ECE-BOT is available as a hosted web app at https://ece-bot-zd84.onrender.com. This guide walks you through creating an account, selecting a hardware assistant, and sending your first message. If you want to run ECE-BOT on your own infrastructure instead, see Deploy ECE-BOT.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/Kr-Yogsa/ECE-BOT/llms.txt
Use this file to discover all available pages before exploring further.
Sign up for an account
Open https://ece-bot-zd84.onrender.com in your browser and click Sign up.Enter your name, email address, and a password. Click Send OTP to receive a one-time passcode at your email address (sent via Brevo). Paste the OTP into the verification field and click Verify.Once verified, your account is created and you are redirected to the login page.Underlying API flow (for reference):
The very first user to complete signup is automatically assigned the admin role. All subsequent users are assigned the user role. Admins can later promote accounts to operator from the admin dashboard.
Log in
On the login page, enter your email and password and click Log in. ECE-BOT authenticates you and stores a JWT token in your session, which authorises all subsequent requests.A successful login returns a
token field in the response body. The web app handles this automatically.Select a hardware assistant
After logging in you land on the Chat page. The sidebar lists the available hardware assistants. Click the one that matches the machine you need support for:
Selecting an assistant sets the context for your conversation. You can switch assistants at any time by clicking a different one in the sidebar.Valid
| Assistant | Hardware type |
|---|---|
| MELFA | Mitsubishi MELFA industrial robots |
| PLC | Programmable logic controllers |
| CNC | CNC machining centres |
hardware_id values are melfa, plc, and cnc. To retrieve the full list programmatically:Send your first message
Type a question into the message field at the bottom of the chat window and press Enter or click Send. ECE-BOT processes your message using a TF-IDF intent classifier and, when confidence is below 0.75, falls back to a Gemini LLM response.Example questions to try:Pass
- “What does alarm code 10 mean on the MELFA RV-4FL?”
- “How do I reset a PLC output latch?”
- “What coolant pressure should I use for rough milling?”
session_id: null to start a new conversation. The response includes a session_id you can pass in subsequent requests to continue the same thread. The web app manages session continuity automatically.Next steps
Deploy ECE-BOT
Run ECE-BOT on your own server with Docker or Python.
Hardware chatbots
Learn how the intent model and Gemini fallback work together.
Machine monitoring
View live telemetry and trend charts from the dashboard.
API reference
Explore every endpoint with request parameters and examples.