mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-16 02:45:13 +02:00
d35473f7f7
Introduces `workspace` as the isolation boundary for config, flows,
library, and knowledge data. Removes `user` as a schema-level field
throughout the code, API specs, and tests; workspace provides the
same separation more cleanly at the trusted flow.workspace layer
rather than through client-supplied message fields.
Design
------
- IAM tech spec (docs/tech-specs/iam.md) documents current state,
proposed auth/access model, and migration direction.
- Data ownership model (docs/tech-specs/data-ownership-model.md)
captures the workspace/collection/flow hierarchy.
Schema + messaging
------------------
- Drop `user` field from AgentRequest/Step, GraphRagQuery,
DocumentRagQuery, Triples/Graph/Document/Row EmbeddingsRequest,
Sparql/Rows/Structured QueryRequest, ToolServiceRequest.
- Keep collection/workspace routing via flow.workspace at the
service layer.
- Translators updated to not serialise/deserialise user.
API specs
---------
- OpenAPI schemas and path examples cleaned of user fields.
- Websocket async-api messages updated.
- Removed the unused parameters/User.yaml.
Services + base
---------------
- Librarian, collection manager, knowledge, config: all operations
scoped by workspace. Config client API takes workspace as first
positional arg.
- `flow.workspace` set at flow start time by the infrastructure;
no longer pass-through from clients.
- Tool service drops user-personalisation passthrough.
CLI + SDK
---------
- tg-init-workspace and workspace-aware import/export.
- All tg-* commands drop user args; accept --workspace.
- Python API/SDK (flow, socket_client, async_*, explainability,
library) drop user kwargs from every method signature.
MCP server
----------
- All tool endpoints drop user parameters; socket_manager no longer
keyed per user.
Flow service
------------
- Closure-based topic cleanup on flow stop: only delete topics
whose blueprint template was parameterised AND no remaining
live flow (across all workspaces) still resolves to that topic.
Three scopes fall out naturally from template analysis:
* {id} -> per-flow, deleted on stop
* {blueprint} -> per-blueprint, kept while any flow of the
same blueprint exists
* {workspace} -> per-workspace, kept while any flow in the
workspace exists
* literal -> global, never deleted (e.g. tg.request.librarian)
Fixes a bug where stopping a flow silently destroyed the global
librarian exchange, wedging all library operations until manual
restart.
RabbitMQ backend
----------------
- heartbeat=60, blocked_connection_timeout=300. Catches silently
dead connections (broker restart, orphaned channels, network
partitions) within ~2 heartbeat windows, so the consumer
reconnects and re-binds its queue rather than sitting forever
on a zombie connection.
Tests
-----
- Full test refresh: unit, integration, contract, provenance.
- Dropped user-field assertions and constructor kwargs across
~100 test files.
- Renamed user-collection isolation tests to workspace-collection.
102 lines
2.7 KiB
Python
Executable file
102 lines
2.7 KiB
Python
Executable file
|
|
"""
|
|
Graph embeddings query service. Input is vector, output is list of
|
|
entities
|
|
"""
|
|
|
|
import logging
|
|
|
|
from .... direct.milvus_graph_embeddings import EntityVectors
|
|
from .... schema import GraphEmbeddingsResponse, EntityMatch
|
|
from .... schema import Error, Term, IRI, LITERAL
|
|
from .... base import GraphEmbeddingsQueryService
|
|
|
|
# Module logger
|
|
logger = logging.getLogger(__name__)
|
|
|
|
default_ident = "graph-embeddings-query"
|
|
default_store_uri = 'http://localhost:19530'
|
|
|
|
class Processor(GraphEmbeddingsQueryService):
|
|
|
|
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)
|
|
|
|
def create_value(self, ent):
|
|
if ent.startswith("http://") or ent.startswith("https://"):
|
|
return Term(type=IRI, iri=ent)
|
|
else:
|
|
return Term(type=LITERAL, value=ent)
|
|
|
|
async def query_graph_embeddings(self, workspace, msg):
|
|
|
|
try:
|
|
|
|
vec = msg.vector
|
|
if not vec:
|
|
return []
|
|
|
|
# Handle zero limit case
|
|
if msg.limit <= 0:
|
|
return []
|
|
|
|
resp = self.vecstore.search(
|
|
vec,
|
|
workspace,
|
|
msg.collection,
|
|
limit=msg.limit * 2
|
|
)
|
|
|
|
entity_set = set()
|
|
entities = []
|
|
|
|
for r in resp:
|
|
ent = r["entity"]["entity"]
|
|
# Milvus returns distance, convert to similarity score
|
|
distance = r.get("distance", 0.0)
|
|
score = 1.0 - distance if distance else 0.0
|
|
|
|
# De-dupe entities, keep highest score
|
|
if ent not in entity_set:
|
|
entity_set.add(ent)
|
|
entities.append(EntityMatch(
|
|
entity=self.create_value(ent),
|
|
score=score,
|
|
))
|
|
|
|
# Keep adding entities until limit
|
|
if len(entities) >= msg.limit:
|
|
break
|
|
|
|
logger.debug("Send response...")
|
|
return entities
|
|
|
|
except Exception as e:
|
|
|
|
logger.error(f"Exception querying graph embeddings: {e}", exc_info=True)
|
|
raise e
|
|
|
|
@staticmethod
|
|
def add_args(parser):
|
|
|
|
GraphEmbeddingsQueryService.add_args(parser)
|
|
|
|
parser.add_argument(
|
|
'-t', '--store-uri',
|
|
default=default_store_uri,
|
|
help=f'Milvus store URI (default: {default_store_uri})'
|
|
)
|
|
|
|
def run():
|
|
|
|
Processor.launch(default_ident, __doc__)
|
|
|