20 Commits

Include renames

Author	SHA1	Message	Date
Thomas Lemoine	719674541c	modified main of textsplitter	2023-03-14 02:21:18 -04:00
Thomas Lemoine	6503a61bd3	created the TextSplitter class	2023-03-14 00:04:05 -04:00
Thomas Lemoine	49b8cd0239	added functionality to textsplitter	2023-03-13 21:19:13 -04:00
Thomas Lemoine	e8ee64cd7c	raw text can be converted to chunks with signature	2023-03-10 21:09:51 -05:00
henri123lemoine	8d4a0b9b45	Moved files around, updated semantic search and added prompt search.	2023-03-09 16:20:52 -05:00
henri123lemoine	3b1451bf64	Same	2023-03-09 16:20:33 -05:00
henri123lemoine	ced7e927f7	Changing format of folders.	2023-03-09 16:19:40 -05:00
henri123lemoine	47175fe074	Updated readme and testing notebook	2023-02-06 21:22:07 -05:00
henri123lemoine	c6dd827c4a	added if __name__	2023-02-06 20:52:52 -05:00
henri123lemoine	82e79354f4	added main.py, do not run	2023-02-06 20:52:21 -05:00
henri123lemoine	59d9f25f65	Added settings.py	2023-02-06 20:51:34 -05:00
henri123lemoine	ec03b854cc	Added AlignmentSearch class, takes dataset class as input. Does semantic search, question answering and summarization.	2023-02-06 20:50:39 -05:00
henri123lemoine	47cb734bc3	Added helper functions for sentence-splitting and article splitting	2023-02-06 20:49:55 -05:00
henri123lemoine	807a7f066c	Added dataset.py from testing.ipynb, gets the data from the jsonl file from wanted sources and gets the embeddings from each paragraph.	2023-02-06 20:48:58 -05:00
henri123lemoine	0155a3cc52	Didn't change much	2023-02-05 01:41:52 -05:00
henri123lemoine	f047045208	Added a search+q&a class	2023-02-04 05:11:22 -05:00
henri123lemoine	aa39a22bf2	Updated testing.ipynb	2023-02-03 09:53:40 -05:00
henri123lemoine	88d2164d88	Updated the testing considerably. Loading the dataset works pretty well.	2023-02-03 06:37:35 -05:00
henri123lemoine	571d0195f4	OOPed notebook	2023-02-03 01:06:58 -05:00
henri123lemoine	3b603a51fa	Updated the testing notebook for extracting the jsonl dataset.	2023-02-01 02:15:10 -05:00