Initial commit: library-desk service extraction from portainer-core

src/models/vector.py

@@ -0,0 +1,100 @@
+"""
+Vector models for Library Desk Qdrant operations.
+
+Provides models for semantic search, document chunks, and embeddings.
+"""
+
+from pydantic import BaseModel, Field
+from typing import List, Dict, Any, Optional
+
+
+class DocumentChunk(BaseModel):
+    """Document chunk with embedding."""
+    chunk_id: str = Field(..., description="Unique chunk ID (page_id:chunk_index)")
+    page_id: int = Field(..., description="Wiki page ID")
+    chunk_index: int = Field(..., description="Chunk index within document")
+    content: str = Field(..., description="Chunk text content")
+    metadata: Dict[str, Any] = Field(default_factory=dict, description="Additional metadata")
+
+
+class SearchResult(BaseModel):
+    """Semantic search result."""
+    chunk_id: str = Field(..., description="Chunk ID")
+    page_id: int = Field(..., description="Wiki page ID")
+    page_title: Optional[str] = Field(None, description="Page title")
+    page_path: Optional[str] = Field(None, description="Page path")
+    chunk_index: int = Field(..., description="Chunk index")
+    content: str = Field(..., description="Chunk content")
+    score: float = Field(..., description="Similarity score (0-1)")
+    metadata: Dict[str, Any] = Field(default_factory=dict, description="Additional metadata")
+
+
+class SearchRequest(BaseModel):
+    """Semantic search request."""
+    query: str = Field(..., min_length=1, description="Search query")
+    user: str = Field(default="jpmschweitzer", description="User identifier")
+    limit: int = Field(default=10, ge=1, le=100, description="Maximum results")
+    score_threshold: float = Field(default=0.5, ge=0.0, le=1.0, description="Minimum similarity score")
+
+
+class SearchResponse(BaseModel):
+    """Semantic search response."""
+    query: str = Field(..., description="Search query")
+    results: List[SearchResult] = Field(..., description="Search results")
+    total: int = Field(..., description="Number of results")
+    user: str = Field(..., description="User filter applied")
+
+
+class VectorUpdateRequest(BaseModel):
+    """Request to update vectors from a wiki page."""
+    page_id: int = Field(..., description="Wiki page ID to process")
+    user: str = Field(
+        default="jpmschweitzer",
+        description="User identifier for namespace scoping"
+    )
+    force_refresh: bool = Field(
+        default=False,
+        description="Force re-embedding even if page hasn't changed"
+    )
+
+
+class VectorUpdateSummary(BaseModel):
+    """Summary of vector update operation."""
+    page_id: int = Field(..., description="Page ID processed")
+    page_title: str = Field(..., description="Page title")
+    chunks_created: int = Field(default=0, description="New chunks created")
+    chunks_updated: int = Field(default=0, description="Existing chunks updated")
+    chunks_deleted: int = Field(default=0, description="Old chunks deleted")
+    total_chunks: int = Field(default=0, description="Total chunks for this page")
+    embedding_dim: int = Field(default=768, description="Embedding dimensionality")
+    processing_time_ms: float = Field(..., description="Processing time in milliseconds")
+    success: bool = Field(default=True, description="Whether update succeeded")
+    error_message: Optional[str] = Field(default=None, description="Error message if failed")
+
+
+class CollectionInfo(BaseModel):
+    """Qdrant collection information."""
+    name: str = Field(..., description="Collection name")
+    vectors_count: int = Field(..., description="Number of vectors")
+    points_count: int = Field(..., description="Number of points")
+    segments_count: int = Field(..., description="Number of segments")
+
+
+class CollectionListResponse(BaseModel):
+    """List of Qdrant collections."""
+    collections: List[CollectionInfo] = Field(..., description="List of collections")
+    total: int = Field(..., description="Total number of collections")
+
+
+class DeletePageChunksRequest(BaseModel):
+    """Request to delete all chunks for a page."""
+    page_id: int = Field(..., description="Wiki page ID")
+    user: str = Field(default="jpmschweitzer", description="User identifier")
+
+
+class DeletePageChunksResponse(BaseModel):
+    """Response from deleting page chunks."""
+    page_id: int = Field(..., description="Page ID")
+    chunks_deleted: int = Field(..., description="Number of chunks deleted")
+    success: bool = Field(..., description="Whether deletion succeeded")
+    message: str = Field(..., description="Result message")