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else):\n\n{{input}}", "systemMessage": "=You are a helpful AI assistant. You are chatting with the user named `{{ $json.message.from.first_name }}`. Today is {{ DateTime.fromISO($now).toLocaleString(DateTime.DATETIME_FULL) }}\n\nFrom time to time call a user by name (if the user name is provided). In your reply, always send a message in Telegram-supported HTML format. Here are the formatting instructions:\n1. The following tags are currently supported:\n<b>bold</b>, <strong>bold</strong>\n<i>italic</i>, <em>italic</em>\n<u>underline</u>, <ins>underline</ins>\n<s>strikethrough</s>, <strike>strikethrough</strike>, <del>strikethrough</del>\n<span class=\"tg-spoiler\">spoiler</span>, <tg-spoiler>spoiler</tg-spoiler>\n<b>bold <i>italic bold <s>italic bold strikethrough <span class=\"tg-spoiler\">italic bold strikethrough spoiler</span></s> <u>underline italic bold</u></i> bold</b>\n<a href=\"http://www.example.com/\">inline URL</a>\n<code>inline fixed-width code</code>\n<pre>pre-formatted fixed-width code block</pre>\n2. Any code that you send should be wrapped in these tags: <pre><code class=\"language-python\">pre-formatted fixed-width code block written in the Python programming language</code></pre>\nOther programming languages are supported as well.\n3. All <, > and & symbols that are not a part of a tag or an HTML entity must be replaced with the corresponding HTML entities (< with &lt;, > with &gt; and & with &amp;)\n4. If the user sends you a message starting with / sign, it means this is a Telegram bot command. For example, all users send /start command as their first message. Try to figure out what these commands mean and reply accodringly\n"}}, "typeVersion": 1.1}], "active": true, "pinData": {}, "settings": {"callerPolicy": "workflowsFromSameOwner", "executionOrder": "v1", "saveManualExecutions": true, "saveDataSuccessExecution": "all"}, "versionId": "3e9c27eb-1d2f-40bf-b284-4f6a1bece30c", "connections": {"AI Agent": {"main": [[{"node": "Telegram", "type": "main", "index": 0}]]}, "Telegram": {"main": [[], [{"node": "Correct errors", "type": "main", "index": 0}]]}, "Dall-E 3 Tool": {"ai_tool": [[{"node": "AI Agent", "type": "ai_tool", "index": 0}]]}, "OpenAI Chat Model": {"ai_languageModel": [[{"node": "AI Agent", "type": "ai_languageModel", "index": 0}]]}, "Send back an image": {"main": [[{"node": "add response field", "type": "main", "index": 0}]]}, "Window Buffer Memory": {"ai_memory": [[{"node": "AI Agent", "type": "ai_memory", "index": 0}]]}, "Execute Workflow Trigger": {"main": [[{"node": "Generate image in Dall-E 3", "type": "main", "index": 0}]]}, "Generate image in Dall-E 3": {"main": [[{"node": "Send back an image", "type": "main", "index": 0}]]}, "Listen for incoming events": {"main": [[{"node": "AI Agent", "type": "main", "index": 0}]]}}}

How to Import This Workflow

  1. 1Copy the workflow JSON above using the Copy Workflow JSON button.
  2. 2Open your n8n instance and go to Workflows.
  3. 3Click Import from JSON and paste the copied workflow.

Don't have an n8n instance? Start your free trial at n8nautomation.cloud

Related Templates

Business WhatsApp AI RAG Chatbot

Automate your business's WhatsApp customer service with an intelligent AI chatbot that leverages your Google Drive documents for accurate, context-aware responses. This powerful workflow connects incoming WhatsApp messages, triggered by a webhook, to an OpenAI-powered AI Agent, which then queries a Qdrant Vector Store populated with information from your Google Drive files. When a customer sends a message, the workflow first verifies the webhook, then routes the message to the AI Agent. The AI Agent uses an OpenAI Chat Model and a Window Buffer Memory to maintain conversation context, retrieving relevant data from your Google Drive documents via the Qdrant Vector Store, which is kept up-to-date by the Refresh collection and Create collection HTTP requests. Google Drive's Get folder and Download Files nodes extract your business's knowledge base, which is then processed by the Embeddings OpenAI, Default Data Loader, and Token Splitter nodes before being stored in Qdrant. This setup allows businesses to provide instant, personalized support 24/7, reducing response times, freeing up staff from repetitive inquiries, and ensuring consistent, accurate information delivery directly through WhatsApp. It's ideal for sales teams answering product questions, support departments resolving common issues, or marketing teams providing information about services, significantly enhancing customer satisfaction and operational efficiency.

24 nodes

Discord AI bot

Automate the intelligent routing of incoming user requests from a webhook to the appropriate Discord department with this powerful workflow. This n8n workflow leverages OpenAI's advanced natural language processing to analyze user input, then directs the request to either the User Success Dept, IT Dept, or Helpdesk Discord channel based on the identified category. Imagine a customer submitting a query through a web form; this workflow instantly understands their need and posts it in the relevant team's Discord channel, eliminating manual triage and ensuring faster response times. This solution is ideal for businesses and support teams looking to streamline their customer service operations, reduce response delays, and improve internal communication by automatically categorizing and distributing inquiries, saving significant time and effort in managing support tickets.

9 nodes

Telegram AI-bot

Build an intelligent Telegram AI-bot that responds to user messages, generates images, and provides dynamic greetings. This workflow connects Telegram as the primary communication channel with OpenAI for advanced AI capabilities, including text generation for chat responses and image creation. Users can interact with the bot to ask questions, receive personalized greetings, or request images, making it ideal for customer support, community engagement, or creative content generation. By automating AI-powered interactions directly within Telegram, this solution significantly reduces manual effort in responding to common queries, generating visual content, and maintaining an active, engaging presence, ultimately saving time and resources for businesses and individuals alike.

16 nodes

Ready to automate with n8n?

Get affordable managed n8n hosting with 24/7 support.