assistance-engine/docs/ADR
izapata 4deda83a8e Add BEIR analysis notebooks and evaluation pipeline for embedding models
- Created `n00 Beir Analysis_cosqa.ipynb` for analyzing CoSQA dataset with BEIR.
- Created `n00 first Analysis.ipynb` for initial analysis using Ragas and Ollama embeddings.
- Implemented `evaluate_embeddings_pipeline.py` to evaluate embedding models across CodexGlue, CoSQA, and SciFact benchmarks.
- Added adapters for Ollama and HuggingFace embeddings to ensure compatibility with BEIR.
- Included functions to load datasets and evaluate models with detailed metrics.
2026-03-26 16:53:20 +01:00
..
ADR-0001-grpc-primary-interface.md feat: editor context injection (PRD-0002) + repository governance 2026-03-20 19:43:48 -07:00
ADR-0002-two-phase-streaming.md feat: editor context injection (PRD-0002) + repository governance 2026-03-20 19:43:48 -07:00
ADR-0003-hybrid-retrieval-rrf.md feat: editor context injection (PRD-0002) + repository governance 2026-03-20 19:43:48 -07:00
ADR-0004-claude-eval-judge.md feat: editor context injection (PRD-0002) + repository governance 2026-03-20 19:43:48 -07:00
ADR-0005-embedding-model-selection.md Add BEIR analysis notebooks and evaluation pipeline for embedding models 2026-03-26 16:53:20 +01:00
ADR-0006-reward-algorithm-dataset-synthesis.md feat(dataset): add ADR-0006 and scaffold reward algorithm pipeline 2026-03-25 22:19:19 -07:00