mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-30 02:46:23 +02:00
13ff7d765d
* Tech spec * Refactored Cassanda knowledge graph for single table * Collection management, librarian services to manage metadata and collection deletion
131 lines
4.4 KiB
Python
Executable file
131 lines
4.4 KiB
Python
Executable file
|
|
"""
|
|
Accepts entity/vector pairs and writes them to a Milvus store.
|
|
"""
|
|
|
|
import logging
|
|
|
|
from .... direct.milvus_graph_embeddings import EntityVectors
|
|
from .... base import GraphEmbeddingsStoreService
|
|
from .... base import AsyncProcessor, Consumer, Producer
|
|
from .... base import ConsumerMetrics, ProducerMetrics
|
|
from .... schema import StorageManagementRequest, StorageManagementResponse, Error
|
|
from .... schema import vector_storage_management_topic, storage_management_response_topic
|
|
|
|
# Module logger
|
|
logger = logging.getLogger(__name__)
|
|
|
|
default_ident = "ge-write"
|
|
default_store_uri = 'http://localhost:19530'
|
|
|
|
class Processor(GraphEmbeddingsStoreService):
|
|
|
|
def __init__(self, **params):
|
|
|
|
store_uri = params.get("store_uri", default_store_uri)
|
|
|
|
super(Processor, self).__init__(
|
|
**params | {
|
|
"store_uri": store_uri,
|
|
}
|
|
)
|
|
|
|
self.vecstore = EntityVectors(store_uri)
|
|
|
|
# Set up metrics for storage management
|
|
storage_request_metrics = ConsumerMetrics(
|
|
processor=self.id, flow=None, name="storage-request"
|
|
)
|
|
storage_response_metrics = ProducerMetrics(
|
|
processor=self.id, flow=None, name="storage-response"
|
|
)
|
|
|
|
# Set up consumer for storage management requests
|
|
self.storage_request_consumer = Consumer(
|
|
taskgroup=self.taskgroup,
|
|
client=self.pulsar_client,
|
|
flow=None,
|
|
topic=vector_storage_management_topic,
|
|
subscriber=f"{self.id}-storage",
|
|
schema=StorageManagementRequest,
|
|
handler=self.on_storage_management,
|
|
metrics=storage_request_metrics,
|
|
)
|
|
|
|
# Set up producer for storage management responses
|
|
self.storage_response_producer = Producer(
|
|
client=self.pulsar_client,
|
|
topic=storage_management_response_topic,
|
|
schema=StorageManagementResponse,
|
|
metrics=storage_response_metrics,
|
|
)
|
|
|
|
async def store_graph_embeddings(self, message):
|
|
|
|
for entity in message.entities:
|
|
|
|
if entity.entity.value != "" and entity.entity.value is not None:
|
|
for vec in entity.vectors:
|
|
self.vecstore.insert(
|
|
vec, entity.entity.value,
|
|
message.metadata.user,
|
|
message.metadata.collection
|
|
)
|
|
|
|
@staticmethod
|
|
def add_args(parser):
|
|
|
|
GraphEmbeddingsStoreService.add_args(parser)
|
|
|
|
parser.add_argument(
|
|
'-t', '--store-uri',
|
|
default=default_store_uri,
|
|
help=f'Milvus store URI (default: {default_store_uri})'
|
|
)
|
|
|
|
async def on_storage_management(self, message):
|
|
"""Handle storage management requests"""
|
|
logger.info(f"Storage management request: {message.operation} for {message.user}/{message.collection}")
|
|
|
|
try:
|
|
if message.operation == "delete-collection":
|
|
await self.handle_delete_collection(message)
|
|
else:
|
|
response = StorageManagementResponse(
|
|
error=Error(
|
|
type="invalid_operation",
|
|
message=f"Unknown operation: {message.operation}"
|
|
)
|
|
)
|
|
await self.storage_response_producer.send(response)
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error processing storage management request: {e}", exc_info=True)
|
|
response = StorageManagementResponse(
|
|
error=Error(
|
|
type="processing_error",
|
|
message=str(e)
|
|
)
|
|
)
|
|
await self.storage_response_producer.send(response)
|
|
|
|
async def handle_delete_collection(self, message):
|
|
"""Delete the collection for graph embeddings"""
|
|
try:
|
|
self.vecstore.delete_collection(message.user, message.collection)
|
|
|
|
# Send success response
|
|
response = StorageManagementResponse(
|
|
error=None # No error means success
|
|
)
|
|
await self.storage_response_producer.send(response)
|
|
logger.info(f"Successfully deleted collection {message.user}/{message.collection}")
|
|
|
|
except Exception as e:
|
|
logger.error(f"Failed to delete collection: {e}")
|
|
raise
|
|
|
|
def run():
|
|
|
|
Processor.launch(default_ident, __doc__)
|
|
|