pizzato / llmme Goto Github PK

2023-10-16 13:04:59,691 - Indexing emails
2023-10-16 13:07:54,946 - Indexed 16043 emails
2023-10-16 13:07:54,946 - Creating dataframe
2023-10-16 13:07:55,837 - Getting email content
2023-10-16 13:09:48,972 - Getting replies
2023-10-16 13:09:49,061 - Dataset (total replies 53)
2023-10-16 13:09:49,086 - Getting original emails sent
2023-10-16 13:09:49,112 - Dataset (total new emails 177)
2023-10-16 13:09:49,137 - Dataset (total emails received 0)
Traceback (most recent call last):
File "\LLMMe\convert_mbox_to_csv.py", line 159, in
create_email_csv_dataset(mbox_filename=args.input, my_email_addresses=args.emails, csv_file_output=args.output)
File "\LLMMe\convert_mbox_to_csv.py", line 130, in create_email_csv_dataset
messages_received_not_replied = messages_received_not_replied.sample(n=len(emails_replied) + len(emails_i_started))
File \Python\Python310\site-packages\pandas\core\generic.py", line 5858, in sample
sampled_indices = sample.sample(obj_len, size, replace, weights, rs)
File "\Python\Python310\site-packages\pandas\core\sample.py", line 151, in sample
return random_state.choice(obj_len, size=size, replace=replace, p=weights).astype(
File "mtrand.pyx", line 928, in numpy.random.mtrand.RandomState.choice
ValueError: a must be greater than 0 unless no samples are taken

Just to clarify, we only extract the sent emails from google takeout?

That should include sent & reply emails with their threads & original messages.

Or do we need to extract all email data?

Thanks again !

Hi,
Is there any "cloud" service that allows one to train other than h2o studio?
What is the model that you recommend now best for answering emails? I guess opt is now old and maybe you can recommend something better?
Thanks a lot.
Hesham