Test files › RAG test corpus › all-facts.txt
Sample Text file (all facts)
Every fact in the corpus as one plain sentence each, with its source file. The control.
↓ Download all-facts.txt| Filename | all-facts.txt |
| Format | Text |
| Size | 1.5 KB (1,488 bytes) |
| MIME type | text/plain; charset=utf-8 |
| SHA-256 | c2df6752bd0dc9ec5022b19655969e86192d7412f3f6b745e9a04b75578edc52 |
What this file catchesIndex this alone and run the answer key against it. If this scores well and rag/corpus/ does not, the model is fine and the extraction is what is failing.
Download & verify
curl -fsSL -o "all-facts.txt" "https://files.hexaqa.com/rag/baseline/all-facts.txt"
curl -fsSL "https://files.hexaqa.com/rag/baseline/all-facts.txt" | sha256sum
# expect: c2df6752bd0dc9ec5022b19655969e86192d7412f3f6b745e9a04b75578edc52