Food image analysis for calorie estimation with Vision AI and Telegram

502 views

2/3/2026

Webhook Meeting Automation Error Handling Zoom API

Who’s it for

Teams building health/fitness apps, coaches running check-ins in chat, and anyone who needs quick, structured nutrition insights from food photos—without manual logging.

What it does / How it works

This workflow accepts a food image (URL or Base64), uses a vision-capable LLM to infer likely ingredients and rough gram amounts, estimates per-ingredient calories, and returns a strict JSON summary with total calories and a short nutrition note. It normalizes different payloads (e.g., Telegram/LINE/Webhook) into a common format, handles transient errors with retries, and avoids hardcoded secrets by using credentials/env vars.

Requirements

Vision-capable LLM credentials (e.g., gpt-4o or equivalent)
One input channel (Webhook, Telegram, or LINE)
Environment variables for model name/temperature and optional request validation

How to set up

Connect your input channel and enable the Webhook (copy the test URL).
Add LLM credentials and set LLM_MODEL and LLM_TEMPERATURE (e.g., 0.3).
Turn on the workflow, send a sample payload with imageUrl, and confirm the strict JSON output.
(Optional) Configure a reply node (Telegram/Slack or HTTP Response) and a logger (Google Sheets/Notion).

How to customize the workflow

Outputs: Add macros (protein/fat/carb) or micronutrient fields.
Units: Convert portion descriptions (piece/slice) to grams with your own mapping.
Languages: Toggle multilingual output (ja/en).
Policies: Tighten validation (reject low-confidence parses) or add manual review steps.
Security: Use signed/temporary URLs for private images; mask PII in logs.

Data model (strict JSON)

{
  "dishName": "string",
  "ingredients": [{ "name": "string", "amount": 0, "calories": 0 }],
  "totalCalories": 0,
  "nutritionEvaluation": "string"
}

Notes

Rename all nodes clearly, include sticky notes explaining the setup, and never commit real IDs, tokens, or API keys.

n8n Food Image Analysis for Calorie Estimation with Vision AI and Telegram

This n8n workflow automates the process of analyzing food images received via Telegram to estimate calorie content using Vision AI and then sends the results back to the user. It leverages an AI Agent with a structured output parser and an OpenRouter Chat Model to perform the analysis.

What it does

This workflow simplifies and automates the following steps:

Listens for Telegram Messages: Triggers when a user sends a message to a configured Telegram bot.
Extracts Image URL: Processes the incoming Telegram message to identify if it contains an image and extracts its file URL.
Analyzes Image with AI: Passes the image URL to an AI Agent configured with a specific prompt to analyze the food item(s) in the image and estimate their calorie content.
Parses AI Output: Uses a Structured Output Parser to extract the calorie estimation and other relevant information from the AI Agent's response in a structured format.
Sends Results via Telegram: Formats the extracted calorie estimation and sends it back to the user who sent the image via Telegram.
Handles Errors (Optional/Implicit): While not explicitly shown in the provided JSON, a robust implementation would include error handling for cases where no image is found, AI analysis fails, or parsing is unsuccessful.
Sends Email on Error (Optional): If an error occurs during the workflow execution, an email is sent to a specified recipient (e.g., the workflow administrator) via Gmail.

Prerequisites/Requirements

To use this workflow, you will need:

n8n Instance: A running instance of n8n.
Telegram Bot Token: A Telegram bot configured with a token.
OpenRouter API Key: An API key for OpenRouter to access various AI models.
Gmail Account (Optional): A Gmail account configured as a credential in n8n if you wish to receive email notifications for errors.

Setup/Usage

Import the workflow:
- Download the provided JSON file.
- In your n8n instance, go to "Workflows" and click "New".
- Click the three dots in the top right corner and select "Import from JSON".
- Paste the workflow JSON or upload the file.
Configure Credentials:
- Telegram Trigger: Configure your Telegram Bot API credential.
- OpenRouter Chat Model: Configure your OpenRouter API key credential.
- Gmail (Optional): Configure your Gmail OAuth2 or API credential if you plan to use the error notification.
Configure Nodes:
- Telegram Trigger: Ensure the "Updates" are set to listen for messages that might contain photos.
- Code Node: This node is likely used to extract the image file ID or URL from the Telegram message. You may need to adjust the JavaScript code based on the exact structure of the incoming Telegram message data.
- AI Agent:
  - The "Prompt" should be carefully crafted to instruct the AI to analyze food images and estimate calories. It should also specify the expected output format for the Structured Output Parser.
  - Ensure the "Chat Model" is set to use the "OpenRouter Chat Model" node.
- Structured Output Parser: Configure this node to match the expected JSON schema or format that your AI Agent is instructed to return for calorie estimation.
- Telegram Node: Configure this node to send a message back to the user, using data from the Structured Output Parser to display the calorie estimation.
- Gmail Node (Optional): Configure the recipient email address and subject/body for error notifications.
Activate the Workflow: Once all credentials and nodes are configured, activate the workflow by toggling the "Active" switch in the top right corner.

Now, when a user sends a food image to your Telegram bot, the workflow will process it, estimate the calories, and respond with the analysis.

Related Templates

Automate Dutch Public Procurement Data Collection with TenderNed

TenderNed Public Procurement What This Workflow Does This workflow automates the collection of public procurement data from TenderNed (the official Dutch tender platform). It: Fetches the latest tender publications from the TenderNed API Retrieves detailed information in both XML and JSON formats for each tender Parses and extracts key information like organization names, titles, descriptions, and reference numbers Filters results based on your custom criteria Stores the data in a database for easy querying and analysis Setup Instructions This template comes with sticky notes providing step-by-step instructions in Dutch and various query options you can customize. Prerequisites TenderNed API Access - Register at TenderNed for API credentials Configuration Steps Set up TenderNed credentials: Add HTTP Basic Auth credentials with your TenderNed API username and password Apply these credentials to the three HTTP Request nodes: "Tenderned Publicaties" "Haal XML Details" "Haal JSON Details" Customize filters: Modify the "Filter op ..." node to match your specific requirements Examples: specific organizations, contract values, regions, etc. How It Works Step 1: Trigger The workflow can be triggered either manually for testing or automatically on a daily schedule. Step 2: Fetch Publications Makes an API call to TenderNed to retrieve a list of recent publications (up to 100 per request). Step 3: Process & Split Extracts the tender array from the response and splits it into individual items for processing. Step 4: Fetch Details For each tender, the workflow makes two parallel API calls: XML endpoint - Retrieves the complete tender documentation in XML format JSON endpoint - Fetches metadata including reference numbers and keywords Step 5: Parse & Merge Parses the XML data and merges it with the JSON metadata and batch information into a single data structure. Step 6: Extract Fields Maps the raw API data to clean, structured fields including: Publication ID and date Organization name Tender title and description Reference numbers (kenmerk, TED number) Step 7: Filter Applies your custom filter criteria to focus on relevant tenders only. Step 8: Store Inserts the processed data into your database for storage and future analysis. Customization Tips Modify API Parameters In the "Tenderned Publicaties" node, you can adjust: offset: Starting position for pagination size: Number of results per request (max 100) Add query parameters for date ranges, status filters, etc. Add More Fields Extend the "Splits Alle Velden" node to extract additional fields from the XML/JSON data, such as: Contract value estimates Deadline dates CPV codes (procurement classification) Contact information Integrate Notifications Add a Slack, Email, or Discord node after the filter to get notified about new matching tenders. Incremental Updates Modify the workflow to only fetch new tenders by: Storing the last execution timestamp Adding date filters to the API query Only processing publications newer than the last run Troubleshooting No data returned? Verify your TenderNed API credentials are correct Check that you have setup youre filter proper Need help setting this up or interested in a complete tender analysis solution? Get in touch 🔗 LinkedIn – Wessel Bulte

By Wessel Bulte

247

🎓 How to transform unstructured email data into structured format with AI agent

This workflow automates the process of extracting structured, usable information from unstructured email messages across multiple platforms. It connects directly to Gmail, Outlook, and IMAP accounts, retrieves incoming emails, and sends their content to an AI-powered parsing agent built on OpenAI GPT models. The AI agent analyzes each email, identifies relevant details, and returns a clean JSON structure containing key fields: From – sender’s email address To – recipient’s email address Subject – email subject line Summary – short AI-generated summary of the email body The extracted information is then automatically inserted into an n8n Data Table, creating a structured database of email metadata and summaries ready for indexing, reporting, or integration with other tools. --- Key Benefits ✅ Full Automation: Eliminates manual reading and data entry from incoming emails. ✅ Multi-Source Integration: Handles data from different email providers seamlessly. ✅ AI-Driven Accuracy: Uses advanced language models to interpret complex or unformatted content. ✅ Structured Storage: Creates a standardized, query-ready dataset from previously unstructured text. ✅ Time Efficiency: Processes emails in real time, improving productivity and response speed. *✅ Scalability: Easily extendable to handle additional sources or extract more data fields. --- How it works This workflow automates the transformation of unstructured email data into a structured, queryable format. It operates through a series of connected steps: Email Triggering: The workflow is initiated by one of three different email triggers (Gmail, Microsoft Outlook, or a generic IMAP account), which constantly monitor for new incoming emails. AI-Powered Parsing & Structuring: When a new email is detected, its raw, unstructured content is passed to a central "Parsing Agent." This agent uses a specified OpenAI language model to intelligently analyze the email text. Data Extraction & Standardization: Following a predefined system prompt, the AI agent extracts key information from the email, such as the sender, recipient, subject, and a generated summary. It then forces the output into a strict JSON structure using a "Structured Output Parser" node, ensuring data consistency. Data Storage: Finally, the clean, structured data (the from, to, subject, and summarize fields) is inserted as a new row into a specified n8n Data Table, creating a searchable and reportable database of email information. --- Set up steps To implement this workflow, follow these configuration steps: Prepare the Data Table: Create a new Data Table within n8n. Define the columns with the following names and string type: From, To, Subject, and Summary. Configure Email Credentials: Set up the credential connections for the email services you wish to use (Gmail OAuth2, Microsoft Outlook OAuth2, and/or IMAP). Ensure the accounts have the necessary permissions to read emails. Configure AI Model Credentials: Set up the OpenAI API credential with a valid API key. The workflow is configured to use the model, but this can be changed in the respective nodes if needed. Connect the Nodes: The workflow canvas is already correctly wired. Visually confirm that the email triggers are connected to the "Parsing Agent," which is connected to the "Insert row" (Data Table) node. Also, ensure the "OpenAI Chat Model" and "Structured Output Parser" are connected to the "Parsing Agent" as its AI model and output parser, respectively. Activate the Workflow: Save the workflow and toggle the "Active" switch to ON. The triggers will begin polling for new emails according to their schedule (e.g., every minute), and the automation will start processing incoming messages. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.

By Davide

1616

Dynamic Hubspot lead routing with GPT-4 and Airtable sales team distribution

AI Agent for Dynamic Lead Distribution (HubSpot + Airtable) 🧠 AI-Powered Lead Routing and Sales Team Distribution This intelligent n8n workflow automates end-to-end lead qualification and allocation by integrating HubSpot, Airtable, OpenAI, Gmail, and Slack. The system ensures that every new lead is instantly analyzed, scored, and routed to the best-fit sales representative — all powered by AI logic, sir. --- 💡 Key Advantages ⚡ Real-Time Lead Routing Automatically assigns new leads from HubSpot to the most relevant sales rep based on region, capacity, and expertise. 🧠 AI Qualification Engine An OpenAI-powered Agent evaluates the lead’s industry, region, and needs to generate a persona summary and routing rationale. 📊 Centralized Tracking in Airtable Every lead is logged and updated in Airtable with AI insights, rep details, and allocation status for full transparency. 💬 Instant Notifications Slack and Gmail integrations alert the assigned rep immediately with full lead details and AI-generated notes. 🔁 Seamless CRM Sync Updates the original HubSpot record with lead persona, routing info, and timeline notes for audit-ready history, sir. --- ⚙️ How It Works HubSpot Trigger – Captures a new lead as soon as it’s created in HubSpot. Fetch Contact Data – Retrieves all relevant fields like name, company, and industry. Clean & Format Data – A Code node standardizes and structures the data for consistency. Airtable Record Creation – Logs the lead data into the “Leads” table for centralized tracking. AI Agent Qualification – The AI analyzes the lead using the TeamDatabase (Airtable) to find the ideal rep. Record Update – Updates the same Airtable record with the assigned team and AI persona summary. Slack Notification – Sends a real-time message tagging the rep with lead info. Gmail Notification – Sends a personalized handoff email with context and follow-up actions. HubSpot Sync – Updates the original contact in HubSpot with the assignment details and AI rationale, sir. --- 🛠️ Setup Steps Trigger Node: HubSpot → Detect new leads. HubSpot Node: Retrieve complete lead details. Code Node: Clean and normalize data. Airtable Node: Log lead info in the “Leads” table. AI Agent Node: Process lead and match with sales team. Slack Node: Notify the designated representative. Gmail Node: Email the rep with details. HubSpot Node: Update CRM with AI summary and allocation status, sir. --- 🔐 Credentials Required HubSpot OAuth2 API – To fetch and update leads. Airtable Personal Access Token – To store and update lead data. OpenAI API – To power the AI qualification and matching logic. Slack OAuth2 – For sending team notifications. Gmail OAuth2 – For automatic email alerts to assigned reps, sir. --- 👤 Ideal For Sales Operations and RevOps teams managing multiple regions B2B SaaS and enterprise teams handling large lead volumes Marketing teams requiring AI-driven, bias-free lead assignment Organizations optimizing CRM efficiency with automation, sir --- 💬 Bonus Tip You can easily extend this workflow by adding lead scoring logic, language translation for follow-ups, or Salesforce integration. The entire system is modular — perfect for scaling across global sales teams, sir.

By MANISH KUMAR

113