updated app.py

app.py

@@ -1,9 +1,10 @@
-import torch
-from transformers import GPT2LMHeadModel, GPT2TokenizerFast, GPT2Config
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, Depends
+from fastapi.security import HTTPBearer
 from pydantic import BaseModel
-from contextlib import asynccontextmanager
+from transformers import GPT2LMHeadModel, GPT2TokenizerFast, GPT2Config
+import torch
 import asyncio
+from contextlib import asynccontextmanager
 
 # FastAPI app instance
 app = FastAPI()
@@ -11,6 +12,9 @@ app = FastAPI()
 # Global model and tokenizer variables
 model, tokenizer = None, None
 
+# HTTPBearer instance for security
+bearer_scheme = HTTPBearer()
+
 # Function to load model and tokenizer
 def load_model():
     model_path = "./Ai-Text-Detector/model"
@@ -21,7 +25,7 @@ def load_model():
         config = GPT2Config.from_pretrained(model_path)
         model = GPT2LMHeadModel(config)
         model.load_state_dict(torch.load(weights_path, map_location=torch.device("cpu")))
-        model.eval()  # Set model to evaluation mode
+        model.eval() 
     except Exception as e:
         raise RuntimeError(f"Error loading model: {str(e)}")
 
@@ -61,14 +65,20 @@ def classify_text(sentence: str):
 
     return result, perplexity
 
-# POST route to analyze text
+# POST route to analyze text with Bearer token
 @app.post("/analyze")
-async def analyze_text(data: TextInput):
+async def analyze_text(data: TextInput, token: str = Depends(bearer_scheme)):
     user_input = data.text.strip()
+
     if not user_input:
         raise HTTPException(status_code=400, detail="Text cannot be empty")
+    
+    # Check if there are at least two words
+    word_count = len(user_input.split())
+    if word_count < 2:
+        raise HTTPException(status_code=400, detail="Text must contain at least two words")
+
 
-    # Run classification asynchronously to prevent blocking
     result, perplexity = await asyncio.to_thread(classify_text, user_input)
     
     return {