Searching for smiles regardless of the position column

app.py

@@ -21,31 +21,44 @@ model = load_smi_ted(
 
 # 3) Single function to process either a single SMILES or a CSV of SMILES
 def process_inputs(smiles: str, file_obj):
-    # If a CSV file is provided, process in batch
+    # Se um arquivo CSV for fornecido, processa em batch
     if file_obj is not None:
         try:
             df_in = pd.read_csv(file_obj.name)
-            smiles_list = df_in.iloc[:, 0].astype(str).tolist()
+            
+            # Procura coluna "smiles" (case‐insensitive), mas sem aceitar prefixes/sufixos
+            smiles_cols = [col for col in df_in.columns if col.lower() == "smiles"]
+            if not smiles_cols:
+                return (
+                    "Error: The CSV must have a column named 'Smiles' with the respective SMILES.",
+                    gr.update(visible=False),
+                )
+            smiles_col = smiles_cols[0]
+            smiles_list = df_in[smiles_col].astype(str).tolist()
+
             embeddings = []
             for sm in smiles_list:
                 vec = model.encode(sm, return_torch=True)[0].tolist()
                 embeddings.append(vec)
-            # Build output DataFrame
+
+            # Constroi DataFrame de saída
             out_df = pd.DataFrame(embeddings)
             out_df.insert(0, "smiles", smiles_list)
             out_df.to_csv("embeddings.csv", index=False)
+
             msg = f"Processed batch of {len(smiles_list)} SMILES. Download embeddings.csv."
             return msg, gr.update(value="embeddings.csv", visible=True)
+
         except Exception as e:
             return f"Error processing batch: {e}", gr.update(visible=False)
 
-    # Otherwise, process a single SMILES
+    # Modo single
     smiles = smiles.strip()
     if not smiles:
         return "Please enter a SMILES or upload a CSV file.", gr.update(visible=False)
     try:
         vec = model.encode(smiles, return_torch=True)[0].tolist()
-        # Save CSV with header
+        # Salva CSV com header
         cols = ["smiles"] + [f"dim_{i}" for i in range(len(vec))]
         df_out = pd.DataFrame([[smiles] + vec], columns=cols)
         df_out.to_csv("embeddings.csv", index=False)
@@ -53,6 +66,7 @@ def process_inputs(smiles: str, file_obj):
     except Exception as e:
         return f"Error extracting embedding: {e}", gr.update(visible=False)
 
+
 # 4) Build the Gradio Blocks interface
 with gr.Blocks() as demo:
     gr.Markdown(