Spaces:

below-threshold
/

ai-response-validator

Running

App Files Files Community

ai-response-validator

421 kB

Ctrl+K

Ctrl+K

3 contributors

History: 36 commits

mbochniak01

Claude Sonnet 4.6

Switch faithfulness to text_pair encoding, promote score logging to INFO

29f3273 15 minutes ago

backend
Switch faithfulness to text_pair encoding, promote score logging to INFO 15 minutes ago
client
Add typed client library, unit + integration tests, mypy, ruff, NOTES.md 6 days ago
eval
Faithfulness: mean sentence scoring, strip chunk title prefix, lower threshold to 0.35 3 days ago
knowledge
Load all KB formats merged — drop CSV directly, no conversion needed 6 days ago
scripts
Add 15 drug profiles to pharma KB from Kaggle dataset 6 days ago
tests
Add typed client library, unit + integration tests, mypy, ruff, NOTES.md 6 days ago
ui
UX: welcome message with example questions, specific failure details in verdict 6 days ago
.dockerignore

69 Bytes
Speed up Docker builds: .dockerignore + merge model download layers 3 days ago
.gitattributes

1.52 kB
initial commit 6 days ago
.gitignore

29 Bytes
Add .env and .DS_Store to gitignore 6 days ago
ARCHITECTURE.md

9.91 kB
Add /refresh-cache endpoint, bi-encoder comparison, eval results, Ollama/Prometheus notes 2 days ago
Dockerfile

983 Bytes
Fix Vectara label check and input format 2 days ago
Makefile

910 Bytes
Add typed client library, unit + integration tests, mypy, ruff, NOTES.md 6 days ago
NOTES.md

6.75 kB
Add /refresh-cache endpoint, bi-encoder comparison, eval results, Ollama/Prometheus notes 2 days ago
README.md

4.16 kB
Add /refresh-cache endpoint, bi-encoder comparison, eval results, Ollama/Prometheus notes 2 days ago
mypy.ini

429 Bytes
Add typed client library, unit + integration tests, mypy, ruff, NOTES.md 6 days ago
pytest.ini

144 Bytes
Add typed client library, unit + integration tests, mypy, ruff, NOTES.md 6 days ago
requirements.txt

360 Bytes
Add sentencepiece dependency for T5Tokenizer 3 days ago
ruff.toml

314 Bytes
Add typed client library, unit + integration tests, mypy, ruff, NOTES.md 6 days ago