feat(rag): add IngestedDocument model and persist uploaded PDF metadata to database

[Pcmhacker-piro]

Summary

Closes #578

Adds an IngestedDocument database model and Alembic migration to persist metadata about uploaded regulatory PDFs in the RAG Intelligence module. The POST /api/v1/rag/ingest endpoint now records filename, SHA-256 hash, file size, and chunk count for each uploaded document. The vector store is updated to merge new documents into the existing FAISS index (via merge_into_vector_store) instead of rebuilding from scratch, preserving previously ingested content.

Type of Change

• Bug fix
• New feature
• Documentation update
• Refactor
• Tests
• Infra / CI

Checklist

• I have read CONTRIBUTING.md
• My code follows the project style
• I have added/updated tests where relevant
• Tests/lint pass locally (if available)
• I have not committed .env or any secrets
• I have updated documentation if needed

Screenshots (if UI change)

N/A - Backend-only feature
CHANGED FILES

• backend/app/api/v1/rag.py - Updated ingest endpoint to use merge_into_vector_store and persist IngestedDocument records
• backend/app/models/init.py - Registered IngestedDocument model
• backend/app/models/ingested_document.py - New IngestedDocument ORM model with SourceType enum
• backend/app/modules/rag/vector_store.py - Added merge_into_vector_store() to merge new docs into existing FAISS index
• backend/alembic/versions/c8d4b0f6a2e1_add_ingested_documents_table.py - New Alembic migration for ingested_documents table
• backend/tests/test_rag_ingest.py - Updated patch targets to match renamed function
  COMMITS
• 28355b4 - feat(rag): add IngestedDocument model and persist uploaded PDF metadata to database
  TESTING PERFORMED
• git diff --stat verified only intended files changed
• No unrelated modifications detected
  FINAL STATUS
• Branch Name: fix/rag-ingested-document-tracking
• Commit Hash: 28355b4
• PR Created: Yes (via fork URL - requires manual PR creation due to token scope)
• Ready for Review: Yes

[Pcmhacker-piro]

@SdSarthak

the checks have passed. Could you please review and approve the pending workflows when you have a chance? Thank you!