embedded datasets

discord_chat_logs/newbotcommandscausefarmboisanoucnce.csv

@@ -1 +1 @@
-message_id,timestamp_utc,author_id,author_name,author_nickname,content,attachment_urls,embeds
+message_id,timestamp_utc,author_id,author_name,author_nickname,content,attachment_urls,embeds

discord_chat_logs/oop.csv

@@ -1 +1 @@
-message_id,timestamp_utc,author_id,author_name,author_nickname,content,attachment_urls,embeds
+message_id,timestamp_utc,author_id,author_name,author_nickname,content,attachment_urls,embeds

scripts/embedder.py

@@ -100,11 +100,11 @@ def process_csvs_in_directory(directory_path: str, model_name: str = 'all-MiniLM
 if __name__ == '__main__':
     # Define the directory where your CSV files are located.
     # The script will look for a folder named 'csv_data' in the current directory.
-    CSV_DIRECTORY = 'csv_data'
+    CSV_DIRECTORY = '../discord_chat_logs'
     
     # This function will create the 'csv_data' directory and some sample
     # files if they don't exist. You can comment this out if you have your own files.
-    create_sample_files(CSV_DIRECTORY)
+    # create_sample_files(CSV_DIRECTORY)
 
     # Run the main processing function on the directory
     process_csvs_in_directory(CSV_DIRECTORY)