SA-653/migrate sic data access to library

[dstewartons]

📌 Pull Request Template

Please complete all sections

✨ Summary

Consumes SIC workbook data access from sic-classification-library (SA-653) and removes the duplicate sic_data_access module from utils. LLM, prompt, and sic_specific_embed import industrial_classification.data_access.sic_data_access instead, behaviour and config tuples are unchanged).

CI note: CI purposefully fails here as until the dependency tags exist in the remote remerged repos, sopyproject.toml temporarily uses local editable paths:

📜 Changes Introduced

• Feature implementation (feat:) / bug fix (fix:) / refactoring (chore:) / documentation (docs:) / testing (test:)

• Updates to tests and/or documentation

• Terraform changes (if applicable) — N/A

• Removed src/industrial_classification_utils/utils/sic_data_access.py and tests/test_sic_data_access.py (coverage lives in library tests/test_data_access.py).

• llm/llm.py: load_sic_hierarchy from library for lazy hierarchy build in _prompt_candidate.

• llm/prompt.py: load_sic_index from library (import-time index load unchanged).

• embed/sic_specific_embed.py: load_sic_hierarchy from library for vector-store build helper.

• tests/test_embedding.py: patch load_sic_hierarchy instead of separate index/structure/hierarchy mocks.

• docs/utils.md, README.md: point to library sic_data_access module.

• pyproject.toml / poetry.lock: pin sic-classification-library v0.1.5; utils version 0.1.14.

Unchanged

• Packaged .xlsx paths under industrial_classification_utils.data.sic_index.
• get_default_config() lookup tuples and flat-file EmbeddingHandler behaviour.

✅ Checklist

Please confirm you've completed these checks before requesting a review.

• Code is formatted using Black
• Imports are sorted using isort
• Code passes linting with Ruff, Pylint, and Mypy
• Security checks pass using Bandit
• API and Unit tests are written and pass using pytest
• Terraform files (if applicable) follow best practices and have been validated (terraform fmt & terraform validate)
• DocStrings follow Google-style and are added as per Pylint recommendations
• Documentation has been updated if needed

🔍 How to Test

Unit tests (this repo only)

cd sic-classification-utils
poetry install
poetry run pytest tests/test_embedding.py -k "sic_index_files" -q

Verified: 2 passed

Import-time prompt load (loads full SIC index at module import):

poetry run python -c "from industrial_classification_utils.llm import prompt; print(len(prompt.sic_index))"

Expected: large row count (e.g. ~15k), no import error.

Broader regression (optional):

poetry run pytest tests/test_embedding.py -q
make check-python   # if used in this repo

[gibbardsteve]

See comments against sic-classification-library. Happy to approve the PRs