38210 segmentation fault

[Lionardo]

Is there a way to fix this? I am asking here because I couldn't find any other source.

I am using the simple example and when I run this code I am getting the error:

38328 segmentation fault pipenv run python3 embedding.py

machine:
Monterey version: 12.6.3
MacBook Pro (14-inch, 2021)
chip Apple M1 Max

example code:

from txtai.embeddings import Embeddings
data = ["US tops 5 million confirmed virus cases",
        "Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg",
        "Beijing mobilises invasion craft along coast as Taiwan tensions escalate",
        "The National Park Service warns against sacrificing slower friends in a bear attack",
        "Maine man wins $1M from $25 lottery ticket",
        "Make huge profits without work, earn up to $100,000 a day"]

# Create embeddings index with content enabled. The default behavior is to only store indexed vectors.
embeddings = Embeddings({"path": "sentence-transformers/nli-mpnet-base-v2", "content": True})

# Create an index for the list of text
embeddings.index([(uid, text, None) for uid, text in enumerate(data)])

# Run a search
embeddings.search("feel good story", 1)

[davidmezzetti]

Hi @Lionardo, thank you for posting the issue.

Unfortunately, I don't have a great solution on why the latest version of PyTorch have this issue on macOS. The current workarounds can be found in #377

[davidmezzetti]

Closing this due to inactivity. #377 fixed a similar issue by setting the env variable OMP_NUM_THREADS=1

[avi-cenna]

A similar issue happened for me. I'm on an Intel Mac. Setting export OMP_NUM_THREADS=1 in ~/.zshrc fixed the issue for me.