Losing connection when working with vectordatabases on Windows

[LDelPinoNT]

Describe the bug

I have been working with chromadb and vicinity for RAG services and when I try to run them on Windows at certain point the connection is broken with no message. But the same code works perfectly on Ubuntu.

Any clue ? Maybe I'm missing any configuration param.
Thank you for your time!

Have you searched existing issues? 🔎

• I have searched and found no existing issues

Reproduction

Example code I'm running inside a gradio app:
MinishLab/semhash#48 (comment)

Screenshot

No response

Logs

System Info

Gradio Environment Information:
------------------------------
Operating System: Windows
gradio version: 5.16.2
gradio_client version: 1.7.1

------------------------------------------------
gradio dependencies in your environment:

aiofiles: 23.2.1
anyio: 4.8.0
audioop-lts is not installed.
fastapi: 0.115.8
ffmpy: 0.5.0
gradio-client==1.7.1 is not installed.
httpx: 0.28.1
huggingface-hub: 0.28.1
jinja2: 3.1.5
markupsafe: 2.1.5
numpy: 1.26.4
orjson: 3.10.15
packaging: 24.2
pandas: 2.2.3
pillow: 11.1.0
pydantic: 2.10.4
pydub: 0.25.1
python-multipart: 0.0.20
pyyaml: 6.0.2
ruff: 0.9.6
safehttpx: 0.1.6
semantic-version: 2.10.0
starlette: 0.45.3
tomlkit: 0.13.2
typer: 0.15.1
typing-extensions: 4.12.2
urllib3: 2.3.0
uvicorn: 0.34.0
authlib; extra == 'oauth' is not installed.
itsdangerous; extra == 'oauth' is not installed.


gradio_client dependencies in your environment:

fsspec: 2024.9.0
httpx: 0.28.1
huggingface-hub: 0.28.1
packaging: 24.2
typing-extensions: 4.12.2
websockets: 14.2

Severity

I can work around it

[abidlabs]

Hi @LDelPinoNT can you please a minimal code example, including the Gradio app, that we can use to reproduce the issue above? See: https://stackoverflow.com/help/minimal-reproducible-example

[LDelPinoNT]

import gradio as gr
from datasets import load_dataset
from semhash import SemHash

async def generate():
    # Load a dataset to deduplicate
    dataset = load_dataset("ag_news", split="train")

    # Convert the dataset to a list of dictionaries
    records = [dict(row) for row in dataset]

    # Initialize a SemHash instance with the column(s) to deduplicate
    semhash = SemHash.from_records(records=records, columns=["text"])  # it stop working at this line

    # Deduplicate the texts
    deduplicated_records  = semhash.self_deduplicate().deduplicated
    print(deduplicated_records[0])



def gradio_app():


    with gr.Blocks() as app:
            submit_button = gr.Button("Submit")


            submit_button.click(generate,
                            show_progress="full")

    return app

if __name__ == "__main__":

    app = gradio_app()
    app.queue().launch(debug=True)

Here you are @abidlabs Please keep in mind that the instalation of semhash is needed for this example. Just pip install semhash

Let me know if you need something else. And thank you for your time in advance.