Core Module Testing Tools

1. Course Content

• muto-llm provides minimal test programs for testing the core functional modules of a large model, used to quickly locate problems in abnormal situations.

2. Start the Dify service

xxxxxxxxxx
bringup_dify

3. Enter the test tool path

xxxxxxxxxx
cd /root/muto-llm-2.0/test
ls

• Test tools are as follows:

4. Test if the robot can access Dify normally

• When the program displays that the model service is unavailable, and it is unclear whether the robot's inability to access Dify is due to an incorrect network address, you can test this:

xxxxxxxxxx
python3 test_dify_connection.py 

If the robot displays the following information normally, it proves that the robot is connected to Dify normally. Otherwise, it may be that Dify is not running or the Dify program has crashed and needs to be restarted.

5. Online Voice Service for International Users

5.1 iFlytek Speech Recognition Service

• If online speech recognition encounters errors, you can test the Bailian speech recognition service separately.

xxxxxxxxxx
python test_XunfeiASR.py

• After running, it will perform speech recognition tests on the preset test audio.

5.2 iFlytek Speech Synthesis Service

• If errors occur during online speech synthesis, you can test Bailian's speech recognition service separately.

xxxxxxxxxx
python test_XunfeiTTS.py

After running, it will first perform speech synthesis on the default text, and then play the corresponding audio.