ab0828b976
Backend: - Deterministic SQLite connection cleanup. The RAG code used bare `with get_connection() as conn:`, which commits but never closes, leaning on GC to release handles (the rest of studio_db closes explicitly). Add a closing_connection() context manager that commits/rolls back like sqlite3's own manager and always closes, and route all 30 RAG call sites through it. - filter_by_min_score no longer drops BM25-only and figure-ref hits. min_score is a cosine floor, so it now gates only hits that carry a dense_score; lexical and figure-ref hits (dense_score is None) pass through instead of being silently discarded when the floor is raised. - Fix two tests that could not pass against the production code: the RRF fusion test asserted the wrong winner (c edges out b: 0.032266 vs 0.032258), and two tool-handler scope tests stubbed retrieve_hybrid without accepting the embedder_model kwarg the handler now passes (TypeError was swallowed, leaving captured["scope"] unset). Frontend: - Removing an in-flight upload chip now routes through the teardown thunk already registered for the aggregate-progress toast (abort, unsubscribe, release the index slot, delete the backend doc with the correct kb/thread scope key it closed over) and clears the toast entry. Deleting directly leaked the concurrency slot and hardcoded the thread scope, mis-targeting KB-scoped docs. Applied in both the composer hook and the compare-view composer; drop the now-vestigial chip-scope-key tracking and unused activeThreadId selectors. Add index-progress-store.remove(id).
49 lines
1.8 KiB
Python
49 lines
1.8 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""Scope identifiers (kb_<id> / thread_<id>) + per-scope embedder resolver."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from storage.studio_db import closing_connection, list_chat_settings
|
|
from utils.rag.config import resolve_embedder
|
|
|
|
RAG_DEFAULTS_KEY = "rag.defaults"
|
|
|
|
|
|
def thread_settings_key(thread_id: str) -> str:
|
|
return f"thread:{thread_id}:rag"
|
|
|
|
|
|
def resolve_scope_embedder(scope: str) -> str | None:
|
|
"""KB → kb.embedding_model; thread → per-thread/defaults/matrix. None = use default."""
|
|
if scope.startswith("kb_"):
|
|
kb_id = scope[len("kb_") :]
|
|
with closing_connection() as conn:
|
|
row = conn.execute(
|
|
"SELECT embedding_model FROM rag_knowledge_bases WHERE id = ?",
|
|
(kb_id,),
|
|
).fetchone()
|
|
return row["embedding_model"] if row else None
|
|
|
|
if scope.startswith("thread_"):
|
|
thread_id = scope[len("thread_") :]
|
|
all_settings = list_chat_settings()
|
|
defaults = all_settings.get(RAG_DEFAULTS_KEY) or {}
|
|
if not isinstance(defaults, dict):
|
|
defaults = {}
|
|
per_thread = all_settings.get(thread_settings_key(thread_id)) or {}
|
|
if not isinstance(per_thread, dict):
|
|
per_thread = {}
|
|
explicit = per_thread.get("embedding_model") or defaults.get("embedding_model")
|
|
if explicit:
|
|
return explicit
|
|
mode = per_thread.get("mode") or defaults.get("mode") or "text"
|
|
chunking_strategy = (
|
|
per_thread.get("chunking_strategy")
|
|
or defaults.get("chunking_strategy")
|
|
or "standard"
|
|
)
|
|
return resolve_embedder(mode, chunking_strategy)
|
|
|
|
return None
|