cjc0013's picture
Create readme.txt
68121f3 verified
raw
history blame contribute delete
764 Bytes
# Epstein Semantic Explorer β€” HuggingFace Edition
A lightweight, dependency-free semantic analysis tool for the
recently released House Oversight Epstein documents.
### πŸš€ Features
- Cluster browser
- BM25 semantic search
- Topic terms
- Entity frequency explorer
- Cross-cluster entity mapping
- Works entirely on CPU
### πŸ“ How to Use
1. Upload your dataset: `epstein_semantic.jsonl`
2. Select a cluster
3. Search keywords
4. Explore entities / topics
### πŸ“¦ Dataset Source
Full processed dataset is available on Kaggle:
https://www.kaggle.com/datasets/cjc0013/epstein-bge-large-hdbscan-bm25/data
### πŸ“ Notes
- No external API calls
- No model downloads
- 100% local execution inside the Space
MIT License Β© cjc0013