Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,45 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# 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])),
-    ))
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import re
+
+# ----------------------------
+# Загрузка модели
+# ----------------------------
+model_name = "Waris01/google-t5-finetuning-text-summarization"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+# ----------------------------
+# Очистка текста
+# ----------------------------
+def clean_text(text):
+    text = re.sub(r'\s+', ' ', text)
+    text = re.sub(r'\[[0-9]+\]', '', text)
+    text = re.sub(r'http\S+', '', text)
+    return text.strip()
+
+# ----------------------------
+# Генерация суммаризации
+# ----------------------------
+def summarize(text):
+    cleaned = clean_text(text)
+    inputs = tokenizer("summarize: " + cleaned, return_tensors="pt", truncation=True, max_length=512)
+    summary_ids = model.generate(inputs["input_ids"], max_length=150, num_beams=2, early_stopping=True)
+    return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+
+# ----------------------------
+# Интерфейс Streamlit
+# ----------------------------
+st.title("🧬 Scientific Article Summarizer")
+st.write("Вставьте текст статьи и получите краткую аннотацию.")
+
+input_text = st.text_area("Введите текст статьи:", height=250)
+
+if st.button("Суммаризировать"):
+    if len(input_text.strip()) == 0:
+        st.error("Введите текст!")
+    else:
+        with st.spinner("Генерация суммаризации..."):
+            summary = summarize(input_text)
+        st.subheader("📘 Краткое содержание:")
+        st.write(summary)