Create app.py

app.py

@@ -0,0 +1,49 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from transformers import BartTokenizer, BartForConditionalGeneration
+import torch
+
+# Initialize the FastAPI app
+app = FastAPI()
+
+# Load the fine-tuned BART model and tokenizer from the local directory
+MODEL_DIR = './BART model small/model'
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = BartTokenizer.from_pretrained(MODEL_DIR)
+model = BartForConditionalGeneration.from_pretrained(MODEL_DIR).to(device)
+
+# Define a request model for the API input
+class Article(BaseModel):
+    text: str
+
+# API Endpoint for summarization
+@app.post("/summarize")
+async def summarize(article: Article):
+    try:
+        # Tokenize the input article
+        inputs = tokenizer(
+            article.text,
+            return_tensors="pt",
+            max_length=1024,
+            truncation=True
+        ).to(device)
+
+        # Generate the summary
+        summary_ids = model.generate(
+            inputs['input_ids'],
+            attention_mask=inputs['attention_mask'],
+            max_length=150,  # Set maximum length for the summary
+            min_length=30,   # Set minimum length for the summary
+            num_beams=4,     # Use beam search to generate the summary
+            early_stopping=True
+        )
+
+        # Decode the summary
+        summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+
+        # Return the summary in the response
+        return {"summary": summary}
+    
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))