JOX — ETL with LLM
Intelligent ETL pipeline for structured data extraction from agricultural bulletins in PDF using LLM with structured output.
The Problem
Daily agricultural bulletins in PDF without structure, requiring manual reading to extract quotes and news relevant to the business.
The Solution
LLM structured output with automatic retry and invalid JSON repair, Pydantic v2 validation, date-based idempotency, complete auditing and typed Gold layer for Power BI.
Result
Automated daily extraction with 100% idempotency, structured data in Delta Tables ready for BI consumption.
Related Projects
MeteoRAG
Intelligent weather assistant with RAG combining real-time INMET API data with LLMs for natural language queries.
Melisso AI Agent
AI conversational assistant embedded in the portfolio — Claude Haiku streaming, Redis rate limiting and animated interface.