unsloth/studio/frontend/src
Roland Tannous 4c1ab745d6 Studio: schema + API plumbing for per-KB chunking strategy + mode
Phase 3 lays two orthogonal per-KB knobs in the data and API layers so
follow-up commits (Phase 3B-late, Phase 3B-multimodal) only need to add
their code path and UI selector, not schema or types.

Schema (studio/backend/storage/studio_db.py)
- rag_knowledge_bases gains chunking_strategy ('standard'|'late', default
  'standard') and mode ('text'|'multimodal', default 'text'). Both are
  immutable after KB creation — changing either invalidates existing
  chunks because they were ingested through a specific pipeline.
- rag_chunks gains kind ('text'|'image'|'caption', default 'text'),
  image_path (NULLABLE), linked_chunk_id (NULLABLE) — used by Phase
  3B-multimodal to pair image chunks with their captions.
- Idempotent ALTER TABLE additions for existing installs (mirrors the
  chat_threads display_name / *_code_exec_container_id pattern earlier
  in the file).

API (studio/backend/routes/rag.py)
- ChunkingStrategy + KBMode Literal aliases.
- CreateKBRequest accepts both fields with backward-compat defaults.
- KBResponse exposes both.
- _validate_mode_combo rejects (multimodal, late) with 400 — no public
  open-weight embedder supports both at once. Surface the constraint
  early rather than failing silently during ingestion.

Config (studio/backend/utils/rag/config.py)
- RAG_EMBEDDER_MATRIX dict keyed by (mode, strategy) → embedder name.
- resolve_embedder() helper falls back to RAG_EMBEDDING_MODEL for legacy
  KBs that pre-date the columns.
- (multimodal, late) intentionally absent.

Frontend (studio/frontend/src/features/rag/)
- api/rag-api.ts: ChunkingStrategy + KBMode types; KnowledgeBase
  interface and createKnowledgeBase request type updated.
- stores/rag-store.ts: createKB signature uses the shared request type.

No user-visible UI changes yet — the only currently-usable combination
is (text, standard), so adding one-option selectors would be UX noise.
Phase 3B-late and Phase 3B-multimodal each add the relevant selector
option as part of shipping the code path.
2026-05-24 11:54:38 +04:00
..
app Studio: add RAG with hybrid search, reranker, chat integration 2026-05-23 18:46:15 +04:00
assets Final cleanup 2026-03-12 18:28:04 +00:00
components Truncate long code execution tool output (#5708) 2026-05-22 07:45:58 -07:00
config feat(studio): add Continued Pretraining (CPT) as a training method (#4677) 2026-05-06 13:38:35 +04:00
features Studio: schema + API plumbing for per-KB chunking strategy + mode 2026-05-24 11:54:38 +04:00
hooks studio: engage draft-mtp on vision MTP GGUFs (drop incorrect vision gate) (#5560) 2026-05-18 08:42:55 -07:00
lib studio: fix toast close-button click and light-mode hover (#5597) 2026-05-19 00:55:55 -07:00
shared studio/frontend: make toast and inline error text selectable and copyable (#5506) 2026-05-18 03:47:21 -07:00
stores Update license headers 2026-03-12 17:23:10 +00:00
types feat(studio): add Continued Pretraining (CPT) as a training method (#4677) 2026-05-06 13:38:35 +04:00
utils Update license headers 2026-03-12 17:23:10 +00:00
index.css studio: respect prefers-reduced-motion across animations (#5611) 2026-05-19 06:45:36 -07:00
main.tsx chat only with gguf for mac devices (#4300) 2026-03-15 23:20:48 +04:00
speech-recognition.d.ts Update license headers 2026-03-12 17:23:10 +00:00