label new

train_finetune.py

@@ -4,6 +4,7 @@
 import pandas as pd
 from sentence_transformers import SentenceTransformer, InputExample, losses
 from torch.utils.data import DataLoader
+from create_triplets import create_triplets # Import the function
 
 # --- File Paths ---
 TRIPLETS_PATH = "data/esg_triplets.csv"
@@ -28,9 +29,14 @@ def fine_tune_model():
         triplets_df = pd.read_csv(TRIPLETS_PATH)
         train_examples = [InputExample(texts=[row['anchor'], row['positive'], row['negative']]) for _, row in triplets_df.iterrows()]
     except FileNotFoundError:
-        print(f"Error: Triplets file not found at {TRIPLETS_PATH}. Aborting.")
-        print("Please run 'create_triplets.py' first to generate the training data.")
-        return
+        print(f"Info: Triplets file not found at {TRIPLETS_PATH}. Generating it now...")
+        create_triplets() # Generate the triplets
+        try:
+            triplets_df = pd.read_csv(TRIPLETS_PATH)
+            train_examples = [InputExample(texts=[row['anchor'], row['positive'], row['negative']]) for _, row in triplets_df.iterrows()]
+        except FileNotFoundError:
+            print(f"Error: Failed to generate or find triplets file at {TRIPLETS_PATH}. Aborting.")
+            return
         
     if not train_examples:
         print("No training examples found. Aborting fine-tuning.")