Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,46 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+from huggingface_hub import snapshot_download
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer
+from arabert.preprocess import ArabertPreprocessor
 import streamlit as st
+import torch
+import os
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# Download model from Hugging Face Hub (cached after first run)
+model_dir = snapshot_download(repo_id="MarioMamdouh121/arabic-qa-model")  # <-- change to your username/model
+
+# Load model
+model = AutoModelForQuestionAnswering.from_pretrained(model_dir)
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+
+arabert_prep = ArabertPreprocessor(model_name="aubmindlab/bert-base-arabertv2")
+
+# Streamlit interface
+st.title("Arabic Question Answering")
+st.write("أدخل سياقًا وسؤالًا بالعربية واحصل على الجواب.")
+
+context = st.text_area("السياق", height=150)
+question = st.text_input("السؤال")
+
+if st.button("احصل على الجواب") and context and question:
+    # Preprocess
+    context_proc = arabert_prep.preprocess(context)
+    question_proc = arabert_prep.preprocess(question)
+
+    # Tokenize
+    inputs = tokenizer(
+        question_proc,
+        context_proc,
+        return_tensors="pt",
+        truncation=True,
+        max_length=512
+    )
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    start_index = torch.argmax(outputs.start_logits)
+    end_index = torch.argmax(outputs.end_logits)
+    answer_tokens = inputs["input_ids"][0][start_index : end_index + 1]
+    answer = tokenizer.decode(answer_tokens, skip_special_tokens=True)
+
+    st.success(f"الجواب: {answer}")