search

urchade / GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024
https://arxiv.org/abs/2311.08526
Apache License 2.0
1.48k stars 127 forks source link

[Urgent] Oh no. Error running app in Streamlit #61

Closed huseyincenik closed 7 months ago

huseyincenik commented 7 months ago

I developed a streamlit ner application with the gliner from Hugging Face. Even though the application runs locally, streamlit gives an error "Oh no.

Error running app. “If this keeps happening, please contact support.” What should I do about this? Where am I making a mistake?

My code blocks: streamlit_ner_with_gliner/app.py at main · huseyincenik/streamlit_ner_with_gliner · GitHub

My Streamlit App: https://ner-with-gliner.streamlit.app/

image image

urchade commented 7 months ago

Hi @huseyincenik

is it possible to have more detailled error message ? I am not familiar with streamlit

huseyincenik commented 7 months ago

Hi @huseyincenik

is it possible to have more detailled error message ? I am not familiar with streamlit

Hello, of course the error is as follows: "❗️ The service has encountered an error while checking the health of the Streamlit app: Get "http://localhost:8501/script-health-check": EOF" I'm also adding log records.

logs-huseyincenik-streamlit_ner_with_gliner-main-app.py-2024-04-11T07_30_10.480Z.txt

tomaarsen commented 7 months ago

I can't find anything in the logs or provided information that indicates that something broke on the GLiNER side:

[06:37:33] ❗️ The service has encountered an error while checking the health of the Streamlit app: Get "http://localhost:8501/script-health-check": EOF
[06:39:06] ❗️ Streamlit server consistently failed status checks
[06:39:06] ❗️ Please fix the errors, push an update to the git repo, or reboot the app.
huseyincenik commented 7 months ago

@tomaarsen @urchade Thanks. The problem was caused by streamlit. It was fixed after making changes. Would you like to try the Streamlit app?

🚀 Thrilled to introduce our new NER (Named Entity Recognition) application powered by Gliner! 🛠️ Easily extract entities from your data with just a few clicks using GLiNER models. Choose from a variety of models like Gliner Multi-v2.1, Gliner Medium-v2.1, Gliner Small-v2.1, and Gliner Large-v2.1. Upload your dataset, define new columns with NER labels (separated by commas for multiple labels in one column), set thresholds for precision, process the data, and download the results as an Excel file! Try it out now!

🔗 App: https://lnkd.in/dGRBwRyF ✨ 🔗 Github: https://lnkd.in/d3EQhKUx ✨