Create app.py

app.py

@@ -0,0 +1,43 @@
+from transformers import pipeline
+import gradio as gr
+import re
+
+# Load NER pipeline
+ner = pipeline("ner", model="dslim/bert-base-NER", aggregation_strategy="simple")
+
+# Custom sentence splitting function
+def split_sentences(text):
+    # Avoid splitting after abbreviations
+    protected = r"\b(?:[A-Z]\.|D\.C\.|U\.S\.|Mr\.|Mrs\.|Dr\.|Jr\.|Sr\.|vs\.|Inc\.|Ltd\.|etc\.)"
+    
+    # Split on ., ?, ! followed by a space + capital/lowercase/’ (not part of abbreviation)
+    pattern = re.compile(rf"(?<!{protected})(?<=[.!?])\s+(?=[A-Z'‘“a-z])")
+    sentences = re.split(pattern, text.strip())
+    return [s.strip() for s in sentences if s.strip()]
+
+# API function
+def analyze_text(text):
+    sentences = split_sentences(text)
+    results = []
+
+    for i, sentence in enumerate(sentences, start=1):
+        entities = ner(sentence)
+        results.append({
+            "sentence_number": i,
+            "sentence": sentence,
+            "entities": entities
+        })
+
+    return {"sentences": results, "total_sentences": len(sentences)}
+
+# Gradio interface (API-style)
+demo = gr.Interface(
+    fn=analyze_text,
+    inputs=gr.Textbox(label="Input Text", lines=6, placeholder="Paste your article..."),
+    outputs=gr.JSON(label="NER + Sentence Output"),
+    title="Sentence Splitter + NER API",
+    description="Splits text into sentences (with abbreviation protection) and runs NER using dslim/bert-base-NER."
+)
+
+if __name__ == "__main__":
+    demo.launch()