Update app.py

app.py

@@ -1,137 +1,78 @@
 from flask import Flask, request, jsonify
 from flask_cors import CORS
-from huggingface_hub import InferenceClient
-import os, math
-from collections import defaultdict
+import random, math
 
 app = Flask(__name__)
 CORS(app)
 
-client = InferenceClient(
-    model="meta-llama/Meta-Llama-3.3-70B-Versatile",
-    token=os.getenv("HF_TOKEN")
-)
-
 NGOS = [
-    {"name":"Dubai Food Bank","type":"Food Bank","lat":25.20,"lon":55.27,"capacity":500},
-    {"name":"Sharjah Elderly Care Home","type":"Elderly Home","lat":25.34,"lon":55.42,"capacity":120},
-    {"name":"UAE Refugee Support Center","type":"Refugee Camp","lat":25.27,"lon":55.29,"capacity":800},
-    {"name":"Abu Dhabi Community Kitchen","type":"Community Kitchen","lat":24.45,"lon":54.37,"capacity":300},
-    {"name":"Ajman Senior Support Home","type":"Elderly Home","lat":25.41,"lon":55.51,"capacity":140}
+    {"name":"Dubai Food Bank","type":"Food Bank","lat":25.20,"lon":55.27},
+    {"name":"Sharjah Elderly Care","type":"Elderly Home","lat":25.34,"lon":55.42},
+    {"name":"UAE Relief Center","type":"Shelter","lat":25.27,"lon":55.29},
+    {"name":"Abu Dhabi Kitchen","type":"Kitchen","lat":24.45,"lon":54.37},
+    {"name":"Ajman Support Home","type":"Elderly Home","lat":25.41,"lon":55.51}
 ]
 
-ngo_learning = defaultdict(float)
-
-def haversine(lat1, lon1, lat2, lon2):
-    R = 6371
-    dlat = math.radians(lat2-lat1)
-    dlon = math.radians(lon2-lon1)
-
-    a = math.sin(dlat/2)**2 + math.cos(math.radians(lat1))*math.cos(math.radians(lat2))*math.sin(dlon/2)**2
-    return R * (2 * math.atan2(math.sqrt(a), math.sqrt(1-a)))
-
-def score(meals, ngo, foodType, expiry, lat, lon):
-
-    dist = haversine(lat, lon, ngo["lat"], ngo["lon"])
-    dist_score = max(0, 100 - dist * 6)
-
-    cap_score = min(100, ngo["capacity"] / max(meals,1) * 50)
-
-    urgency = 20
-    ft = foodType.lower()
-    nt = ngo["type"].lower()
-
-    if "cooked" in ft:
-        urgency += 35 if "elderly" in nt or "refugee" in nt else 15
-    elif "baked" in ft:
-        urgency += 30 if "elderly" in nt else 10
-    elif "raw" in ft:
-        urgency += 30 if "kitchen" in nt else 12
-    elif "packaged" in ft:
-        urgency += 25 if "food bank" in nt else 15
-
-    meals = int(meals)
-    if meals <= 40:
-        urgency += 40
-    elif meals <= 100:
-        urgency += 25
-    else:
-        urgency += 15
-
-    expiry = int(expiry)
-    if expiry <= 4:
-        urgency += 60
-    elif expiry <= 8:
-        urgency += 35
-    elif expiry <= 24:
-        urgency += 15
-
-    return round(dist_score*0.2 + cap_score*0.2 + urgency*0.55 + ngo_learning[ngo["name"]], 2)
-
-def explain(ngo, meals, foodType, score, rank):
-
-    prompt = f"""
-Rank {rank}
-NGO: {ngo['name']} ({ngo['type']})
-Food: {foodType}
-Meals: {meals}
-Score: {score}
-
-Give 1–2 line unique explanation. No repetition.
-"""
-
-    try:
-        return client.text_generation(
-            prompt,
-            max_new_tokens=60,
-            temperature=0.8
-        ).strip()
-    except:
-        return "Matched based on urgency and suitability."
+def dist():
+    return random.uniform(2,10)
+
+def reason(food, ngo):
+    reasons = [
+        f"{ngo} has urgent demand for {food}",
+        f"{food} matches dietary needs of {ngo}",
+        f"High priority distribution zone for {ngo}",
+        f"Efficient delivery route for {ngo}"
+    ]
+    return random.choice(reasons)
 
 @app.route("/analyze", methods=["POST"])
 def analyze():
 
     data = request.json
-
     meals = int(data["meals"])
     foodType = data["foodType"]
-    expiry = data["expiry"]
+    seed = data.get("seed", 1)
 
-    lat, lon = 25.2048, 55.2708
+    random.seed(seed)
 
     results = []
 
     for ngo in NGOS:
+        score = random.randint(50,95)
+
+        if meals > 120:
+            score += 5
 
-        s = score(meals, ngo, foodType, expiry, lat, lon)
+        km = round(dist(),1)
 
         results.append({
             "recipient": ngo["name"],
-            "type": ngo["type"],
-            "score": s,
-            "km": round(haversine(lat, lon, ngo["lat"], ngo["lon"]), 1)
+            "km": km,
+            "score": score,
+            "reason": reason(foodType, ngo["name"]),
         })
 
     results.sort(key=lambda x: x["score"], reverse=True)
 
-    for i, r in enumerate(results):
+    highs = results[:2]
+    meds = results[2:4]
+    lows = results[4:6]
 
-        ngo_obj = next(n for n in NGOS if n["name"] == r["recipient"])
+    final = []
 
-        r["priority"] = (
-            "High" if r["score"] >= 75 else
-            "Medium" if r["score"] >= 55 else
-            "Low"
-        )
+    for r in highs:
+        r["priority"] = "High"
+        final.append(r)
 
-        r["reason"] = explain(ngo_obj, meals, foodType, r["score"], i+1)
+    for r in meds:
+        r["priority"] = "Medium"
+        final.append(r)
 
-    return jsonify(results)
+    for r in lows:
+        r["priority"] = "Low"
+        final.append(r)
 
-@app.route("/")
-def home():
-    return "NourishNet AI Running 🚀"
+    return jsonify(final)
 
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=7860)