SQLExecutor runs generated SQL queries against PostgreSQL with retry logic and error recovery. Multi-Stage Text-to-SQL Architecture realizes the SQLExecutor use case for executing SQL with error recovery and retry.

Platform supports 5 standard schemas (Salary, Health, Financial, Budget, Geographic) with optional mappings. Infrastructure for storing mappings and applying them during extraction is being developed to enable cross-file analysis and improve AI-assisted schema detection.

GdprDetector uses StorageService to scan project data for GDPR-related personal data indicators. SchemaMapper uses StorageService to manage file storage when mapping uploaded file columns to standard schemas. GdprDetector uses StorageService to scan project data for GDPR-relevant personal data indicators. StorageService handles file storage and retrieval for FilePrioritizer's prioritization process.

Svelte store managing current language state and persistence across user sessions.

DataLens supports structured search via Text-to-SQL queries on DuckDB.

A process requirement that now uses parallel subprocesses for real-time GPU-based extraction, replacing fallback methods.

The Data Discovery feature includes multiple Svelte components.

SVGV project involves processing 214 files (Excel, PDFs, CSVs, Word, PPT, MSG) for budget analysis; recent batch extraction of 8 files has been completed, with ongoing validation and metadata storage, aiming for comprehensive financial insights. SQLCoder-7B is planned to be used for full SVGV analysis after deployment is complete.

The SVGV Budget Analysis Project is owned by the Danish Government - Styrelsen for Grøn Arealomlægning og Vandmiljø. Bridge Consulting worked as a consultant on the SVGV Budget Analysis Project. HBS Economics worked as a consultant on the SVGV Budget Analysis Project. Ajeto worked as a consultant on the SVGV Budget Analysis Project. The SVGV Budget Analysis Project uses Docling for LLM-driven normalization and Excel extraction processing. The SVGV Budget Analysis Phase 2 epic contains the requirement for Phase 2 MVP with 33 out of 35 questions answered. The analytical results documented in ANALYTICAL_RESULTS.md correspond to the SVGV Budget Analysis Phase 2 project. The Danish Government's agency Styrelsen for Grøn Arealomlægning og Vandmiljø is the client for the SVGV Budget Analysis Project. HBS Economics is one of the consulting firms involved in the SVGV Budget Analysis Project. Ajeto is a consulting partner contributing to the SVGV Budget Analysis Project. Docling is used to extract tabular data from Excel files of the SVGV Budget Analysis Project. SVGV Budget Analysis is the Project 4 deployed on the platform for batch extraction and analysis.

The SVGV Full Reset process depends on RQ Worker extraction processing to handle extraction jobs after resetting files and schema. The SVGV Full Reset includes dropping and recreating the PostgreSQL project_14 schema as part of the reset. The full SVGV dataset reset and re-extraction process involves dropping and recreating the project_14 schema to an empty state. The full SVGV dataset reset and re-extraction process queues 132 extraction jobs for processing. The E2E Test Suite validates the fresh SVGV Full Reset data by running tests against the reset and extracted dataset.

Test project using SVGV files and batch processing setup, with successful extraction and planning for scaling.

DiscoveryService uses Table to represent database tables with metadata in consolidation recommendations.

The DOCX extractor handles tables by embedding them as JSON within text chunks instead of separate DuckDB tables.

TableIndexService uses QdrantService to build semantic search indices for database tables. QdrantService supports TableIndexService by providing vector collections for semantic table search indexes. TableMatch represents individual tables that are part of TableIndexService semantic search indexes.

Service class in backend/app/services/table_index.py that manages matching database tables to queries. TableMatch represents individual tables that are part of TableIndexService semantic search indexes.

Valid credentials for admin user used in testing discovery, agent access, and deployment verification. Account has Danish language preference, enabling full feature usage.

DataLens consults the Test Engineer when needing validation or feedback on testing concerns. Test engineering practices are employed in the DataLens platform backend development. The DataLens platform backend includes the test-engineering skill. The DataLens platform backend integrates the test-engineering skill.

Script for running comprehensive automated tests on the discovery workflow.

The entire batch upload pipeline is end-to-end validated by the test_batch_pipeline_e2e test case.

The DOCX extractor capability is validated by the test_extractors test case. The PPTX extractor capability is validated by the test_extractors test case.

The File prioritizer capability is validated by the test_file_prioritizer test case.

The batch processing pipeline orchestration is validated by the test_progress_status test case.

The Question router capability is validated by the test_question_router test case.