The focus of this PR is to enhance the repository by adding semantic similarity functionality and generating a similar.csv file with top-5 similar examples.
Detailed summary
Added semantic_similarity.py for text similarity calculations.
Introduced similar.py for finding similar text examples.
Included similar.csv to store top-5 similar examples.
Updated embed.py to use environment variables for data sources.
✨ Ask PR-Codex anything about this PR by commenting with /codex {your question}
closes #33
PR-Codex overview
The focus of this PR is to enhance the repository by adding semantic similarity functionality and generating a
similar.csv
file with top-5 similar examples.Detailed summary
semantic_similarity.py
for text similarity calculations.similar.py
for finding similar text examples.similar.csv
to store top-5 similar examples.embed.py
to use environment variables for data sources.