Spaces:

seanpedrickcase
/

data_text_search

Sleeping

App Files Files Community

data_text_search / app.py

Commit History

Minor changes to file path for outputs, documentation, location of pyinstaller build dependencies

200480d

seanpedrickcase commited on Jan 11, 2024

Many changes to code organisation. More efficient searches from using intermediate outputs. Version 0.1

99d6fba

seanpedrickcase commited on Jan 10, 2024

Now works correctly with npz. Minor formatting improvements

d3b1ac5

seanpedrickcase commited on Jan 5, 2024

Changed in_query to keyword_query

6768a6d

seanpedrickcase commited on Jan 5, 2024

Added semantic search using Jina

ceb8617

seanpedrickcase commited on Jan 5, 2024

Faster embedding with GPU, fast document split, writes to chromadb file correctly. No longer needs FAISS or langchain

2cb9977

seanpedrickcase commited on Dec 13, 2023

Now outputs correct dataframe for semantic search. Can join on extra details

2a8aba8

Sean-Case commited on Dec 12, 2023

Added basic semantic search functionality

78d71d4

Sean-Case commited on Dec 12, 2023

added nltk punkt load

ba838fc

Sean-Case commited on Nov 9, 2023

Added stopwords and wordnet nltk dependencies

c1da670

Sean-Case commited on Nov 9, 2023

Added nltk download for names for HF use

7e5fca9

Sean-Case commited on Nov 9, 2023

Updates to readme file. Changed app file name to work with HF.

5c04910

Sean-Case commited on Nov 9, 2023