feat(search): recherche semantique - embeddings vectoriels + hybride RRF (#70)

backend/main.py

@@ -98,6 +98,7 @@ from backend.search import (
     suggest_tags,
     suggest_titles,
 )
+from backend.semantic_search import init_semantic_index
 from backend.services.backups import diff_backup as service_diff_backup
 from backend.services.backups import get_backup_dir as service_get_backup_dir
 from backend.services.backups import list_backup_files as service_list_backup_files
@@ -281,7 +282,8 @@ class AdvancedSearchResultItem(BaseModel):
     path: str = Field(description="Relative file path")
     title: str = Field(description="File title")
     tags: list[str] = Field(description="File tags")
-    score: float = Field(description="TF-IDF relevance score")
+    score: float = Field(description="TF-IDF relevance score (or fused RRF score in semantic mode)")
+    semantic_score: float = Field(default=0.0, description="Cosine similarity from the semantic index (0 when unavailable)")
     snippet: str = Field(description="Content excerpt with <mark> highlights")
     modified: str = Field(description="ISO 8601 modification timestamp")
     extension: str = Field(default="", description="File extension")
@@ -301,6 +303,7 @@ class AdvancedSearchResponse(BaseModel):
     limit: int = Field(description="Page size")
     facets: SearchFacets = Field(description="Faceted counts by tag and vault")
     query_time_ms: float = Field(default=0, description="Server-side query time in milliseconds")
+    semantic_available: bool = Field(default=False, description="True when the semantic (embedding) index is ready")
 
 
 class TitleSuggestion(BaseModel):
@@ -694,6 +697,8 @@ async def lifespan(app: FastAPI):
         # would freeze HTTP responses if run in the async event loop.
         loop = asyncio.get_running_loop()
         await loop.run_in_executor(_search_executor, init_inverted_index)
+        # Build the semantic (embedding) index in the same background thread pool.
+        await loop.run_in_executor(_search_executor, init_semantic_index)
 
         # Scan for plugins in all vaults
         logger.info("Scanning for plugins...")
@@ -2589,6 +2594,7 @@ async def api_advanced_search(
     created: str | None = Query(None, description="Created date filter (>date, <date, date..date)"),
     modified: str | None = Query(None, description="Modified date filter (>date, <date, date..date, <Nd)"),
     size: str | None = Query(None, description="Size filter (>size, <size, size..size, e.g. >1MB, <10KB)"),
+    semantic: bool = Query(False, description="Fuse TF-IDF with semantic embeddings (RRF)"),
     current_user=Depends(require_auth),
 ):
     """Advanced full-text search with TF-IDF scoring, facets, and pagination.
@@ -2605,6 +2611,8 @@ async def api_advanced_search(
     - Remaining text is scored using TF-IDF with accent normalization.
     - Toggles: case_sensitive, whole_word, regex
     - Path filters: include_paths, exclude_paths (glob patterns)
+    - ``semantic=true`` — fuse the TF-IDF ranking with the semantic (embedding)
+      ranking via Reciprocal Rank Fusion and expose ``semantic_score`` per result.
 
     Results include ``<mark>``-highlighted snippets and faceted tag/vault counts.
     """
@@ -2615,7 +2623,7 @@ async def api_advanced_search(
                 limit=limit, offset=offset, sort=sort,
                 case_sensitive=case_sensitive, whole_word=whole_word, regex=regex,
                 include_paths=include_paths, exclude_paths=exclude_paths,
-                created=created, modified=modified, size=size),
+                created=created, modified=modified, size=size, semantic=semantic),
     )