Chris Coutinho
8f45e996e8
Implements background vector database synchronization using anyio TaskGroups for BasicAuth mode with single-user credentials. Scanner Implementation: - Periodic document discovery (hourly, configurable) - Timestamp-based change detection (Nextcloud vs Qdrant) - Wake event for immediate scanning on-demand - Supports both initial sync (all docs) and incremental sync (changes only) - Detects deleted documents and queues for removal Processor Implementation: - Concurrent document processing pool (3 workers default) - I/O-bound embedding generation via Ollama API - Retry logic with exponential backoff (3 retries) - Document chunking (512 words, 50-word overlap) - Handles both index and delete operations - Upserts vectors to Qdrant with rich metadata App Lifespan Integration: - Extended AppContext with background task state - Modified app_lifespan_basic() to start tasks via anyio TaskGroups - Graceful shutdown with coordinated task cancellation - Only activates when VECTOR_SYNC_ENABLED=true Embedding Service: - OllamaEmbeddingProvider with TLS support - Singleton pattern for shared client instances - Batch embedding support for efficiency - Auto-detects embedding dimension (768 for nomic-embed-text) Qdrant Client: - Async client wrapper with singleton pattern - Auto-creates collection on first use - COSINE distance metric for semantic similarity - Integrates with embedding service for dimension detection Health Check Enhancement: - Added Qdrant status check to /health/ready endpoint - Only checks when VECTOR_SYNC_ENABLED=true - 2-second timeout for health probe - Reports connection errors with details Configuration: - VECTOR_SYNC_ENABLED: Enable background sync - VECTOR_SYNC_SCAN_INTERVAL: Scanner frequency (3600s default) - VECTOR_SYNC_PROCESSOR_WORKERS: Concurrent processors (3 default) - QDRANT_URL, QDRANT_API_KEY, QDRANT_COLLECTION: Vector DB config - OLLAMA_BASE_URL, OLLAMA_EMBEDDING_MODEL: Embedding service config Dependencies Added: - qdrant-client>=1.7.0: Vector database client Docker Compose: - Added Qdrant service with health check - Exposed ports 6333 (REST) and 6334 (gRPC) - Configured MCP service with vector sync environment - Added qdrant-data volume for persistence Known Issue: - FastMCP lifespan not triggering for streamable-http transport - Background tasks will start once lifespan integration is complete - Lifespan triggers on MCP session establishment, not server startup Related: ADR-007 Background Vector Database Synchronization 🤖 Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
103 lines
2.7 KiB
Python
103 lines
2.7 KiB
Python
"""Embedding service with provider detection."""
|
|
|
|
import logging
|
|
import os
|
|
|
|
from .base import EmbeddingProvider
|
|
from .ollama_provider import OllamaEmbeddingProvider
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class EmbeddingService:
|
|
"""Unified embedding service with automatic provider detection."""
|
|
|
|
def __init__(self):
|
|
"""Initialize embedding service with auto-detected provider."""
|
|
self.provider = self._detect_provider()
|
|
|
|
def _detect_provider(self) -> EmbeddingProvider:
|
|
"""
|
|
Auto-detect available embedding provider.
|
|
|
|
Checks environment variables in order:
|
|
1. OLLAMA_BASE_URL - Use Ollama provider
|
|
|
|
Returns:
|
|
Configured embedding provider
|
|
|
|
Raises:
|
|
ValueError: If no embedding provider is configured
|
|
"""
|
|
# Ollama provider (for this deployment)
|
|
ollama_url = os.getenv("OLLAMA_BASE_URL")
|
|
if ollama_url:
|
|
return OllamaEmbeddingProvider(
|
|
base_url=ollama_url,
|
|
model=os.getenv("OLLAMA_EMBEDDING_MODEL", "nomic-embed-text"),
|
|
verify_ssl=os.getenv("OLLAMA_VERIFY_SSL", "true").lower() == "true",
|
|
)
|
|
|
|
raise ValueError(
|
|
"No embedding provider configured. "
|
|
"Set OLLAMA_BASE_URL environment variable."
|
|
)
|
|
|
|
async def embed(self, text: str) -> list[float]:
|
|
"""
|
|
Generate embedding vector for text.
|
|
|
|
Args:
|
|
text: Input text to embed
|
|
|
|
Returns:
|
|
Vector embedding as list of floats
|
|
"""
|
|
return await self.provider.embed(text)
|
|
|
|
async def embed_batch(self, texts: list[str]) -> list[list[float]]:
|
|
"""
|
|
Generate embeddings for multiple texts.
|
|
|
|
Args:
|
|
texts: List of texts to embed
|
|
|
|
Returns:
|
|
List of vector embeddings
|
|
"""
|
|
return await self.provider.embed_batch(texts)
|
|
|
|
def get_dimension(self) -> int:
|
|
"""
|
|
Get embedding dimension.
|
|
|
|
Returns:
|
|
Vector dimension
|
|
"""
|
|
return self.provider.get_dimension()
|
|
|
|
async def close(self):
|
|
"""Close provider resources."""
|
|
if hasattr(self.provider, "close") and callable(
|
|
getattr(self.provider, "close")
|
|
):
|
|
close_method = getattr(self.provider, "close")
|
|
await close_method()
|
|
|
|
|
|
# Singleton instance
|
|
_embedding_service: EmbeddingService | None = None
|
|
|
|
|
|
def get_embedding_service() -> EmbeddingService:
|
|
"""
|
|
Get singleton embedding service instance.
|
|
|
|
Returns:
|
|
Global EmbeddingService instance
|
|
"""
|
|
global _embedding_service
|
|
if _embedding_service is None:
|
|
_embedding_service = EmbeddingService()
|
|
return _embedding_service
|