Commit History

removed debugging messages now that search is working
4c7c106

wbrooks commited on

making sure all the correct arguments are there in the function calls
67412fc

wbrooks commited on

pass IDF DTM to the function factory
84c4c3d

wbrooks commited on

the factory has to actually return the function
35bf0ca

wbrooks commited on

corrected the name of the fasttext model binary
4842291

wbrooks commited on

send row names to be included in the results
2f234b8

wbrooks commited on

switched to the new search functions using sentence-transformers
68fd999

wbrooks commited on

added search URL to the README
1aa0d22

wbrooks commited on

renamed modules that do the search
c1d8ce6

wbrooks commited on

changes TF-IDF search to cosine similarity from dot product
ab4ff40

wbrooks commited on

changes TF-IDF search to cosine similarity from dot product
1310186

wbrooks commited on

switch tfidf search to use file list saved by joblib
3facea3

wbrooks commited on

reshape with shape, not size
1cf6271

wbrooks commited on

reduce files list to 1-d
7b687d4

wbrooks commited on

testing separate query methods
c70ddc5

wbrooks commited on

use block_embeddings_df from the compressed serialized parquet file
68239c7

wbrooks commited on

copied encode function directly into search_embeddings.py
6b6def4

wbrooks commited on

need to specify path to encode because this is a hacky prototype
88bbcb9

wbrooks commited on

use a pre-serialized dtm_svd
d503cc1

wbrooks commited on

allow pickle for deserializing data
4e5f6d2

wbrooks commited on

load the DTM and file list from serialized versions
21ca93f

wbrooks commited on

don't need to install glob
17f8024

wbrooks commited on

added scripts for testing inference
c795cd4

wbrooks commited on