{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/acff991e3da94d5aa4e98dcee0b100e2\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/acff991e3da94d5aa4e98dcee0b100e2-14851ea806de7898.gif","duration":32.36,"title":"33s RAG walkthrough (pgvector HNSW + Gemini)","description":"End-to-end RAG demo of Knowlex, the AI knowledge-retrieval half of craftstack.\n\nShown in 33 seconds:\n- /kb ingest — chunk + embed (gemini-embedding-001, 768 dim)\n- / ask — cosine kNN over pgvector HNSW, streamed Gemini 2.0 Flash answer with numbered citations\n- /api/kb/stats — live index-type probe\n- /docs/api — hand-written OpenAPI 3.1\n\nStack: Next.js 16, Prisma 7, Neon Postgres + pgvector, @ai-sdk/google.\nCompanion: Boardly walkthrough — https://www.loom.com/share/1f6915e588cb4176bfc8272f0f9310bb\nRepo: https://github.com/leagames0221-sys/craftstack"}