The SVGV bulk extraction process processes the 132 SVGV files to extract data into DuckDB tables The Backend container runs the SVGV bulk extraction process to parse files and store data

Telegram bot operates on the Telegram platform. DataLens Skill integrates with Telegram to provide user interface access. DataLens Skill integrates with Telegram to receive file uploads and user queries. DataLens Skill handles user requests via Telegram interface on theo.

The FastAPI backend exposes a Text-to-SQL query API for natural language queries. Text-to-SQL incorporates the natural language to SQL pipeline for query translation.

The TextToSQLService class is defined within backend/app/services/text_to_sql.py. The TextToSQLService class integrates with the Ollama API for LLM-based SQL generation. The generate_sql method is part of the Text-to-SQL Service.

The Unified /ask endpoint uses the Question router to process queries, replacing the SQL-only /query endpoint. The unified ask use case is realized by the Unified /ask endpoint integrating structured and semantic querying.

The unified question interface routes structured queries to DuckDB SQL within DataLens. The unified question interface routes semantic search queries via Qdrant in DataLens. The Unified analysis page implements the unified question interface providing a combined SQL and semantic query experience. The unified ask use case is realized by the Unified /ask endpoint integrating structured and semantic querying. The unified ask capability is realized in Phase C, which provides a unified question interface combining SQL and semantic routing.

Text-to-SQL integrates with Vanna.AI. Vanna 2.0 implements user-aware identity propagation through system prompts, tool execution, and SQL filtering for permissions. Vanna 2.0 implements a Tool Registry that supports extensible tools with access control via access_groups. Vanna 2.0 provides streaming server-sent events responses with progress updates and structured UI components. Vanna 2.0 implements lifecycle hooks for quota checking, logging, and content filtering at request lifecycle points. Vanna 2.0 enforces row-level security by filtering queries based on user permissions. Vanna 2.0 maintains audit logs tracking every query per user for compliance purposes. SQLAgent integrates with Vanna.AI for SQL generation from natural language questions. The architecture comparison with Vanna 2.0 and WrenAI validates architectural design decisions related to Vanna 2.0. DataLens provides a native Text-to-SQL endpoint that covers functionality similar to Vanna AI in the SVGV Budget Analysis Project ecosystem. The Text-to-SQL capability integrates with the external system Vanna.AI for best practice implementations and query optimization. The Text-to-SQL Agent integrates with Vanna.AI to generate SQL queries from natural language. Vanna AI and DataLens are functionally equivalent in providing Text-to-SQL capabilities, but DataLens includes a built-in Text-to-SQL API. Vanna.AI integrates schema and documents embedding into ChromaDB.

DataLens Agent Mode uses WebSocket for real-time communication with IronClaw.

XLSX file uploaded successfully via POST /files/upload?project_id=4 endpoint