# Document RAG Pipeline Architecture

> Sub-skill of document-rag-pipeline: Architecture.

- Skill: `vamseeachanta/document-rag-pipeline-architecture` (Agent Skill)
- Install (CLI): `npx skillmds@latest add vamseeachanta/document-rag-pipeline-architecture`
- Raw SKILL.md: https://api.skillmd.com/api/skills/vamseeachanta/document-rag-pipeline-architecture/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: vamseeachanta (https://skillmd.com/u/vamseeachanta)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/vamseeachanta/document-rag-pipeline-architecture

---


# Architecture

## Architecture


```
Document Folder
      │
      ▼
┌─────────────────────┐
│ 1. Build Inventory  │  SQLite catalog of all files
└──────────┬──────────┘
           ▼
┌─────────────────────┐
│ 2. Extract Text     │  PyMuPDF for regular PDFs
└──────────┬──────────┘
           ▼
┌─────────────────────┐
│ 3. OCR Scanned PDFs │  Tesseract + pytesseract
└──────────┬──────────┘
           ▼
┌─────────────────────┐
│ 4. Chunk Text       │  1000 chars, 200 overlap
└──────────┬──────────┘
           ▼
┌─────────────────────┐
│ 5. Generate Embeds  │  sentence-transformers
└──────────┬──────────┘
           ▼
┌─────────────────────┐
│ 6. Semantic Search  │  Cosine similarity
└─────────────────────┘
```

