unsloth/studio/backend/core/rag
danielhanchen a357e85c3f Merge branch 'main' into feature/deep-research
Resolve conflicts across the Studio chat stack, keeping both the Deep
Research additions and the attachment-inventory work that landed on main:

- storage/studio_db.py: keep the research schema plus main's chat
  attachment inventory. In sync_chat_messages and upsert_chat_message run
  the inventory refresh and the research-message guard together, and reuse
  main's tombstone reconciliation and chunked prune path while still
  protecting research prompts and responses from deletion. Read the
  inventory-state row positionally so _ensure_schema does not depend on a
  Row factory.
- tests/test_middleware.py: keep both the research port middleware and the
  frontend asset test suites.
- chat/chat-page.tsx: keep the mobile and research composer wiring; drop
  the now-unused useLatestRef import since main's pendingHubAutoLoad
  contextKey check supersedes the ref-based stale-load guard.
- chat/stores/chat-runtime-store.ts: keep the Deep Research toggle state
  and drop the staged-model helpers main removed.
- assistant-ui/thread.tsx: keep the Deep Research composer state, button,
  and availability prop alongside main's composer changes.
2026-07-22 06:10:41 +00:00
..
__init__.py Studio: clean-room compact RAG (knowledge bases, hybrid search, fast indexing) (#5910) 2026-06-09 21:17:04 -07:00
captioner.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
chunking.py Studio: clean-room compact RAG (knowledge bases, hybrid search, fast indexing) (#5910) 2026-06-09 21:17:04 -07:00
config.py Studio: hide the RAG embedder and llama.cpp probe from the hub cached inventory (#7018) 2026-07-19 03:20:56 -07:00
embed_llama_server.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
embeddings.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
ingestion.py Studio: customizable RAG embedding model with HF search, settings tab reorganization (#6800) 2026-07-02 05:26:33 -07:00
locators.py Whole-document context for RAG chat attachments (#6693) 2026-06-30 15:55:23 +02:00
parsers.py Studio: extract text from PDF web results (#7154) 2026-07-16 19:48:12 -03:00
retrieval.py Studio: customizable RAG embedding model with HF search, settings tab reorganization (#6800) 2026-07-02 05:26:33 -07:00
store.py Studio: Data settings tab, uploaded files manager, quant pinning, and chat image preview fix (#7029) 2026-07-20 04:57:44 -07:00
tool.py Whole-document context for RAG chat attachments (#6693) 2026-06-30 15:55:23 +02:00
web_rank.py Studio: read Deep Research synthesis context from the inference orchestrator 2026-07-21 11:05:19 +00:00