Follow the instruction step by step, but couldn't run my local LLM successfully.

[GregChiang0201]

I think the program has no problem, and everything can work properly(I already used print to check every crucial parts), while I ran python3 run_localGPT.py, it can show Enter a query: too, but it I enter anything(except exit), my program will stuck and no response as follow, and I always need to use crtl+C to shut it down.

2024-07-18 18:32:05,980 - INFO - run_localGPT.py:145 - LLM pipeline loaded.
2024-07-18 18:32:05,985 - INFO - run_localGPT.py:167 - Retrieval-based QA pipeline created.
2024-07-18 18:32:05,985 - INFO - run_localGPT.py:257 - Model is ready for queries. Enter 'exit' to quit the program.

Enter a query: explain pdf to me
2024-07-18 18:32:12,415 - INFO - run_localGPT.py:268 - Processing query: explain pdf to me
^C
Aborted!

[GregChiang0201]

The program has no problem, is device issue, I only access 1 CPU core to run the program, if rise the number of CPU will be fine.