StackFlow AI Platform
Devices & Quick Start
LLM630 Compute Kit
Models
Qwen3
DeepSeek-R1
Applications
CV Vision Application
Vision Language Model (VLM)
Large Language Model (LLM)
Module LLM - LLM Chat
This example demonstrates how to use the M5ModuleLLM library on the Arduino platform to implement generative dialogue using an LLM. Communication is done via USB serial, where you can send questions to the module and receive responses through a serial terminal.
Preparation
Refer to Module LLM Arduino Quick Start to complete the basic setup and install the M5ModuleLLM driver library.
Refer to Module LLM Software Package Update Guide to install the following model packages:
apt install llm-llmapt install llm-model-qwen2.5-0.5b-prefill-20e- Required hardware for this example:
LLM CoreS3
/*
* SPDX-FileCopyrightText: 2024 M5Stack Technology CO LTD
*
* SPDX-License-Identifier: MIT
*/
#include <Arduino.h>
#include <M5Unified.h>
#include <M5ModuleLLM.h>
#define CommSerialPort Serial
M5ModuleLLM module_llm;
String llm_work_id;
String received_question;
bool question_ok;
void setup()
{
M5.begin();
M5.Display.setTextSize(2);
M5.Display.setTextScroll(true);
/* Init usb serial */
CommSerialPort.begin(115200);
/* Init module serial port */
int rxd = M5.getPin(m5::pin_name_t::port_c_rxd);
int txd = M5.getPin(m5::pin_name_t::port_c_txd);
Serial2.begin(115200, SERIAL_8N1, rxd, txd);
/* Init module */
module_llm.begin(&Serial2);
/* Make sure module is connected */
M5.Display.printf(">> Check ModuleLLM connection..\n");
while (1) {
if (module_llm.checkConnection()) {
break;
}
}
/* Reset ModuleLLM */
M5.Display.printf(">> Reset ModuleLLM..\n");
module_llm.sys.reset();
/* Setup LLM module and save returned work id */
M5.Display.printf(">> Setup llm..\n");
m5_module_llm::ApiLlmSetupConfig_t llm_config;
llm_config.max_token_len = 1023;
llm_work_id = module_llm.llm.setup(llm_config);
M5.Display.printf(">> Setup finish\n");
M5.Display.printf(">> Try send your question via usb serial port\n");
M5.Display.setTextColor(TFT_GREEN);
M5.Display.printf("e.g. \nHi, What's your name?\n");
M5.Display.printf("(end with CRLF \\r\\n)\n\n");
}
void loop()
{
/* Check comm serial port and get received question */
question_ok = false;
if (CommSerialPort.available()) {
while (CommSerialPort.available()) {
char in_char = (char)CommSerialPort.read();
received_question += in_char;
/* Check if question finish */
if (received_question.endsWith("\r\n")) {
received_question.remove(received_question.length() - 2);
question_ok = true;
break;
}
}
}
/* If question is ready */
if (question_ok) {
M5.Display.setTextColor(TFT_GREEN);
M5.Display.printf("<< %s\n", received_question.c_str());
M5.Display.setTextColor(TFT_YELLOW);
M5.Display.printf(">> ");
CommSerialPort.printf("<< \"%s\"\n", received_question.c_str());
CommSerialPort.print(">> ");
/* Push question to LLM module and wait inference result */
module_llm.llm.inferenceAndWaitResult(llm_work_id, received_question.c_str(), [](String& result) {
/* Show result on screen and usb serial */
M5.Display.printf("%s", result.c_str());
CommSerialPort.print(result);
});
/* Clear for next question */
received_question.clear();
M5.Display.println();
CommSerialPort.println();
}
delay(20);
}- Upload the code to CoreS3.
- Open the Serial Monitor in the Arduino IDE, set the baud rate to 115200, and set the line ending to "\r\n". Type your question into the serial monitor and press Enter. The Module LLM will process the input and return a response.
