Update app.py

app.py

@@ -12,47 +12,37 @@ app = FastAPI()
 
 @app.get("/")
 def root():
-    return {"message": "Welcome to the Product Search API!"}
-def encode_image_to_base64(image):
-    """
-    Converts a PIL Image or an image-like object to a Base64-encoded string.
-    """
-    if isinstance(image, Image.Image):
-        buffer = BytesIO()
-        image.save(buffer, format="PNG")
-        return base64.b64encode(buffer.getvalue()).decode("utf-8")
-    return None
-# Initialize FastAPI
-
+    return {"message": "Welcome to the medicine Search API!"}
 # Load Dataset
-dataset = load_dataset("ashraq/fashion-product-images-small", split="train")
+dataset = load_dataset("MohamedAshraf701/medicine-dataset", split="train")
 
 # Define fields for embedding
 fields_for_embedding = [
-    "productDisplayName",
-    "usage",
-    "season",
-    "baseColour",
-    "articleType",
-    "subCategory",
-    "masterCategory",
-    "gender",
+    "product_name",
+    "sub_category",
+    "salt_composition",
+    "product_manufactured",
+    "medicine_desc",
+    "side_effects",
+    "drug",
+    "brand",
+    "effect"
 ]
 
 # Prepare Data
 data = []
 for item in dataset:
     data.append({
-        "productDisplayName": item["productDisplayName"],
-        "usage": item["usage"],
-        "season": item["season"],
-        "baseColour": item["baseColour"],
-        "articleType": item["articleType"],
-        "subCategory": item["subCategory"],
-        "masterCategory": item["masterCategory"],
-        "gender": item["gender"],
-        "year": item["year"],
-        "image": item["image"],
+        "product_name": item["product_name"],
+        "sub_category": item["sub_category"],
+        "salt_composition": item["salt_composition"],
+        "product_price": item["product_price"],
+        "product_manufactured": item["product_manufactured"],
+        "medicine_desc": item["medicine_desc"],
+        "side_effects": item["side_effects"],
+        "drug": item["drug"],
+        "brand": item["brand"],
+        "effect": item["effect"],
     })
 
 # Load Sentence Transformer Model
@@ -60,29 +50,29 @@ model = SentenceTransformer("sentence-transformers/multi-qa-MiniLM-L6-cos-v1")
 
 # Generate Embeddings
 def create_combined_text(item):
-    return " ".join([str(item[field]) for field in fields_for_embedding if item[field]])
+    """
+    Combines fields from an item into a single string for embedding,
+    converting arrays to comma-separated strings where necessary.
+    """
+    combined_text = []
+    for field in fields_for_embedding:
+        value = item.get(field)
+        if value:
+            # If the field is a list, join its elements into a single string
+            if isinstance(value, list):
+                combined_text.append(", ".join(map(str, value)))
+            else:
+                combined_text.append(str(value))
+    return " ".join(combined_text)
+
 
 texts = [create_combined_text(item) for item in data]
 embeddings = model.encode(texts, convert_to_tensor=True)
 
-# Response Model
-class ProductResponse(BaseModel):
-    productDisplayName: str
-    usage: str
-    season: str
-    baseColour: str
-    articleType: str
-    subCategory: str
-    masterCategory: str
-    gender: str
-    year: int
-    image: str  # Base64 encoded string
-
-
 
-@app.get("/products")
+@app.get("/meds")
 def search_products(
-    query: str = Query("", title="Search Query", description="Search term for products"),
+    query: str = Query("", title="Search Query", description="Search term for medicine"),
     page: int = Query(1, ge=1, title="Page Number"),
     items_per_page: int = Query(10, ge=1, le=100, title="Items Per Page"),
 ):
@@ -105,18 +95,7 @@ def search_products(
     results = []
     for idx in paginated_indices:
         item = data[idx]
-        results.append({
-            "productDisplayName": item["productDisplayName"],
-            "usage": item["usage"],
-            "season": item["season"],
-            "baseColour": item["baseColour"],
-            "articleType": item["articleType"],
-            "subCategory": item["subCategory"],
-            "masterCategory": item["masterCategory"],
-            "gender": item["gender"],
-            "year": item["year"],
-            "image": encode_image_to_base64(item["image"]),
-        })
+        results.append(item)
 
     # Construct the API response
     return {