Rag clean up + missing specs

Fix HuggingFace Spaces README metadata

Address comments

Clean up docs

Complete Agent 3 evaluation infrastructure and identify RAG schema issue

Agent 2 implementation + baseline eval and small improvements

Improve on RAG content to have right size

Add innovation narrative and sampling strategy docs

Fix JSON extraction consistency and update docs

Fix baseline feedback template usage and linting

Merge main into phase-1/deepeval-setup

Create prompts with LangChain

Clean up docs and reorganize: Flatten structure, remove outdated files

Implement DeepEval evaluation pipeline with comprehensive fixes

Reorganize for v2: Archive v1, add v2 docs and eval test cases

Setup modern Python tooling and RAG pipeline

Initial project setup: directory structure, dependencies, README