diff --git a/ynr/apps/sopn_parsing/sopn_processing.mermaid b/ynr/apps/sopn_parsing/sopn_processing.mermaid new file mode 100644 index 000000000..42b486a60 --- /dev/null +++ b/ynr/apps/sopn_parsing/sopn_processing.mermaid @@ -0,0 +1,38 @@ +```mermaid + graph TD + --- + title: sopn processing + --- + + flowchart LR + id + subgraph Input + A[Input Documents (PDFs, Non-PDFs)] + end + + subgraph Preprocessing + B[Document Preprocessing] + B --> C[Document Conversion] + B --> D[Page Matching] + B --> E[Page Extraction] + end + + subgraph Parsing + F[Text Parsing] + G[Metadata Extraction] + H[Content Analysis] + I --> J + K --> L + end + + subgraph Output + H[Structured Data] + end + + A --> B + C --> E + D --> E + E --> H + F --> H + G --> H +``` \ No newline at end of file