admin
d2efc7030a
feat: US-019 - Run benchmark and validate accuracy
...
Benchmark passes 19/20 (threshold 18/20) with no zeros.
Structural improvements: Employment Timeline section, leadership
labels on Tesco bullets, GPhC clarification, prompt trimming.
Fixed Q10 expected answer to match actual CV data.
2026-02-16 00:59:37 +00:00
admin
f0870cf320
feat: US-017 - Improve system prompt instructions and LLM parameters
2026-02-16 00:42:58 +00:00
admin
194f83f490
feat: US-016 - Enrich system prompt with full CV context
2026-02-16 00:39:38 +00:00
admin
8cc7038942
feat: US-015 - Migrate benchmark script to OpenRouter
2026-02-16 00:31:16 +00:00
admin
0fbbf9e46f
merge
2026-02-15 23:20:24 +00:00
admin
667e5b249c
feat: US-013 - Self-host ONNX embedding model
...
Download all-MiniLM-L6-v2 model files to public/models/ and configure
@xenova/transformers to load from local path instead of Hugging Face CDN.
Eliminates external dependency for semantic search embedding model.
2026-02-15 20:59:03 +00:00
admin
aa1774320a
feat: US-003 - Generate and commit embeddings.json
2026-02-15 17:55:53 +00:00
admin
489e306b0a
feat: US-001 - Install @xenova/transformers and add generate-embeddings script skeleton
2026-02-15 17:49:25 +00:00
admin
598b1c11f6
Final commit
2026-02-15 02:14:51 +00:00
admin
962729ae92
Supporting info for login screen rework
2026-02-15 01:44:02 +00:00
admin