GenAI Data Engineering
10 episodes — short audio overviews on genai data engineering.
Document Ingestion with VLMs — chapter audio overview
Build document ingestion pipelines using Docling, Google Document AI, and vision-language models for PDF, HTML, and DOCX extraction with structure preservation.
Parse PDF documents using Docling with layout analysis on CPU — lab audio overview
Use Docling's DocumentConverter to parse PDF documents into structured DoclingDocument representations. Configure the Granite-Docling-258M layout model for CPU-based table and figure detection, extract text with structure preservation, and store parsed metadata in PostgreSQL.
Process DOCX, PPTX, and HTML documents through Docling's unified pipeline — lab audio overview
Extend Docling's DocumentConverter to handle DOCX, PPTX, and HTML input formats through a single unified pipeline. Configure format-specific options, batch-process multiple document types, and normalize outputs into a consistent DoclingDocument structure.
Compare Docling output quality across document types and complexity levels — lab audio overview
Build a quality evaluation framework that compares Docling extraction results across PDF, DOCX, PPTX, and HTML formats. Measure structural fidelity by scoring heading preservation, table extraction accuracy, and content completeness across simple and complex documents.
Define a format-agnostic document schema with typed content blocks — lab audio overview
Design and implement a unified document schema using Pydantic models that normalizes extraction outputs from Docling, VLMs, and Google Document AI into a single format-agnostic representation. Define typed content blocks for text, tables, images, and key-value pairs, along with extraction metadata t
Build extraction-method adapters producing the unified document model — lab audio overview
Build adapter classes that convert raw extraction outputs from Docling, VLMs (via OpenAI/Gemini), and Google Document AI into the unified document model. Implement a factory pattern that selects the correct adapter based on the extraction method name, enabling format-agnostic downstream processing.
Validate the unified model with documents processed by all three methods — lab audio overview
Process the same document through Docling, VLM, and Google Document AI adapters, then validate output compatibility across methods. Build a cross-validator that compares block structures and computes content overlap scores, and a quality report generator that summarizes extraction agreement and high
Implement document classification for extraction method routing — lab audio overview
Build a document classifier that inspects PDF files to determine the optimal extraction method. Analyze documents for text layer presence, layout complexity, and scanned-page detection to produce a DocumentProfile that drives routing decisions.
Build cost-aware routing balancing quality vs API spend per document — lab audio overview
Implement an ExtractionRouter that selects extraction methods based on document complexity and cost constraints. Build a cost tracker that estimates per-document API spend and enforces daily budget limits to prevent runaway costs.
Add fallback chains when primary extraction method fails — lab audio overview
Implement a ResilientRouter that extends extraction routing with fallback chains, confidence-based retry logic, and per-method success/failure metrics. When the primary extraction method fails or returns low-confidence results, the router automatically tries the next method in the fallback chain.