The extraction pipeline's source inventory includes client folders from Drive consisting of more than 80 files in DOCX, PPTX, XLSX, and PDF formats targeted to the CLIENTS and PROJECTS sets so that client and project knowledge can be extracted from mixed-format records.

| Client folders (Drive) | ~80+ files | .docx, .pptx, .xlsx, .pdf | CLIENTS, PROJECTS |

— PYRANA_Internal_Knowledge_Graph_Specification.md

### 6.1 Source Document Inventory

— PYRANA_Internal_Knowledge_Graph_Specification.md

Source Category | File Count | Primary Formats | Target Sets

— PYRANA_Internal_Knowledge_Graph_Specification.md