RAG Pipeline Logic

Ingestion

• Script: backend/ingest.py
• Process:
  1. Scans docs/.
  2. Cleans MDX (removes frontmatter/imports).
  3. Chunks text (1000 chars, 100 overlap).
  4. Embeds using models/text-embedding-004.
  5. Upserts to Qdrant collection physical_ai_book.
• Run: python backend/ingest.py

Vector Search (Qdrant)

• Client: qdrant-client
• Collection: physical_ai_book
• Vector Size: 768 (Gecko-004)
• Similarity: Cosine