Update app.py

app.py

@@ -1,150 +1,161 @@
-from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi import FastAPI, HTTPException, File, UploadFile
 from fastapi.middleware.cors import CORSMiddleware
-import tensorflow as tf
-import numpy as np
-from PIL import Image
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer, util
+import google.generativeai as genai
+import pdfplumber
+import pickle
 import io
-import uvicorn
-import tempfile
-import cv2
+import os
+from datetime import datetime
 
+# ================= APP =================
+app = FastAPI(title="Jimma University Plagiarism API")
 
-# Initialize FastAPI app
-app = FastAPI(title="Plant Disease Detection API", version="1.0.0")
-
-# Add CORS middleware to allow requests from your frontend
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=["*"],  # In production, replace with your frontend URL
-    allow_credentials=True,
+    allow_origins=["*"],
     allow_methods=["*"],
     allow_headers=["*"],
 )
 
-# Load your model
-try:
-    model = tf.keras.models.load_model("trained_modela.keras")
-except Exception as e:
-    raise RuntimeError(f"Failed to load model: {e}")
-
-# Define your class names (update with your actual classes)
-class_name = ['Apple___Apple_scab',
-    'Apple___Black_rot',
-    'Apple___Cedar_apple_rust',
-    'Apple___healthy',
-    'Blueberry___healthy',
-    'Cherry_(including_sour)___Powdery_mildew',
-    'Cherry_(including_sour)___healthy',
-    'Corn_(maize)___Cercospora_leaf_spot Gray_leaf_spot',
-    'Corn_(maize)___Common_rust_',
-    'Corn_(maize)___Northern_Leaf_Blight',
-    'Corn_(maize)___healthy',
-    'Grape___Black_rot',
-    'Grape___Esca_(Black_Measles)',
-    'Grape___Leaf_blight_(Isariopsis_Leaf_Spot)',
-    'Grape___healthy',
-    'Orange___Haunglongbing_(Citrus_greening)',
-    'Peach___Bacterial_spot',
-    'Peach___healthy',
-    'Pepper,_bell___Bacterial_spot',
-    'Pepper,_bell___healthy',
-    'Potato___Early_blight',
-    'Potato___Late_blight',
-    'Potato___healthy',
-    'Raspberry___healthy',
-    'Soybean___healthy',
-    'Squash___Powdery_mildew',
-    'Strawberry___Leaf_scorch',
-    'Strawberry___healthy',
-    'Tomato___Bacterial_spot',
-    'Tomato___Early_blight',
-    'Tomato___Late_blight',
-    'Tomato___Leaf_Mold',
-    'Tomato___Septoria_leaf_spot',
-    'Tomato___Spider_mites Two-spotted_spider_mite',
-    'Tomato___Target_Spot',
-    'Tomato___Tomato_Yellow_Leaf_Curl_Virus',
-    'Tomato___Tomato_mosaic_virus',
-    'Tomato___healthy']
+# ================= CONFIG =================
+MODEL_PATH = "plagiarism_model"
+EMBEDDINGS_FILE = "reference_embeddings.pkl"
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY", "YOUR_KEY_HERE")
+
+SIMILARITY_THRESHOLD = 30.0
+
+# ================= LOAD SBERT MODEL =================
+model = SentenceTransformer(MODEL_PATH)
+print("✅ Model loaded:", MODEL_PATH)
+
+# ================= LOAD REFERENCE DATA =================
+with open(EMBEDDINGS_FILE, "rb") as f:
+    data = pickle.load(f)
 
+ref_embeddings = data["embeddings"]
+df_ref = data["df_ref"]
 
+print("✅ Reference dataset loaded")
+
+# ================= GEMINI =================
+genai.configure(api_key=GEMINI_API_KEY)
+gemini_model = genai.GenerativeModel("gemini-2.5-flash")
+
+# ================= REQUEST MODEL =================
+class PlagiarismRequest(BaseModel):
+    text: str
+    title: str = "Unknown"
+    student_name: str = "Unknown"
+    year: str = "2026"
+
+# ================= HEALTH CHECK =================
 @app.get("/")
-async def root():
-    print("dfhkjfdshu")
-    return {"message": "Plant Disease Detection API", "version": "1.0.0"}
+def home():
+    return {"message": "Plagiarism API Running 🚀"}
 
-@app.post("/predict")
-async def predict_disease(file: UploadFile = File(...)):
-    
-    if not file.content_type.startswith('image/'):
-            raise HTTPException(status_code=400, detail="File must be an image")
+# ================= TEXT CHECK API =================
+@app.post("/check_plagiarism")
+async def check_plagiarism(req: PlagiarismRequest):
 
-    try:
-        # Validate file type
-        # Validate file type
-        
-        # Save uploaded file temporarily
-        with tempfile.NamedTemporaryFile(suffix=".jpeg", delete=False) as tmp:
-            temp_path = tmp.name
-            tmp.write(await file.read())
-            tmp.flush()  # Ensure data is written
-        
-        # Read image using OpenCV
-        # img = cv2.imread(temp_path)
-        # if img is None:
-        #     raise HTTPException(status_code=400, detail="Invalid image file")
-        # img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
-        
-        image = tf.keras.preprocessing.image.load_img(temp_path,target_size=(128, 128))
-        
-        input_arr = tf.keras.preprocessing.image.img_to_array(image)
-        input_arr = np.array([input_arr])  # Convert single image to batch
-
-        # Predict
-        prediction = model.predict(input_arr)
-        result_index = np.argmax(prediction)
-        confidence = float(prediction[0][result_index])
-        disease_name = class_name[result_index]
-
-        
+    text = req.text.strip()
 
-        return {
-            "success": True,
-            "disease": disease_name,
-            "confidence": confidence
-        }
+    if len(text) < 100:
+        raise HTTPException(400, "Text too short")
 
-    
-    
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Prediction error: {str(e)}")
+    if len(text) > 8000:
+        text = text[:8000]
+
+    # ================= SBERT =================
+    query_embedding = model.encode(
+        text,
+        convert_to_tensor=True,
+        normalize_embeddings=True
+    )
 
-@app.get("/health")
-async def health_check():
-    return {"status": "healthy"}
+    scores = util.cos_sim(query_embedding, ref_embeddings)[0]
+    scores = (scores * 100).cpu().numpy()
 
-@app.get("/classes")
-async def get_classes():
-    """Get all available disease classes"""
-    return {"classes": class_name}
+    top_idx = int(scores.argmax())
+    top_score = float(scores[top_idx])
 
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    row = df_ref.iloc[top_idx]
 
+    # ================= LOW RISK =================
+    if top_score < SIMILARITY_THRESHOLD:
+        return {
+            "status": "low_risk",
+            "similarity_percent": round(top_score, 2),
+            "rating": 1,
+            "most_similar_source": str(row.get("title", "N/A")),
+            "message": "No significant plagiarism detected"
+        }
 
+    # ================= GEMINI REPORT =================
+    prompt = f"""
+You are an academic plagiarism expert.
 
+Title: {req.title}
+Student: {req.student_name}
+Year: {req.year}
 
+Similarity: {top_score:.2f}%
 
+Source: {row.get("title", "N/A")}
 
+Give:
+1. Similarity explanation
+2. Risk level
+3. Recommendation
+"""
 
+    try:
+        response = gemini_model.generate_content(prompt)
+        report = response.text
+    except Exception as e:
+        report = f"Gemini error: {str(e)}"
 
+    # ================= RESPONSE =================
+    return {
+        "status": "suspicious",
+        "similarity_percent": round(top_score, 2),
+        "rating": 4 if top_score > 70 else 3,
+        "stars": "★★★★☆" if top_score > 70 else "★★★☆☆",
+        "most_similar_source": str(row.get("title", "N/A")),
+        "source_student": str(row.get("student_name", "N/A")),
+        "gemini_report": report,
+        "timestamp": datetime.now().isoformat()
+    }
 
+# ================= PDF UPLOAD API (OPTIONAL) =================
+@app.post("/check_pdf")
+async def check_pdf(file: UploadFile = File(...)):
 
+    content = await file.read()
 
+    text = ""
 
+    with pdfplumber.open(io.BytesIO(content)) as pdf:
+        for page in pdf.pages:
+            if page.extract_text():
+                text += page.extract_text() + "\n"
 
+    if len(text) < 100:
+        return {"error": "PDF too short"}
 
+    query_embedding = model.encode(text, convert_to_tensor=True, normalize_embeddings=True)
 
+    scores = util.cos_sim(query_embedding, ref_embeddings)[0]
+    scores = (scores * 100).cpu().numpy()
 
+    top_idx = int(scores.argmax())
+    top_score = float(scores[top_idx])
 
+    row = df_ref.iloc[top_idx]
 
+    return {
+        "status": "done",
+        "similarity_percent": round(top_score, 2),
+        "best_match": str(row.get("title", "N/A"))
+    }