Update app.py

app.py

@@ -25,30 +25,14 @@ logger = logging.getLogger("ArabicSignNLP")
 
 # ----- Project Configuration -----
 class Config:
-    # Path to your CSV dataset containing sign labels
-    # On HF Spaces, upload your CSV to the repo and set the path here
     CSV_PATH: str = os.getenv("CSV_PATH", "arabic_sign_lang_features.csv")
-
-    # Folder where .npy keypoint files are stored (optional on HF Spaces)
     KEYPOINTS_FOLDER: str = os.getenv("KEYPOINTS_FOLDER", "keypoints")
-
-    # Output file path for Blender sequence
     SEQUENCE_OUTPUT_PATH: str = "/tmp/sequence.txt"
-
-    # AraBERT model for Arabic semantic understanding
     EMBEDDING_MODEL: str = "aubmindlab/bert-base-arabertv2"
-
-    # Similarity threshold for sign matching
     SIMILARITY_THRESHOLD: float = float(os.getenv("SIMILARITY_THRESHOLD", "0.72"))
-
-    # Include prepositions in signing
     INCLUDE_PREPOSITION_WORDS: bool = False
-
-    # FastAPI server settings
     API_HOST: str = "0.0.0.0"
-    API_PORT: int = 7860  # HF Spaces uses port 7860
-
-    # Column name in your CSV that contains the sign labels
+    API_PORT: int = 7860
     CSV_LABEL_COLUMN: str = "label"
 
 
@@ -237,9 +221,19 @@ class SemanticSignMatcher:
         return label
 
     def _load_database(self, csv_path: str, label_column: str):
+        # ---- التعديل: لو الـ CSV مش موجود، حمّله من HF ----
         if not os.path.exists(csv_path):
-            logger.warning(f"CSV not found at {csv_path}. No word signs loaded.")
-            return
+            logger.info("CSV not found locally. Downloading from Hugging Face...")
+            import urllib.request
+            url = "https://huggingface.co/spaces/SondosM/avatarAPI/resolve/main/arabic_sign_lang_features.csv"
+            try:
+                urllib.request.urlretrieve(url, csv_path)
+                logger.info("CSV downloaded successfully.")
+            except Exception as e:
+                logger.warning(f"Failed to download CSV: {e}. No word signs loaded.")
+                return
+        # -----------------------------------------------------
+
         df = pd.read_csv(csv_path, low_memory=False)
         if label_column not in df.columns:
             raise ValueError(f"Column '{label_column}' not found. Available: {list(df.columns)}")
@@ -539,4 +533,4 @@ def read_sequence_file():
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host=Config.API_HOST, port=Config.API_PORT)
+    uvicorn.run(app, host=Config.API_HOST, port=Config.API_PORT)