Create app.py

app.py

@@ -0,0 +1,50 @@
+import pdfplumber
+from transformers import AutoModelForTokenClassification, AutoTokenizer
+import torch
+import gradio as gr
+
+def load_model_and_tokenizer(model_name="dbmdz/bert-large-cased-finetuned-conll03-english"):
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForTokenClassification.from_pretrained(model_name)
+    return tokenizer, model
+
+def named_entity_recognition(text, tokenizer, model):
+    
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+    tokens = tokenizer.convert_ids_to_tokens(inputs["input_ids"][0])
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    predictions = torch.argmax(outputs.logits, dim=-1)
+    entities = [(token, model.config.id2label[prediction.item()]) for token, prediction in zip(tokens, predictions[0])]
+
+    return [entity for entity in entities if entity[1] != 'O']
+
+def extract_text_from_pdf(pdf):
+    text = ""
+    with pdfplumber.open(pdf) as pdf_file:
+        for page in pdf_file.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + " "
+    return text.strip()
+
+def process_pdf(pdf):
+    text = extract_text_from_pdf(pdf)
+    
+    if not text:
+        return "No text found in the PDF."
+        
+    entities = named_entity_recognition(text, tokenizer, model)
+    return entities if entities else "No named entities found."
+
+tokenizer, model = load_model_and_tokenizer()
+
+gr.Interface(
+    fn=process_pdf,
+    inputs=gr.File(label="Upload PDF"),
+    outputs="text",
+    title="Named Entity Recognition from PDF",
+    description="Upload a PDF file to extract text and perform Named Entity Recognition using a pre-trained BERT model."
+).launch()