unsloth/tests/python
Roland Tannous d9dfc7db80 Studio: re-ingest existing KBs / threads with new settings (Backfill UX)
Closes the upgrade-path gap from Phase 3: a KB or thread whose chunks
were ingested under one strategy can now be rebuilt under a different
one without losing the uploaded files.

Backend
- routes/rag.py:
  - POST /api/rag/knowledge-bases/{kb_id}/reingest takes optional
    chunking_strategy / mode / embedding_model in the body. Validates
    the (multimodal, late) constraint via _validate_mode_combo, updates
    the rag_knowledge_bases row, wipes scope artifacts (sqlite chunks
    via cascade, Qdrant collection, bm25), and re-INSERTs a fresh
    rag_documents row + ingestion job per stored file. Returns the new
    job IDs so callers can stream progress via the existing SSE.
  - POST /api/rag/threads/{thread_id}/reingest is the simpler thread
    variant — no body, rebuilds with current defaults.
  - Shared _reingest_scope helper strips the UUID upload prefix when
    re-naming docs so users see the original filenames again.

Frontend
- rag-api.ts: reingestKnowledgeBase(kbId, opts) and
  reingestThreadDocuments(threadId) wrappers + ReingestResponse type.
- rag-store.ts: reingestKB / reingestThread actions refresh the KB +
  doc lists and subscribe to every returned job so the existing
  IngestionProgress chips render without further wiring.
- kb-reconfigure-dialog.tsx (new): mirrors KBCreateDialog but
  pre-fills with the KB's current strategy / mode / embedder, enforces
  the same (multimodal + late) constraint with disabled options, and
  confirms before submitting. Submit label flips between "Re-index"
  (no settings change) and "Reconfigure & re-index".
- kb-detail-panel.tsx: header gains the chunking + mode summary and
  a "Reconfigure…" button that opens the dialog. Button is disabled
  when the KB has no documents.
- chat-settings-sheet.tsx Retrieval section: "Re-index" button beside
  the existing "Clear thread index" when the thread has documents.

Tests
- test_rag_reingest.py: ReingestKBRequest accepts optional fields,
  rejects unknown enum values via Pydantic, and the shared mode-combo
  guard still bites on the reingest path.
2026-05-24 12:41:55 +04:00
..
__init__.py Consolidate dual venvs and separate install from update (#4530) 2026-03-25 05:24:21 -07:00
conftest.py fix: add tokenizers to no-torch deps and TORCH_CONSTRAINT for arm64 macOS py313+ (#4748) 2026-04-01 06:12:17 -07:00
test_cross_platform_parity.py Add configurable PyTorch mirror via UNSLOTH_PYTORCH_MIRROR env var (#5024) 2026-04-15 11:39:11 +04:00
test_dpo_vision_processor_passthrough.py Fix DPO trainer multi process hang (#5199) 2026-04-29 04:15:34 -07:00
test_e2e_no_torch_sandbox.py tests: add no-torch / Intel Mac test suite (#4646) 2026-03-27 02:33:45 -07:00
test_fast_sentence_transformer_redirect_lifecycle.py Add Studio PR-time CI: pin enforcement, frontend, backend, wheel smoke (#5298) 2026-05-06 04:41:57 -07:00
test_flash_attn_install_python_stack.py studio: skip flash-attn install on Blackwell GPUs (sm_100+) (#5420) 2026-05-14 18:13:50 +04:00
test_gpu_init_ldconfig_guard.py feat(studio): MLX training tab on Apple Silicon (LoRA / full FT, VLM, export) (#5265) 2026-05-05 23:54:58 -07:00
test_install_python_stack.py Consolidate dual venvs and separate install from update (#4530) 2026-03-25 05:24:21 -07:00
test_no_torch_filtering.py [Studio] Install flash attn at setup time for linux (#4979) 2026-04-14 16:40:17 +04:00
test_orpo_processor_text_tokenizer.py Fix ORPO text-only tokenization with processors (#5501) 2026-05-18 00:40:30 -07:00
test_patch_trl_rl_trainers_defensive.py fix: unblock 4 tests deselected/skipped in #5312 (real bugs) (#5359) 2026-05-11 02:39:17 -07:00
test_rag_bm25.py Studio: add RAG with hybrid search, reranker, chat integration 2026-05-23 18:46:15 +04:00
test_rag_chunking.py Studio: layout-aware RAG parsers + heading-aware chunking (Phase 3A) 2026-05-24 11:10:13 +04:00
test_rag_late_chunking.py Studio: late chunking opt-in per KB (Phase 3B-late) 2026-05-24 12:18:09 +04:00
test_rag_multimodal.py Studio: multimodal RAG mode (Phase 3B-multimodal) 2026-05-24 12:33:08 +04:00
test_rag_parsers.py Studio: layout-aware RAG parsers + heading-aware chunking (Phase 3A) 2026-05-24 11:10:13 +04:00
test_rag_reingest.py Studio: re-ingest existing KBs / threads with new settings (Backfill UX) 2026-05-24 12:41:55 +04:00
test_rag_reranker.py Studio: add RAG with hybrid search, reranker, chat integration 2026-05-23 18:46:15 +04:00
test_rag_retrieval.py Studio: add RAG with hybrid search, reranker, chat integration 2026-05-23 18:46:15 +04:00
test_rag_vector_store.py Studio: add RAG with hybrid search, reranker, chat integration 2026-05-23 18:46:15 +04:00
test_studio_import_no_torch.py tests: add no-torch / Intel Mac test suite (#4646) 2026-03-27 02:33:45 -07:00
test_tokenizers_and_torch_constraint.py fix: add tokenizers to no-torch deps and TORCH_CONSTRAINT for arm64 macOS py313+ (#4748) 2026-04-01 06:12:17 -07:00
test_unsloth_run_tool_policy_resolver.py unsloth run: add --enable-tools/--disable-tools server-side tool policy (#5277) 2026-05-05 12:45:15 +04:00