Spaces:
Sleeping
Sleeping
Commit History
-
style: Fix code formatting and linting issues for CI/CD compliance
Tobias Pasquale- Fix black code formatting across all Python files - Fix isort import ordering - Remove unused imports (pytest, pathlib, numpy, Union) - Fix line length issues (split long lines) - Remove unused variables in tests - Fix whitespace and end-of-file issues - Address flake8 linting requirements All changes maintain functionality while ensuring CI/CD pipeline passes.7793bb6
-
feat: implement data ingestion and processing pipeline
Tobias Pasquale- Add complete document parsing, chunking, and ingestion pipeline - Support for .txt and .md file formats - Character-based chunking with configurable overlap - Reproducible results with fixed seed (42) - Comprehensive test suite (19 new tests, all passing) - Flask /ingest endpoint for corpus processing - Successfully processes 98 chunks from 22 policy documents - Follows TDD approach with 100% test coverage Completes milestone 4 (Data Ingestion and Processing) from project plan. Tests: 22/22 passing Coverage: Document parser, chunker, integration pipeline, Flask endpointffa0f3d