Agentic AI Reference Architecture

Knowledge & Data · Software component

Document Ingestor

Software componentKnowledge & DataKnowledge & Dataarc:DocumentIngestor

A component that extracts text, tables and chart values from source documents such as PDFs into structured data.

Responsibility. Extracts content from source documents.

Also known as: PDF extractor, Table parser, Bulk document ingestion, Document content extractor, Image page detector, Binary document parser, Office document parser, OCR extractor, Document processing, PDF parsing

is orchestrated bysends data tosends data tosends data tosends data tois invoked bydeployed onreadsinvokesis invoked bywritesIngestion Pipeline Orchestrator: is orchestrated byIngestion Pipeline Orche…Document Chunker: sends data toDocument ChunkerPerception Interpreter: sends data toPerception InterpreterData Quality Validator: sends data toData Quality ValidatorMultimodal Content Router: sends data toMultimodal Content RouterKnowledge Base Refresher: is invoked byKnowledge Base RefresherSpot GPU Node: deployed onSpot GPU NodeKnowledge Source System: readsKnowledge Source SystemChart Data Extractor: invokesChart Data ExtractorFile Store Extractor: is invoked byFile Store ExtractorSource Media Store: writesSource Media Store
Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

invokes dependency

is invoked by dependency

reads dependency

writes dependency

sends data to dynamic

is orchestrated by control

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Patterns
OCR for scanned PDFsBoilerplate-filtering HTML parsing
Technologies
LlamaIndex MultiModalpypdfpython-docxpython-pptx
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Corrupted tables from PDF extraction errorsDate and jurisdiction metadata parsing failuresPDF extraction converting charts to vague alt-text or skipping them

Sources

  1. Ch1.4: T. Nguyen, "Memory and Perception Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.4. ISBN: 9798244538229.
  2. Ch1.8: T. Nguyen, "Scalability and Production Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.8. ISBN: 9798244538229.
  3. Ch2.7: T. Nguyen, "Multimodal RAG Approaches," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.7. ISBN: 9798244538229.
  4. Ch3.10: T. Nguyen, "Efficiency Metrics," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.10. ISBN: 9798244538229.
  5. Ch6.3A: T. Nguyen, "ETL Pipeline Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.3A. ISBN: 9798244538229.
  6. Ch6.4: T. Nguyen, "Data Quality Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.4. ISBN: 9798244538229.
  7. Ch6.5: T. Nguyen, "Production RAG Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.5. ISBN: 9798244538229.
  8. Ch7.5: T. Nguyen, "NeMo Curator, Riva Speech AI & Multimodal Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.5. ISBN: 9798244538229.
  9. Ref2.07: NVIDIA Developer, "Building multimodal AI RAG with LlamaIndex, NVIDIA NIM, and Milvus | LLM app development," YouTube. Accessed: Sep. 26, 2026. [Online Video]. Available: https://www.youtube.com/watch?v=NaT5Eo97_I0