Update app.py

app.py

@@ -6,6 +6,33 @@ from sklearn.metrics.pairwise import cosine_similarity
 from groq import Groq
 import pandas as pd
 
+
+# Use the current directory for Hugging Face Spaces
+dataset_folder = "./data"  # Assuming files are in a 'data/' folder
+
+# Verify the folder exists
+if not os.path.exists(dataset_folder):
+    dataset_folder = "."  # Fallback: Look in the current directory
+
+# Load all CSV files in the dataset folder
+dataframes = []
+for file in os.listdir(dataset_folder):
+    if file.endswith(".csv"):  # Check if the file is a CSV
+        df = pd.read_csv(os.path.join(dataset_folder, file))
+        dataframes.append(df)
+
+# Merge all CSV files into one DataFrame
+full_data = pd.concat(dataframes, ignore_index=True)
+
+# Ensure required columns exist
+assert 'question' in full_data.columns, "Dataset must have a 'question' column"
+assert 'query' in full_data.columns, "Dataset must have a 'query' column"
+
+print(full_data.head())  # Debugging: Check if data loads correctly
+
+
+
+
 load_dotenv()
 
 groq_api_key = os.getenv("groq_api_key")
@@ -83,7 +110,5 @@ def response(user_query, dataset_folder):
     system_prompt = create_prompt(user_query, table_metadata)
     return generate_sql_query(system_prompt)
 
-# Example usage:
-dataset_folder = r"C:\\Users\\khuma\\data"
-user_query = "Show me the top 10 startups with the highest funding."
-print(response(user_query, dataset_folder))
+dataset_folder = "./data"  # Change this based on where your files are uploaded
+user_query = "Show me the top 10 startups with the highest funding."