Create app.py

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+
+# Load BioBERT model for NER
+model_name = "d4data/biobert_ner"  # pretrained BioBERT for biomedical NER
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForTokenClassification.from_pretrained(model_name)
+
+# Create a NER pipeline
+ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
+
+# Inference function
+def bio_ner(text):
+    ner_results = ner_pipeline(text)
+    annotated = ""
+    last_end = 0
+    for ent in ner_results:
+        start, end, label = ent['start'], ent['end'], ent['entity_group']
+        annotated += text[last_end:start]
+        annotated += f"[{text[start:end]}]({label})"
+        last_end = end
+    annotated += text[last_end:]
+    return annotated
+
+# Gradio interface
+gr.Interface(
+    fn=bio_ner,
+    inputs=gr.Textbox(lines=5, placeholder="Enter biomedical text here..."),
+    outputs="text",
+    title="🧬 BioBERT NER",
+    description="Uses BioBERT to perform Named Entity Recognition on biomedical text."
+).launch()