# half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation architecture

> Architecture diagram of the GitHub repository half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation
- Repository: https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation

## Overview

This repository is a document-ingestion and handloom-knowledge preparation project; the README names a virtual-reality museum, but the available implementation is focused on preparing knowledge content rather than museum navigation. The principal workflow discovers raw documents, extracts and cleans text, forms sections, tracks document versions, and can generate OKF knowledge files. Chunking is an additional capability. The graph reflects the shown ingestion calls and documented component behavior; it does not assume an unshown application or runtime connection to chunking or OKF generation.

Main entry points: [`script_ingestion/ingestion/processing.py`](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/processing.py) (Ingestion Processor), [`script_ingestion/extraction.py`](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/extraction.py) (PDF Extraction), [`script_ingestion/knowledge/okf.py`](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/okf.py) (OKF Generator), [`script_ingestion/ingestion/manifest.py`](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/manifest.py) (Document Registry)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_ingestion["Ingestion"]
  node_pdf_extract["PDF Extraction<br/>[extraction.py]"]
  node_cleaning["Text Cleaning<br/>[cleaning.py]"]
  node_discovery["File Discovery<br/>[discovery.py]"]
  node_processor["Ingestion Processor<br/>[processing.py]"]
  node_registry[("Document Registry<br/>[manifest.py]")]
  node_manifest_file["Manifest File"]
end

subgraph group_modeling["Knowledge Modeling"]
  node_identity["Document Identity<br/>[document.py]"]
  node_normalized["Normalized Documents<br/>[normalized.py]"]
  node_sections["Document Sections<br/>[section.py]"]
end

subgraph group_knowledge["Knowledge Outputs"]
  node_okf_generator["OKF Generator<br/>[okf.py]"]
  node_okf_files["OKF Knowledge Files"]
  node_chunker["Text Chunking<br/>[chunking.py]"]
end

subgraph group_sources["Knowledge Sources"]
  node_raw["Raw Documents"]
  node_markdown["Markdown Text"]
  node_okf_sources["OKF Process Sources"]
end

node_raw -->|"extracts PDFs"| node_pdf_extract
node_pdf_extract -->|"writes Markdown"| node_markdown
node_processor -->|"discovers files"| node_discovery
node_processor -->|"extracts PDF text"| node_pdf_extract
node_processor -->|"normalizes text"| node_cleaning
node_processor -->|"creates sections"| node_sections
node_processor -->|"builds documents"| node_normalized
node_processor -->|"hashes and creates"| node_identity
node_processor -->|"checks and updates"| node_registry
node_registry -->|"loads and saves"| node_manifest_file
node_okf_generator -->|"formats sections"| node_sections
node_okf_generator -->|"writes knowledge files"| node_okf_files
node_chunker -->|"can parse OKF"| node_okf_sources

click node_raw "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/tree/main/knowledge_base/01_raw_data"
click node_pdf_extract "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/extraction.py"
click node_cleaning "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/cleaning.py"
click node_discovery "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/discovery.py"
click node_processor "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/processing.py"
click node_registry "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/manifest.py"
click node_manifest_file "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/knowledge_base/document_manifest.json"
click node_identity "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/document.py"
click node_normalized "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/normalized.py"
click node_sections "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/section.py"
click node_okf_generator "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/okf.py"
click node_okf_files "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/tree/main/knowledge_base/04_okf/processes"
click node_chunker "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/chunking.py"
click node_okf_sources "https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/tree/main/knowledge_base/04_okf/processes"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_pdf_extract,node_cleaning,node_discovery,node_processor,node_registry,node_manifest_file toneBlue
class node_identity,node_normalized,node_sections toneAmber
class node_okf_generator,node_okf_files,node_chunker toneMint
class node_raw,node_markdown,node_okf_sources toneRose
```

## Components

### Ingestion

- [PDF Extraction](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/extraction.py): `script_ingestion/extraction.py`
- [Text Cleaning](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/cleaning.py): `script_ingestion/cleaning.py`
- [File Discovery](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/discovery.py): `script_ingestion/ingestion/discovery.py`
- [Ingestion Processor](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/processing.py): `script_ingestion/ingestion/processing.py`
- [Document Registry](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/ingestion/manifest.py): `script_ingestion/ingestion/manifest.py`
- [Manifest File](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/knowledge_base/document_manifest.json): `knowledge_base/document_manifest.json`

### Knowledge Modeling

- [Document Identity](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/document.py): `script_ingestion/knowledge/document.py`
- [Normalized Documents](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/normalized.py): `script_ingestion/knowledge/normalized.py`
- [Document Sections](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/section.py): `script_ingestion/knowledge/section.py`

### Knowledge Outputs

- [OKF Generator](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/okf.py): `script_ingestion/knowledge/okf.py`
- [OKF Knowledge Files](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/tree/main/knowledge_base/04_okf/processes): `knowledge_base/04_okf/processes`
- [Text Chunking](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/blob/main/script_ingestion/knowledge/chunking.py): `script_ingestion/knowledge/chunking.py`

### Knowledge Sources

- [Raw Documents](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/tree/main/knowledge_base/01_raw_data): `knowledge_base/01_raw_data`
- **Markdown Text**
- [OKF Process Sources](https://github.com/half-pace/multimodal-agentic-ai-framework-for-virtual-reality-museum-navigation/tree/main/knowledge_base/04_okf/processes): `knowledge_base/04_okf/processes`

## Connections

- Raw Documents → PDF Extraction: extracts PDFs (evidence: `script_ingestion/extraction.py`)
- PDF Extraction → Markdown Text: writes Markdown (evidence: `script_ingestion/extraction.py`)
- Ingestion Processor → File Discovery: discovers files (evidence: `script_ingestion/ingestion/processing.py`)
- Ingestion Processor → PDF Extraction: extracts PDF text (evidence: `script_ingestion/ingestion/processing.py`)
- Ingestion Processor → Text Cleaning: normalizes text (evidence: `script_ingestion/ingestion/processing.py`)
- Ingestion Processor → Document Sections: creates sections (evidence: `script_ingestion/ingestion/processing.py`)
- Ingestion Processor → Normalized Documents: builds documents (evidence: `script_ingestion/ingestion/processing.py`)
- Ingestion Processor → Document Identity: hashes and creates (evidence: `script_ingestion/ingestion/processing.py`)
- Ingestion Processor → Document Registry: checks and updates (evidence: `script_ingestion/ingestion/processing.py`)
- Document Registry → Manifest File: loads and saves (evidence: `script_ingestion/ingestion/manifest.py`)
- OKF Generator → Document Sections: formats sections (evidence: `script_ingestion/knowledge/okf.py`)
- OKF Generator → OKF Knowledge Files: writes knowledge files (evidence: `script_ingestion/knowledge/okf.py`)
- Text Chunking → OKF Process Sources: can parse OKF (evidence: `script_ingestion/knowledge/chunking.py`)
