Telegram Image to Text with Groq LLaVA

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "id": "aDPpPIaeM7zfUCdJ",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "GROQ LLAVA V1.5 7B",
  "tags": [],
  "nodes": [
    {
      "id": "d831f75e-0385-482c-b2d5-e8da58216f4c",
      "name": "Telegram Trigger",
      "type": "n8n-nodes-base.telegramTrigger",
      "position": [
        540,
        280
      ],
      "parameters": {
        "updates": [
          "*"
        ],
        "additionalFields": {}
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "0fd97c36-3e3d-45a3-929d-975d17baf1fb",
      "name": "Telegram send the text",
      "type": "n8n-nodes-base.telegram",
      "position": [
        1640,
        280
      ],
      "parameters": {
        "text": "={{ $json.choices[0].message.content }}",
        "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "bd39b29f-e128-4891-bc6a-3eb75de29182",
      "name": "Get only the text",
      "type": "n8n-nodes-base.set",
      "position": [
        1420,
        280
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "52a2f0d9-3137-4f6e-a2c1-8285694f6159",
              "name": "choices[0].message.content",
              "type": "string",
              "value": "={{ $json.choices[0].message.content }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "f1a96061-6d81-4d21-adac-dab475a00eb1",
      "name": "HTTP Request GROQ LLAVA",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1200,
        280
      ],
      "parameters": {
        "url": "https://api.groq.com/openai/v1/chat/completions",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"Describe this image in great detail\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"data:image/jpeg;base64,{{ $json.data }}\"\n          }\n        }\n      ]\n    }\n  ],\n  \"model\": \"llava-v1.5-7b-4096-preview\"\n}",
        "sendBody": true,
        "sendHeaders": true,
        "specifyBody": "json",
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Bearer YOUR_TOKEN_HERE"
            },
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "ab6be84f-06df-4f6f-b7fc-e328bc854116",
      "name": "convert the image file to base64",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        980,
        280
      ],
      "parameters": {
        "options": {},
        "operation": "binaryToPropery"
      },
      "typeVersion": 1
    },
    {
      "id": "888397d6-4fd1-4e9b-852e-1731159df4f5",
      "name": "Receive the File",
      "type": "n8n-nodes-base.telegram",
      "position": [
        760,
        280
      ],
      "parameters": {
        "fileId": "={{ $json.message.photo[0].file_id }}",
        "resource": "file"
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "7d117dd2-bd9f-4930-a727-8bff38cb5b72",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        440,
        -16.000000000000057
      ],
      "parameters": {
        "color": 4,
        "width": 691.428571428571,
        "height": 521.142857142858,
        "content": "## Set Up\n\nOpen the Telegram app and search for the BotFather user (@BotFather)\nStart a chat with the BotFather\nType /newbot to create a new bot\nFollow the prompts to name your bot and get a unique API token\nSave your access token and username\n## Start Using\nOnce you set the Bot, you can send the image. \nThe second node get the image and send to the next node to be convert in base64, that is required by Groq in the documentation.\n\n [Groq docs](https://console.groq.com/docs/vision)"
      },
      "typeVersion": 1
    },
    {
      "id": "a935a3a6-85cd-43c6-aa0a-a37f6c40372a",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1160,
        -20
      ],
      "parameters": {
        "width": 650.2857142857147,
        "height": 524.571428571429,
        "content": "## Using GROQ API\n\nNow we send the image in base64 to the API and get the description of the image."
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "9253a6c2-d5d0-444a-9035-8fd562d54628",
  "connections": {
    "Receive the File": {
      "main": [
        [
          {
            "node": "convert the image file to base64",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Telegram Trigger": {
      "main": [
        [
          {
            "node": "Receive the File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get only the text": {
      "main": [
        [
          {
            "node": "Telegram send the text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "HTTP Request GROQ LLAVA": {
      "main": [
        [
          {
            "node": "Get only the text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "convert the image file to base64": {
      "main": [
        [
          {
            "node": "HTTP Request GROQ LLAVA",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• telegramApi

About this workflow

This template uses GROQ LLAVA V1.5 7B API that offers fast inference for multimodal models with vision capabilities for understanding and interpreting visual data from images. .

Source: https://n8n.io/workflows/2437/ — original creator credit. Request a take-down →

More Slack & Telegram workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.