NeurochainAI No-Code: Intelligent Text Parsing

This guide teaches you how to build a fully functional AI-powered message parser using NeurochainAI IaaS and n8n, all without writing code. You’ll learn to read, classify, extract, and respond to natural language messages across any platform you connect to your automation, such as Telegram, webhooks, forms, CRMs, or databases.

---

🔧 What You'll Build

Your automation will be capable of:

✅ Understanding user intent (e.g., booking, inquiry, registration) ✅ Extracting structured data (e.g., name, date, address, phone) ✅ Formatting and returning clean, readable responses ✅ (Optional) Saving structured data to Supabase or another backend

You can use this setup in:

• Support bots

• Lead forms

• Booking systems

• Feedback processors

• Multi-channel inboxes

---

🛠 Tools You’ll Need

1. n8n Automation Platform

• Host it on a VPS (like DigitalOcean, Hetzner) or use n8n cloud.

• Deployment guide: How to Set Up n8n

2. NeurochainAI IaaS Account

• Sign in to NeurochainAI Dashboard
• Generate an API Key for the model you'd like to use (e.g., Meta-Llama).

3. Optional: Supabase Project

• Create a free account at supabase.com
• Set up a table to store structured data (e.g., name, date, phone)

• Get your API credentials from Project Settings → API

4. Platform to Trigger Input

Use Telegram, Forms, or Webhooks — this guide uses Telegram for illustration, but the setup works with any source.

---

⚙️ Workflow Overview

Here’s the automation logic you’ll implement:

1. Trigger – A message is received (via Telegram, webhook, or form)

2. Field Definitions – You define what to extract (name, date, etc.)

3. Prompt Builder – Dynamically creates the AI prompt

4. AI Request – Sends the prompt to NeurochainAI

5. Response Handler – Returns a formatted response

6. (Optional) Database Insert – Stores the structured data in Supabase

---

🔩 Step-by-Step: Build Your Workflow in n8n

Step 1: Trigger Node (e.g., Telegram or Webhook)

• Add a Telegram Trigger or Webhook Trigger.

• This captures incoming messages from your users.

• For Telegram: Set up a bot via @BotFather, then paste the API token in the node.

---

Step 2: Define Fields to Extract

• Add a Set Node with key-value pairs:

Field Name → What you want to extract  
Value → Clear instruction for AI 

Field	Description
Name	The full name of the user
Age	The age in numbers only
Phone	The phone number with only digits
Email	A valid email address only, no extra text
Address	Full street address, including number

---

Step 3: Generate the Prompt (Code Node)

Paste this into a Code Node:

const fields = $json;
const instructions = [];
const fieldList = [];

for (const [key, value] of Object.entries(fields)) {
	instructions.push(`• ${key}: ${value.trim()}`);
	fieldList.push(key);
}

const telegramNode = "Telegram Trigger";
const telegramData = $node[telegramNode]?.json || {};

const messageText = telegramData.message?.text || "";
const chatId = telegramData.message?.chat?.id || "";

return [
	{
		json: {
			extractionInstructions: `Please extract the following information:\n\n${instructions.join('\n')}`,
			fieldList: fieldList.join(', '),
			message: messageText,
			chatId: chatId
		}
	}
];

This makes your automation fully dynamic — update fields in the Set Node only.

---

Step 4: Call the AI (HTTP Request Node)

Configure a HTTP Request node:

• Method: POST

• URL: https://ncmb.neurochain.io/tasks/message

• Headers:

  • Authorization: Bearer YOUR_API_KEY

  • Content-Type: application/json

• Body (JSON):

{
  "model": "Meta-Llama-3.1-8B-Instruct-Q6_K_L.gguf",
  "prompt": "You are an expert information extractor.\n\nYour task is to analyze the message below and return **only** the requested information, using the exact field names provided.\n\nThe output must follow this exact format:\nFieldName: value\nFieldName: value\n...\n\nEach result on a new line. Do not return any explanations, introductions, or additional formatting.\n\nIf any value is missing from the message, return the field name followed by an empty value (e.g., Age:).\n\n### Message to analyze:\n{{ $json.message }}\n\n### Fields to extract:\n{{ $json.extractionInstructions }}\n\n**Field names (must match exactly):**\n{{ $json.fieldList }}\n\n**Return only the extracted information.**",
  "max_tokens": 1024,
  "temperature": 0.3,
  "top_p": 0.95,
  "frequency_penalty": 0,
  "presence_penalty": 1.1
}

---

Step 5: Return the Result (e.g., Telegram or Webhook Response)

Use a Telegram Send Message or Webhook Response node to send the AI output back:

• Text:

🤖 *Extraction result*

{{ $json.choices[0].text }}

• Chat ID:

{{ $('Code').item.json.chatId }}

---

Step 6: (Optional) Save to Supabase

• Add a Supabase Insert node.

• Map fields (e.g., Name, Age, Phone) to columns in your table.

• Use it to log data, generate dashboards, or sync to other systems.

---

🧪 Test Your Automation

Send test messages like:

"Hi, I’m Lucas, 25 years old. My phone is (11) 91234-5678."

Verify if it extracts:

• Name: Lucas

• Age: 25

• Phone: [phone]

Try:

• Different sentence structures

• Missing values

• Extra irrelevant text

Adjust descriptions in the Set Node if needed.

---

🚀 Ideas to Expand

• 💬 Add multiple language support using a translation API

• 📩 Trigger follow-up emails or WhatsApp messages

• 🧾 Log interactions in Google Sheets or CRMs

• 🎨 Format responses with Markdown, HTML, or emojis

• 🔁 Add logic for fallback replies or validation

---

✅ Summary

You now have a flexible, real-time, no-code AI-powered parser that:

• Understands natural language

• Extracts structured data

• Works across platforms (Telegram, Web, Forms, etc.)

• Can respond, store, or act on the results

All powered by NeurochainAI IaaS and built with n8n, without touching a single line of backend code.

---

📦 Download the Template

🎁 Import the Full n8n Workflow Template Pre-configured with Telegram, AI prompt, and response nodes.

---

📣 Share What You Built

If you’ve adapted this workflow for bookings, support, lead gen, or something unique... show it off! Join the conversation in our community on Telegram or Discord, and inspire others with your automation.