Spaces:
Running
Running
File size: 65,288 Bytes
a55ea57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 | """
File: /networkx_client.py
Project: postgresql
Created Date: Sunday May 24th 2026
Author: Christian Nonis <alch.infoemail@gmail.com>
"""
from __future__ import annotations
from datetime import datetime, timezone
import os
from typing import Any, Dict, List, Literal, Optional, Tuple
from src.adapters.interfaces.embeddings import VectorStoreClient
from src.adapters.interfaces.graph import GraphClient, PredicateWithFlowKey
from src.constants.kg import (
IdentificationParams,
Node,
NodeDict,
Predicate,
PredicateDict,
SearchEntitiesResult,
SearchRelationshipsResult,
Triple,
)
from src.lib.postgresql.graph_store import (
GraphDatabaseError,
PostgreSQLGraphStore,
_RelationshipProxy,
)
from src.lib.postgresql._provisioning import clear_brain_database
from src.utils.serialization.data import always_dict
class NetworkXGraphClient(GraphClient):
"""
Graph client backed by PostgreSQL persistence and NetworkX in-memory traversal.
"""
def __init__(self):
self._store = PostgreSQLGraphStore()
def ensure_database(self, database: str) -> None:
self._store.ensure_database(database)
def clear_brain_data(self, brain_id: str) -> None:
clear_brain_database(brain_id, table_prefixes=("kg_",))
self._store.invalidate_brain(brain_id)
def execute_operation(self, operation: str, brain_id: str) -> Any:
self._store.ensure_database(brain_id)
return self._store.execute_read_query(brain_id, operation)
@property
def graphdb_type(self) -> str:
return "postgresql-networkx"
@property
def graphdb_description(self) -> str:
return (
"The graph database is PostgreSQL (NetworkX-backed). "
"You MUST write read-only SQL only. Cypher is NOT supported. "
"Never use MATCH, RETURN, labels(n), type(r), or EXPLAIN MATCH. "
"Never query a table named nodes or relationships — use kg_nodes and kg_relationships. "
"IMPORTANT: for text filters use data->>'field' (text), never data->'field' (jsonb) with ILIKE/LIKE. "
"Always send one complete SQL statement in a single tool call "
"(never split a WITH RECURSIVE CTE across multiple calls). "
"Tables: "
"kg_nodes(uuid TEXT PRIMARY KEY, data JSONB) where data holds name, labels, "
"description and other node properties; "
"kg_relationships(uuid TEXT PRIMARY KEY, rel_type TEXT, source_uuid TEXT, "
"target_uuid TEXT, data JSONB). "
"Examples: "
"SELECT COUNT(*) AS total FROM kg_nodes; "
"SELECT uuid, data->>'name' AS name, data->'labels' AS labels FROM kg_nodes "
"WHERE data->>'name' ILIKE '%Counsel%' OR data->>'description' ILIKE '%Mental Health%' LIMIT 50; "
"SELECT uuid, data FROM kg_nodes WHERE uuid = '<uuid>'; "
"SELECT n.uuid, n.data->>'name' AS name, r.rel_type, m.uuid AS target_uuid, "
"m.data->>'name' AS target_name, m.data->'labels' AS target_labels "
"FROM kg_relationships r "
"JOIN kg_nodes n ON n.uuid = r.source_uuid "
"JOIN kg_nodes m ON m.uuid = r.target_uuid "
"WHERE n.uuid = '<uuid>'; "
"Filter nodes by label with data->'labels' ? 'PERSON'. "
"Prefer 1-hop joins first. For multi-hop use this single complete statement: "
"WITH RECURSIVE walk AS ("
"SELECT source_uuid, target_uuid, rel_type, 1 AS depth "
"FROM kg_relationships WHERE source_uuid = '<uuid>' "
"UNION ALL "
"SELECT r.source_uuid, r.target_uuid, r.rel_type, w.depth + 1 "
"FROM walk w JOIN kg_relationships r ON r.source_uuid = w.target_uuid "
"WHERE w.depth < 3"
") SELECT * FROM walk LIMIT 50; "
"Only read queries are allowed; results are capped at 100 rows."
)
def _clean_labels(self, labels: list[str]) -> list[str]:
return [
label.replace(" ", "_")
.upper()
.replace("-", "_")
.replace(".", "_")
.replace(",", "_")
.replace(":", "_")
.replace(";", "_")
.replace("(", "_")
.replace(")", "_")
.replace("[", "_")
.replace("]", "_")
.replace("{", "_")
.replace("}", "_")
.replace("'", "_")
for label in labels
]
def _node_label_set(self, brain, node_uuid: str) -> set[str]:
return set(self._clean_labels(list(brain.labels(node_uuid))))
def _clean_property_key(self, property_key: str) -> str:
words = property_key.split()
return words[0].lower() + "".join(word.capitalize() for word in words[1:])
def _format_property_key(self, property_key: str) -> str:
sanitized_key = property_key.rstrip("`").lstrip("`")
needs_quoting = any(
char in sanitized_key
for char in ["-", " ", ".", "+", "*", "/", "%", ":", "@", "#", "$"]
)
cleaned_key = self._clean_property_key(sanitized_key)
return f"`{cleaned_key}`" if needs_quoting else cleaned_key
def _format_value(self, value: Any) -> str:
if isinstance(value, str):
v = value.replace("'", "\\'")
return f"'{v}'"
if isinstance(value, (int, float, bool)):
return str(value)
if value is None:
return "null"
v = str(value).replace("'", "\\'")
return f"'{v}'"
def add_nodes(
self,
nodes: list[Node],
brain_id: str,
identification_params: Optional[dict] = None,
metadata: Optional[dict] = None,
) -> list[Node] | str:
self._store.ensure_database(brain_id)
for node in nodes:
if not node.uuid:
raise ValueError("Node uuid is required for upsert")
identification_dict: dict[str, Any] = {"uuid": node.uuid, "name": node.name}
merged_metadata = {**(metadata or {}), **(node.metadata or {})}
all_properties: dict[str, Any] = {
**(node.properties or {}),
"metadata": merged_metadata or None,
}
if identification_params:
for key, value in identification_params.items():
normalized_key = self._clean_property_key(key)
if normalized_key not in {"uuid", "name"}:
identification_dict[normalized_key] = value
for attr in (
"description",
"happened_at",
"last_updated",
"observations",
"polarity",
):
if getattr(node, attr, None) is not None:
all_properties[attr] = getattr(node, attr)
all_properties["uuid"] = node.uuid
self._store.merge_node(
brain_id,
self._clean_labels(node.labels),
identification_dict,
all_properties,
)
return [
Node(
uuid=node.uuid,
labels=node.labels,
name=node.name,
description=node.description,
properties=node.properties,
metadata={**(node.metadata or {}), **(metadata or {})},
)
for node in nodes
]
def add_relationship(
self,
subject: Node,
predicate: Predicate,
to_object: Node,
brain_id: str,
) -> str:
rel_props: dict[str, Any] = {
"description": predicate.description,
"uuid": predicate.uuid,
"v_id": (predicate.properties or {}).get("v_id"),
"flow_key": predicate.flow_key,
}
for attr in ("properties", "happened_at", "last_updated", "amount"):
value = getattr(predicate, attr, None)
if value:
rel_props[attr] = value
for attr in ("properties", "description", "happened_at", "flow_key", "last_updated", "amount"):
for obj in (subject, to_object):
value = getattr(obj, attr, None)
if value and attr not in rel_props:
rel_props[attr] = value
self._store.ensure_database(brain_id)
self._store.merge_relationship(
brain_id,
self._clean_labels(subject.labels),
subject.name,
self._clean_labels(to_object.labels),
to_object.name,
self._clean_labels([predicate.name])[0],
rel_props,
subject_uuid=subject.uuid,
object_uuid=to_object.uuid,
)
return "ok"
def search_graph(self, nodes: list[Node], brain_id: str) -> list[Node]:
if not nodes:
return []
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
records = []
for node in nodes:
node_uuid = self._store.resolve_node_by_name_labels(
brain, self._clean_labels(node.labels), node.name
)
if not node_uuid:
continue
records.append({"n": brain.node_data(node_uuid), "r": None, "m": None})
for source, target, key in brain.graph.edges(keys=True):
if source != node_uuid and target != node_uuid:
continue
neighbor_uuid = target if source == node_uuid else source
records.append(
{
"n": brain.node_data(node_uuid),
"r": brain.graph.edges[source, target, key],
"m": brain.node_data(neighbor_uuid),
}
)
return records
def node_text_search(self, text: str, brain_id: str) -> list[Node]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
text_lower = text.lower()
nodes = []
for node_uuid, data in brain.graph.nodes(data=True):
if text_lower in str(data.get("name", "")).lower():
nodes.append(
Node(
uuid=node_uuid,
name=data.get("name", "") or "",
labels=list(data.get("labels") or []),
description=data.get("description", "") or "",
properties={k: v for k, v in data.items() if k != "labels"},
)
)
return nodes
def get_nodes_by_uuid(
self,
uuids: list[str],
brain_id: str,
with_relationships: Optional[bool] = False,
relationships_depth: Optional[int] = 1,
relationships_type: Optional[list[str]] = None,
preferred_labels: Optional[list[str]] = None,
) -> list[dict]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
depth = relationships_depth or 1
rel_types = relationships_type
pref = self._clean_labels(preferred_labels) if preferred_labels else None
if not with_relationships:
return [
Node(
uuid=record["uuid"],
name=record["name"],
labels=record["labels"],
description=record["description"],
properties=record["properties"],
)
for record in self._store.match_nodes_by_uuid(brain, uuids)
]
records = []
for node_uuid in uuids:
if node_uuid not in brain.graph:
continue
visited = {node_uuid}
frontier = {node_uuid}
for _ in range(depth):
next_frontier: set[str] = set()
for current_uuid in frontier:
for source, target, key, edge_data in brain.graph.edges(keys=True, data=True):
neighbor = target if source == current_uuid else source
if neighbor in visited:
continue
if rel_types and edge_data.get("rel_type") not in rel_types:
continue
neighbor_labels = brain.labels(neighbor)
if pref and not set(pref).intersection(neighbor_labels):
continue
record = self._store.node_to_record(brain, node_uuid)
record.update(
self._store.relationship_to_record(
brain, source, target, key, current_uuid
)
)
record.update(
{
"m_uuid": neighbor,
"m_name": brain.node_data(neighbor).get("name"),
"m_labels": neighbor_labels,
"m_description": brain.node_data(neighbor).get("description"),
"m_properties": brain.node_data(neighbor),
}
)
records.append(record)
visited.add(neighbor)
next_frontier.add(neighbor)
frontier = next_frontier
return [
{
"node": Node(
uuid=record["uuid"],
name=record["name"],
labels=record["labels"],
description=record["description"],
properties=record["properties"],
),
"relationships": record.get("rel"),
"related_nodes": (
Node(
uuid=record["m_uuid"],
name=record["m_name"],
labels=record["m_labels"],
description=record["m_description"],
properties=record["m_properties"],
)
if record.get("m_uuid")
else None
),
}
for record in records
]
def get_graph_entities(self, brain_id: str) -> list[str]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
labels: list[str] = []
for node_uuid in brain.graph.nodes:
labels.extend(brain.labels(node_uuid))
return labels
def get_graph_relationships(self, brain_id: str) -> list[str]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
return self._store.list_relationship_types(brain)
def get_by_uuid(self, uuid: str, brain_id: str) -> Node:
nodes = self.get_by_uuids([uuid], brain_id)
return nodes[0] if nodes else None
def get_by_uuids(self, uuids: list[str], brain_id: str) -> list[Node]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
return [
Node(
uuid=record.get("uuid", ""),
name=record.get("name", ""),
labels=record.get("labels", []),
description=record.get("description", ""),
properties=record.get("properties", {}),
polarity=record.get("polarity", "neutral"),
**(
{"happened_at": record.get("happened_at")}
if record.get("happened_at") is not None
else {}
),
**(
{"last_updated": record.get("last_updated", datetime.now(timezone.utc))}
if record.get("last_updated") is not None
else {}
),
**(
{"observations": record.get("observations", [])}
if record.get("observations") is not None
else {}
),
**(
{"metadata": record.get("metadata", {})}
if record.get("metadata") is not None
else {}
),
)
for record in self._store.match_nodes_by_uuid(brain, uuids)
]
def get_by_identification_params(
self,
identification_params: IdentificationParams,
brain_id: str,
entity_types: Optional[list[str]] = None,
) -> Node:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
params_dict = identification_params.model_dump(mode="json", exclude={"entity_types"})
labels = self._clean_labels(entity_types) if entity_types else None
matches = brain.find_nodes(labels=labels or None, filters=params_dict)
if not matches:
return None
record = self._store.node_to_record(brain, matches[0])
return Node(
uuid=record.get("uuid", ""),
name=record.get("name", "") or "",
labels=record.get("labels", []) or [],
description=record.get("description", "") or "",
properties=record.get("properties", {}) or {},
)
def get_neighbors(
self,
nodes: list[Node | str],
brain_id: str,
same_type_only: bool = False,
limit: int | None = None,
of_types: Optional[list[str]] = None,
) -> Dict[str, List[Tuple[Predicate, Node]]]:
if len(nodes) == 0:
return {}
node_uuids = nodes if isinstance(nodes[0], str) else [node.uuid for node in nodes]
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
cleaned_types = self._clean_labels(of_types) if of_types else None
records = self._store.neighbor_records_for_uuids(
brain, node_uuids, same_type_only, cleaned_types, limit
)
neighbors_dict: Dict[str, List[Tuple[Predicate, Node]]] = {uuid: [] for uuid in node_uuids}
for record in records:
source_uuid = record["uuid"]
neighbor = (
Predicate(
name=record.get("rel_type", "") or "",
description=record.get("rel_description", "") or "",
direction=record.get("direction", "neutral"),
properties=record.get("rel_properties", {}) or {},
flow_key=record.get("rel_flowkey", "") or "",
uuid=record.get("rel_uuid", "") or "",
),
Node(
uuid=record.get("c_uuid", ""),
name=record.get("c_name", "") or "",
labels=record.get("c_labels", []) or [],
description=record.get("c_description", "") or "",
properties=record.get("c_properties", {}) or {},
),
)
if source_uuid in neighbors_dict:
neighbors_dict[source_uuid].append(neighbor)
return neighbors_dict
def get_node_with_rel_by_uuid(
self, rel_ids_with_node_ids: list[tuple[str, str]], brain_id: str
) -> list[dict]:
"""
Get the node with the relationships by their UUIDs.
"""
def get_neighbor_node_tuples(
self, a_uuid: str, b_uuids: list[str], brain_id: str
) -> list[Tuple[Node, Predicate, Node]]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
b_set = set(b_uuids)
tuples = []
for source, target, key, edge_data in brain.graph.edges(keys=True, data=True):
if source != a_uuid and target != a_uuid:
continue
neighbor = target if source == a_uuid else source
if neighbor not in b_set:
continue
n_uuid, m_uuid = a_uuid, neighbor
direction = "out" if source == a_uuid else "in"
tuples.append(
(
Node(
uuid=n_uuid,
name=brain.node_data(n_uuid).get("name", "") or "",
labels=brain.labels(n_uuid),
description=brain.node_data(n_uuid).get("description", "") or "",
properties=brain.node_data(n_uuid),
),
Predicate(
name=edge_data.get("rel_type", "") or "",
description=edge_data.get("description", "") or "",
direction=direction,
),
Node(
uuid=m_uuid,
name=brain.node_data(m_uuid).get("name", "") or "",
labels=brain.labels(m_uuid),
description=brain.node_data(m_uuid).get("description", "") or "",
properties=brain.node_data(m_uuid),
),
)
)
if not tuples and os.getenv("DEBUG") == "true":
raise ValueError(
f"No neighbor nodes found for UUID: {a_uuid} and b_uuids: {b_uuids}"
)
return tuples
def get_connected_nodes(
self,
brain_id: str,
node: Optional[Node] = None,
uuids: Optional[list[str]] = None,
limit: Optional[int] = 10,
with_labels: Optional[list[str]] = None,
) -> list[Tuple[Node, Predicate, Node]]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
start_uuids: set[str] = set()
if node:
start_uuids.add(node.uuid)
if uuids:
start_uuids.update(uuids)
label_filter = set(with_labels) if with_labels else None
results = []
for source, target, key, edge_data in brain.graph.edges(keys=True, data=True):
if start_uuids and source not in start_uuids and target not in start_uuids:
continue
anchor = source if source in start_uuids or not start_uuids else target
other = target if anchor == source else source
if label_filter and not label_filter.intersection(brain.labels(other)):
continue
direction = "out" if anchor == source else "in"
results.append(
(
Node(
uuid=other,
name=brain.node_data(other).get("name", "") or "",
labels=brain.labels(other),
description=brain.node_data(other).get("description", "") or "",
properties=brain.node_data(other),
),
Predicate(
name=edge_data.get("rel_type", "") or "",
description=edge_data.get("description", "") or "",
direction=direction,
),
Node(
uuid=anchor,
name=brain.node_data(anchor).get("name", "") or "",
labels=brain.labels(anchor),
description=brain.node_data(anchor).get("description", "") or "",
properties=brain.node_data(anchor),
),
)
)
if limit is not None and len(results) >= limit:
break
return results
def search_relationships(
self,
brain_id: str,
limit: int = 10,
skip: int = 0,
relationship_types: Optional[list[str]] = None,
from_node_labels: Optional[list[str]] = None,
to_node_labels: Optional[list[str]] = None,
relationship_uuids: Optional[list[str]] = None,
query_text: Optional[str] = None,
query_search_target: Optional[str] = "all",
) -> SearchRelationshipsResult:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
text_lower = query_text.lower() if query_text else None
from_labels = set(self._clean_labels(from_node_labels)) if from_node_labels else None
to_labels = set(self._clean_labels(to_node_labels)) if to_node_labels else None
matched = []
for source, target, key, edge_data in brain.graph.edges(keys=True, data=True):
rel_type = edge_data.get("rel_type")
if relationship_types and rel_type not in relationship_types:
continue
if relationship_uuids and key not in relationship_uuids and edge_data.get("uuid") not in relationship_uuids:
continue
if from_labels and not from_labels.intersection(
self._node_label_set(brain, source)
):
continue
if to_labels and not to_labels.intersection(
self._node_label_set(brain, target)
):
continue
if text_lower:
haystacks = [
str(brain.node_data(source).get("name", "")).lower(),
str(brain.node_data(target).get("name", "")).lower(),
str(edge_data.get("description", "")).lower(),
]
if query_search_target == "node_name":
haystacks = [str(brain.node_data(source).get("name", "")).lower()]
elif query_search_target == "relationship_description":
haystacks = [str(edge_data.get("description", "")).lower()]
elif query_search_target == "relationship_name":
haystacks = [str(rel_type or "").lower()]
if not any(text_lower in h for h in haystacks):
continue
matched.append((source, target, key, edge_data))
total = len(matched)
page = matched[skip : skip + limit]
triples: list[Triple] = []
for source, target, key, edge_data in page:
direction = "out"
triples.append(
Triple(
subject=Node(
uuid=source,
name=str(brain.node_data(source).get("name") or source),
labels=list(brain.labels(source)),
description=brain.node_data(source).get("description"),
properties=brain.node_data(source),
),
predicate=Predicate(
name=str(edge_data.get("rel_type") or ""),
description=edge_data.get("description") or "",
direction=direction,
observations=None,
level=None,
deprecated=edge_data.get("deprecated", False),
),
object=Node(
uuid=target,
name=str(brain.node_data(target).get("name") or target),
labels=list(brain.labels(target)),
description=brain.node_data(target).get("description"),
properties=brain.node_data(target),
),
)
)
return SearchRelationshipsResult(results=triples, total=total)
def search_entities(
self,
brain_id: str,
limit: int = 10,
skip: int = 0,
node_labels: Optional[list[str]] = None,
node_uuids: Optional[list[str]] = None,
query_text: Optional[str] = None,
) -> SearchEntitiesResult:
self.ensure_database(brain_id)
brain = self._store._load_brain(brain_id)
allowed_labels = (
set(self._clean_labels(node_labels)) if node_labels else None
)
uuid_filter = set(node_uuids) if node_uuids else None
text_lower = query_text.lower() if query_text else None
matched: list[str] = []
for node_uuid, data in brain.graph.nodes(data=True):
if uuid_filter is not None and node_uuid not in uuid_filter:
continue
if allowed_labels is not None:
if not allowed_labels.intersection(
self._node_label_set(brain, node_uuid)
):
continue
if text_lower is not None:
if text_lower not in str(data.get("name", "")).lower():
continue
matched.append(node_uuid)
total = len(matched)
page = matched[skip : skip + limit]
nodes: list[Node] = []
for node_uuid in page:
data = brain.node_data(node_uuid)
properties = {k: v for k, v in data.items() if k != "labels"}
nodes.append(
Node(
uuid=str(node_uuid),
name=str(data.get("name") or node_uuid),
labels=list(brain.labels(node_uuid)),
description=data.get("description"),
properties=properties,
)
)
return SearchEntitiesResult(results=nodes, total=total)
def search_nodes_bm25(
self,
query_text: str,
brain_id: str,
*,
limit: int = 10,
node_labels: Optional[list[str]] = None,
node_uuids: Optional[list[str]] = None,
) -> list[tuple[Node, float]]:
rows = self._store.search_nodes_bm25(
query_text,
brain_id,
limit=limit,
node_labels=node_labels,
node_uuids=node_uuids,
)
hits: list[tuple[Node, float]] = []
for node_uuid, score, data in rows:
labels = [str(item) for item in (data.get("labels") or []) if str(item).strip()]
properties = {k: v for k, v in data.items() if k != "labels"}
hits.append(
(
Node(
uuid=str(node_uuid),
name=str(data.get("name") or node_uuid),
labels=labels,
description=data.get("description"),
properties=properties,
),
float(score),
)
)
return hits
def deprecate_relationship(
self,
subject: Node,
predicate: Predicate,
object: Node,
brain_id: str,
) -> Tuple[Node, Predicate, Node] | None:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
source_uuid = self._store.resolve_node_by_name_labels(
brain, self._clean_labels(subject.labels), subject.name
)
target_uuid = self._store.resolve_node_by_name_labels(
brain, self._clean_labels(object.labels), object.name
)
if not source_uuid or not target_uuid:
return None
rel_type = self._clean_labels([predicate.name])[0]
for source, target, key, data in brain.graph.edges(keys=True, data=True):
if source != source_uuid or target != target_uuid:
continue
if data.get("rel_type") != rel_type:
continue
data["deprecated"] = True
self._store._persist_relationship(
brain_id, key, rel_type, source, target, data
)
return (
Node(
uuid=source_uuid,
name=subject.name,
labels=subject.labels,
description=subject.description,
properties=brain.node_data(source_uuid),
),
Predicate(
name=rel_type,
description=data.get("description", "") or "",
direction="out",
),
Node(
uuid=target_uuid,
name=object.name,
labels=object.labels,
description=object.description,
properties=brain.node_data(target_uuid),
),
)
return None
def update_properties(
self,
uuid: str,
updating: Literal["node", "relationship"],
brain_id: str,
new_properties: dict,
properties_to_remove: list[str],
) -> Node | Predicate | None:
self._store.ensure_database(brain_id)
record = self._store.update_entity_properties(
brain_id,
uuid,
updating == "relationship",
new_properties,
properties_to_remove,
)
if not record:
return None
if updating == "node":
return Node(
uuid=record.get("uuid", "") or "",
name=record.get("name", "") or "",
labels=record.get("labels", []) or [],
description=record.get("description", "") or "",
properties=record.get("properties", {}) or {},
)
return Predicate(
name=record.get("rel_type", "") or "",
description=record.get("rel_description", "") or "",
direction=record.get("direction", "neutral"),
)
def get_graph_relationship_types(self, brain_id: str) -> list[str]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
return self._store.list_relationship_types(brain)
def get_graph_node_types(self, brain_id: str) -> list[str]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
return self._store.list_labels(brain)
def get_graph_node_properties(self, brain_id: str) -> list[str]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
return self._store.list_node_property_keys(brain)
def update_node(
self,
uuid: str,
brain_id: str,
new_name: Optional[str] = None,
new_description: Optional[str] = None,
new_labels: Optional[list[str]] = None,
new_properties: Optional[dict] = None,
properties_to_remove: Optional[list[str]] = None,
) -> Node | None:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
if uuid not in brain.graph:
return None
existing_node = self.get_by_uuid(uuid, brain_id)
if (
not new_name
and not new_description
and not new_labels
and not new_properties
and not properties_to_remove
):
return existing_node
data = brain.node_data(uuid)
if new_name:
data["name"] = new_name
if new_description:
data["description"] = new_description
if new_labels:
data["labels"] = self._clean_labels(new_labels)
if new_properties:
existing_properties = (existing_node.properties or {}) if existing_node else {}
for property_key, new_value in new_properties.items():
key_str = self._clean_property_key(property_key)
if property_key not in existing_properties or existing_properties.get(property_key) != new_value:
data[key_str] = new_value
if properties_to_remove:
for prop in properties_to_remove:
data.pop(self._clean_property_key(prop), None)
self._store._persist_node(brain_id, uuid, data)
record = self._store.node_to_record(brain, uuid)
return Node(
uuid=record.get("uuid", "") or "",
name=record.get("name", "") or "",
labels=record.get("labels", []) or [],
description=record.get("description", "") or "",
properties=record.get("properties", {}) or {},
)
def get_schema(self, brain_id: str) -> dict:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
return {
"labels": self._store.list_labels(brain),
"relationships": self._store.list_relationship_types(brain),
"event_names": self._store.event_names(brain),
}
def get_2nd_degree_hops(
self,
from_: List[str],
flattened: bool,
vector_store_adapter: VectorStoreClient,
brain_id: str,
) -> Dict[str, List[Tuple[Predicate, Node, List[Tuple[Predicate, Node]]]]]:
"""
Retrieve second-degree neighbor nodes from the given starting nodes.
Parameters:
from_ (List[str]): List of node UUIDs to start the hop from.
flattened (bool): Whether to flatten the result structure.
vector_store_adapter (VectorStoreClient): Adapter to the vector store.
brain_id (str): Identifier of the brain or graph context.
Returns:
Dict[str, List[Tuple[Predicate, Node, List[Tuple[Predicate, Node]]]]]: Mapping from each starting node UUID to a list of tuples containing
a predicate to a neighbor node, the neighbor node itself, and a list of tuples for that neighbor's predicates and their connected nodes.
"""
return super().get_2nd_degree_hops(
from_, flattened, vector_store_adapter, brain_id
)
def check_node_existence(
self,
uuid: str,
name: str,
labels: list[str],
brain_id: str,
) -> bool:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
return self._store.check_node_exists(
brain, uuid, name, self._clean_labels(labels)
)
def get_neighborhood(
self, node: Node | str, depth: int, brain_id: str
) -> list[dict]:
if depth < 1:
return []
node_uuid = node.uuid if isinstance(node, Node) else node
return self._get_neighborhood_recursive(node_uuid, depth, brain_id, set())
def _get_neighborhood_recursive(
self, node_uuid: str, depth: int, brain_id: str, path_visited: set[str]
) -> list[dict]:
if depth < 1 or node_uuid in path_visited:
return []
path_visited = path_visited.copy()
path_visited.add(node_uuid)
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
records = self._store.neighborhood_records(brain, node_uuid)
neighbors = []
for record in records:
neighbor_node_uuid = record.get("m_uuid", "")
if neighbor_node_uuid in path_visited:
continue
neighbor_node = Node(
uuid=neighbor_node_uuid,
name=record.get("m_name", "") or "",
labels=record.get("m_labels", []) or [],
description=record.get("m_description", "") or "",
properties=always_dict(record.get("m_properties", {})),
polarity=record.get("m_polarity", "neutral"),
metadata=always_dict(record.get("m_metadata", {})),
happened_at=record.get("m_happened_at", "") or "",
last_updated=record.get("m_last_updated", "") or "",
observations=record.get("m_observations", []) or [],
)
predicate = Predicate(
name=record.get("rel_type", "") or "",
description=record.get("rel_description", "") or "",
direction=record.get("direction", "neutral"),
properties=always_dict(record.get("rel_properties", {})),
flow_key=record.get("rel_flowkey", "") or "",
uuid=record.get("rel_uuid", "") or "",
last_updated=record.get("rel_last_updated", "") or "",
observations=record.get("rel_observations", []) or [],
amount=record.get("rel_amount"),
)
nested_neighbors = self._get_neighborhood_recursive(
neighbor_node_uuid, depth - 1, brain_id, path_visited
)
neighbors.append(
{
"predicate": predicate,
"node": neighbor_node,
"neighbors": nested_neighbors,
}
)
return neighbors
def _node_from_brain(self, brain, uuid: str) -> Node:
data = brain.node_data(uuid) if uuid in brain.graph else {}
node_kwargs: Dict[str, Any] = {
"uuid": uuid,
"name": data.get("name", "") or "",
"labels": data.get("labels", []) or [],
"description": data.get("description", "") or "",
"properties": always_dict(data),
"polarity": data.get("polarity", "neutral") or "neutral",
"metadata": always_dict(data.get("metadata", {})),
"happened_at": data.get("happened_at", "") or "",
"observations": data.get("observations", []) or [],
}
last_updated = data.get("last_updated")
if last_updated:
node_kwargs["last_updated"] = last_updated
return Node(**node_kwargs)
def _predicate_from_edge(self, edge_data: dict, direction: str) -> Predicate:
edge_data = always_dict(edge_data)
predicate_kwargs: Dict[str, Any] = {
"uuid": edge_data.get("uuid", "") or "",
"name": edge_data.get("rel_type", "") or edge_data.get("name", "") or "",
"description": edge_data.get("description", "") or "",
"direction": direction,
"properties": always_dict(edge_data),
"flow_key": edge_data.get("flow_key", "") or "",
"observations": edge_data.get("observations", []) or [],
"amount": edge_data.get("amount"),
}
last_updated = edge_data.get("last_updated")
if last_updated:
predicate_kwargs["last_updated"] = last_updated
return Predicate(**predicate_kwargs)
def _incident_edges(
self, brain, node_uuid: str
) -> List[Tuple[str, str, dict, str]]:
if node_uuid not in brain.graph:
return []
edges: List[Tuple[str, str, dict, str]] = []
for _, neighbor, key, data in brain.graph.out_edges(
node_uuid, keys=True, data=True
):
edges.append((neighbor, key, dict(data), "out"))
for neighbor, _, key, data in brain.graph.in_edges(
node_uuid, keys=True, data=True
):
edges.append((neighbor, key, dict(data), "in"))
return edges
def _event_path_records(
self,
brain,
node_uuids: list[str],
predicate_uuid: Optional[str] = None,
flow_key: Optional[str] = None,
):
for n_uuid in node_uuids:
if n_uuid not in brain.graph:
continue
for m_uuid, r1_key, r1_data, r1_direction in self._incident_edges(
brain, n_uuid
):
if (
predicate_uuid is not None
and (r1_data.get("uuid") or r1_key) != predicate_uuid
):
continue
required_flow_key = (
flow_key if flow_key is not None else r1_data.get("flow_key")
)
if not required_flow_key:
continue
for b_uuid, r2_key, r2_data, r2_direction in self._incident_edges(
brain, m_uuid
):
if r2_key == r1_key:
continue
if r2_data.get("flow_key") != required_flow_key:
continue
yield (
n_uuid,
m_uuid,
b_uuid,
r1_data,
r2_data,
r1_direction,
r2_direction,
)
def get_event_centric_neighbors(
self,
nodes: list[Node | str],
brain_id: str,
) -> List[Tuple[Node, Predicate, Node, Predicate, Node]]:
if len(nodes) == 0:
return []
node_uuids = nodes if isinstance(nodes[0], str) else [node.uuid for node in nodes]
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
results = []
for n_uuid, m_uuid, b_uuid, r1_data, r2_data, r_direction, r2_direction in self._event_path_records(brain, node_uuids):
results.append(
(
self._node_from_brain(brain, n_uuid),
self._predicate_from_edge(r1_data, r_direction),
self._node_from_brain(brain, m_uuid),
self._predicate_from_edge(r2_data, r2_direction),
self._node_from_brain(brain, b_uuid),
)
)
return results
def get_nexts_by_flow_key(
self, predicates: list[PredicateWithFlowKey], brain_id: str
) -> Dict[str, List[Tuple[Node, Predicate, Node]]]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
res: Dict[str, List[Tuple[Node, Predicate, Node]]] = {}
for predicate in predicates:
paths = self._event_path_records(
brain,
list(brain.graph.nodes),
predicate_uuid=predicate["predicate_uuid"],
flow_key=predicate["flow_key"],
)
res[predicate["predicate_uuid"]] = [
(
self._node_from_brain(brain, m_uuid),
self._predicate_from_edge(r2_data, "out"),
self._node_from_brain(brain, b_uuid),
)
for _, m_uuid, b_uuid, _, r2_data, _, _ in paths
]
return res
def get_triples_by_uuid(
self, uuids: list[str], brain_id: str
) -> List[Tuple[Node, Predicate, Node]]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
uuid_set = set(uuids)
triples = []
for source, target, key, edge_data in brain.graph.edges(keys=True, data=True):
if key not in uuid_set and edge_data.get("uuid") not in uuid_set:
continue
triples.append(
(
Node(
uuid=source,
name=brain.node_data(source).get("name", "") or "",
labels=brain.labels(source),
description=brain.node_data(source).get("description", "") or "",
properties=brain.node_data(source),
),
Predicate(
name=edge_data.get("rel_type", "") or "",
description=edge_data.get("description", "") or "",
direction="neutral",
properties=dict(edge_data),
),
Node(
uuid=target,
name=brain.node_data(target).get("name", "") or "",
labels=brain.labels(target),
description=brain.node_data(target).get("description", "") or "",
properties=brain.node_data(target),
),
)
)
return triples
def remove_nodes(self, uuids: list[str], brain_id: str) -> list[Node]:
self._store.ensure_database(brain_id)
records = self._store.delete_nodes_by_uuids(brain_id, uuids)
return [Node(**record.get("node", {})) for record in records]
def remove_relationships(
self,
relationships: list[Tuple[NodeDict, PredicateDict, NodeDict]],
brain_id: str,
) -> list[Tuple[Node, Predicate, Node]]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
deleted: list[Tuple[Node, Predicate, Node]] = []
by_rel_uuid: list[str] = []
by_tip_tail: list[Tuple[NodeDict, PredicateDict, NodeDict]] = []
for tail, pred, head in relationships:
if pred.get("uuid"):
by_rel_uuid.append(pred["uuid"])
else:
by_tip_tail.append((tail, pred, head))
if by_rel_uuid:
records = self._store.delete_relationships_by_uuids(brain_id, by_rel_uuid)
for record in records:
deleted.append(self._record_to_triple(record))
for tail, pred, head in by_tip_tail:
tail_uuid = self._resolve_node_dict(brain, tail)
head_uuid = self._resolve_node_dict(brain, head)
rel_type = pred.get("name")
if not tail_uuid or not head_uuid:
continue
for source, target, key, edge_data in list(brain.graph.edges(keys=True, data=True)):
if {source, target} != {tail_uuid, head_uuid}:
continue
if rel_type and edge_data.get("rel_type") != self._clean_labels([rel_type])[0]:
continue
record = self._store.node_to_record(brain, source, "n")
record.update(self._store.relationship_to_record(brain, source, target, key, source))
record.update(self._store.node_to_record(brain, target, "m"))
deleted.append(self._record_to_triple(record))
self._store._delete_relationship(brain_id, key)
return deleted
def _record_to_triple(self, record: Any) -> Tuple[Node, Predicate, Node]:
return (
Node(
uuid=record.get("n_uuid", "") or "",
name=record.get("n_name", "") or "",
labels=record.get("n_labels", []) or [],
description=record.get("n_description", "") or "",
properties=record.get("n_properties", {}) or {},
),
Predicate(
uuid=record.get("r_uuid", "") or "",
name=record.get("r_type", "") or "",
description=record.get("r_description", "") or "",
direction="neutral",
properties=record.get("r_properties", {}) or {},
),
Node(
uuid=record.get("m_uuid", "") or "",
name=record.get("m_name", "") or "",
labels=record.get("m_labels", []) or [],
description=record.get("m_description", "") or "",
properties=record.get("m_properties", {}) or {},
),
)
def list_relationships(
self, subject: str, object: str, brain_id: str
) -> list[Tuple[Node, Predicate, Node]]:
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
triples = []
for source, target, key, edge_data in brain.graph.edges(keys=True, data=True):
if {source, target} != {subject, object}:
continue
triples.append(
(
Node(
uuid=source,
name=brain.node_data(source).get("name", "") or "",
labels=brain.labels(source),
description=brain.node_data(source).get("description", "") or "",
properties=brain.node_data(source),
polarity=brain.node_data(source).get("polarity", "neutral"),
metadata=brain.node_data(source).get("metadata", {}) or {},
happened_at=brain.node_data(source).get("happened_at", "") or "",
last_updated=brain.node_data(source).get("last_updated", "") or "",
observations=brain.node_data(source).get("observations", []) or [],
),
Predicate(
uuid=edge_data.get("uuid", key) or "",
name=edge_data.get("rel_type", "") or "",
description=edge_data.get("description", "") or "",
direction="neutral",
properties=dict(edge_data),
flow_key=edge_data.get("flow_key", "") or "",
last_updated=edge_data.get("last_updated", "") or "",
observations=edge_data.get("observations", []) or [],
amount=edge_data.get("amount"),
),
Node(
uuid=target,
name=brain.node_data(target).get("name", "") or "",
labels=brain.labels(target),
description=brain.node_data(target).get("description", "") or "",
properties=brain.node_data(target),
polarity=brain.node_data(target).get("polarity", "neutral"),
metadata=brain.node_data(target).get("metadata", {}) or {},
happened_at=brain.node_data(target).get("happened_at", "") or "",
last_updated=brain.node_data(target).get("last_updated", "") or "",
observations=brain.node_data(target).get("observations", []) or [],
),
)
)
return triples
def get_event_hub_facts(
self,
event_uuids: list[str],
brain_id: str,
) -> List[Tuple[Node, Predicate, Node, Predicate, Node]]:
unique = sorted({str(u) for u in event_uuids if u})
if not unique:
return []
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
event_set = set(unique)
neighbor_seeds: list[str] = []
seen_seeds: set[str] = set()
for event_uuid in unique:
for neighbor, _key, _data, _direction in self._incident_edges(
brain, event_uuid
):
if neighbor in seen_seeds or neighbor in event_set:
continue
seen_seeds.add(neighbor)
neighbor_seeds.append(neighbor)
neighbor_seeds.sort()
results = []
seen_keys: set[tuple[str, str]] = set()
for (
n_uuid,
m_uuid,
b_uuid,
r1_data,
r2_data,
r_direction,
r2_direction,
) in self._event_path_records(brain, neighbor_seeds):
if m_uuid not in event_set:
continue
key = (
str(r1_data.get("uuid") or ""),
str(r2_data.get("uuid") or ""),
)
if key in seen_keys:
continue
seen_keys.add(key)
results.append(
(
self._node_from_brain(brain, n_uuid),
self._predicate_from_edge(r1_data, r_direction),
self._node_from_brain(brain, m_uuid),
self._predicate_from_edge(r2_data, r2_direction),
self._node_from_brain(brain, b_uuid),
)
)
results.sort(
key=lambda row: (
str(getattr(row[2], "uuid", "") or ""),
str(getattr(row[1], "uuid", "") or ""),
str(getattr(row[3], "uuid", "") or ""),
)
)
return results
def rebuild_hub_bridge_index(self, brain_id: str) -> int:
from src.core.saving.hub_bridges import (
bridges_from_memberships,
entity_event_memberships,
is_event_labels,
)
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
rows: list[tuple[str, str, str, str]] = []
for source, target, _key, edge_data in brain.graph.edges(keys=True, data=True):
rel_name = str(edge_data.get("rel_type") or edge_data.get("name") or "")
source_labels = brain.labels(source)
target_labels = brain.labels(target)
source_is_event = is_event_labels(source_labels)
target_is_event = is_event_labels(target_labels)
if source_is_event and not target_is_event:
rows.append(
(
source,
target,
str(brain.node_data(target).get("name") or ""),
rel_name,
)
)
elif target_is_event and not source_is_event:
rows.append(
(
target,
source,
str(brain.node_data(source).get("name") or ""),
rel_name,
)
)
bridges = bridges_from_memberships(entity_event_memberships(rows))
payload = [
(
br.event_a,
br.event_b,
br.shared_entity,
br.shared_entity_name,
br.weight,
)
for br in bridges
]
return self._store.replace_hub_bridges(brain_id, payload)
def refresh_hub_bridges_for_entities(
self, brain_id: str, entity_uuids: list[str]
) -> int:
from src.core.saving.hub_bridges import (
bridges_from_memberships,
entity_event_memberships,
is_event_labels,
)
touched = sorted({str(u) for u in entity_uuids if u})
if not touched:
return self.rebuild_hub_bridge_index(brain_id)
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
touched_set = set(touched)
rows: list[tuple[str, str, str, str]] = []
for source, target, _key, edge_data in brain.graph.edges(keys=True, data=True):
rel_name = str(edge_data.get("rel_type") or edge_data.get("name") or "")
source_labels = brain.labels(source)
target_labels = brain.labels(target)
source_is_event = is_event_labels(source_labels)
target_is_event = is_event_labels(target_labels)
if source_is_event and not target_is_event and target in touched_set:
rows.append(
(
source,
target,
str(brain.node_data(target).get("name") or ""),
rel_name,
)
)
elif target_is_event and not source_is_event and source in touched_set:
rows.append(
(
target,
source,
str(brain.node_data(source).get("name") or ""),
rel_name,
)
)
bridges = bridges_from_memberships(entity_event_memberships(rows))
payload = [
(
br.event_a,
br.event_b,
br.shared_entity,
br.shared_entity_name,
br.weight,
)
for br in bridges
]
self._store.delete_hub_bridges_for_entities(brain_id, touched)
return self._store.upsert_hub_bridges(brain_id, payload)
def get_hub_bridges(
self,
event_uuids: list[str],
brain_id: str,
) -> list[dict]:
from src.core.saving.hub_bridges import HubBridge
rows = self._store.get_hub_bridges_for_events(brain_id, event_uuids)
return [
HubBridge(
event_a=a,
event_b=b,
shared_entity=entity,
shared_entity_name=name,
weight=weight,
)
for a, b, entity, name, weight in rows
]
def rebuild_topic_index(self, brain_id: str) -> int:
import re
from src.core.saving.hub_bridges import (
is_context_rel,
is_event_labels,
is_spine_rel,
)
from src.core.saving.topic_hyperedges import (
cluster_sessions_into_topics,
session_entity_sets,
)
self._store.ensure_database(brain_id)
brain = self._store.get_brain(brain_id)
session_re = re.compile(
r"session_(\d+)|(?:\b|_)b(\d+)_t(\d+)\b",
re.IGNORECASE,
)
def sessions_from_text(text: str) -> list[str]:
found: list[str] = []
seen: set[str] = set()
for match in session_re.finditer(text or ""):
if match.group(1):
sid = f"session_{match.group(1)}"
else:
sid = f"session_b{match.group(2)}_t{match.group(3)}"
if sid not in seen:
seen.add(sid)
found.append(sid)
return found
chunk_ids: list[str] = []
event_chunks: dict[str, list[str]] = {}
for node_uuid in brain.graph.nodes:
if not is_event_labels(brain.labels(node_uuid)):
continue
props = brain.node_data(node_uuid)
ids = [
str(x)
for x in (props.get("source_chunk_ids") or [])
if x
]
single = props.get("source_chunk_id")
if single:
ids.append(str(single))
ids = sorted(set(ids))
event_chunks[node_uuid] = ids
chunk_ids.extend(ids)
chunk_sessions: dict[str, list[str]] = {}
if chunk_ids:
try:
from src.services.data.main import data_adapter
chunks, _ = data_adapter.get_text_chunks_by_ids(
sorted(set(chunk_ids))[:500],
False,
brain_id,
)
for chunk in chunks:
cid = str(getattr(chunk, "id", "") or "")
body = getattr(chunk, "text", "") or ""
if cid:
chunk_sessions[cid] = sessions_from_text(body)
except Exception:
chunk_sessions = {}
rows: list[tuple[str, str, str]] = []
for source, target, _key, edge_data in brain.graph.edges(keys=True, data=True):
rel_name = str(edge_data.get("rel_type") or edge_data.get("name") or "")
if is_context_rel(rel_name) or not is_spine_rel(rel_name):
continue
source_is_event = is_event_labels(brain.labels(source))
target_is_event = is_event_labels(brain.labels(target))
if source_is_event and not target_is_event:
event_uuid, entity_uuid = source, target
elif target_is_event and not source_is_event:
event_uuid, entity_uuid = target, source
else:
continue
entity_name = str(brain.node_data(entity_uuid).get("name") or "")
sessions: list[str] = []
for cid in event_chunks.get(event_uuid, []):
sessions.extend(chunk_sessions.get(cid, []))
if not sessions:
props = brain.node_data(event_uuid)
sessions = sessions_from_text(
" ".join(
str(props.get(k) or "")
for k in ("name", "description", "summary")
)
)
for sid in sessions:
rows.append((sid, entity_uuid, entity_name))
memberships = cluster_sessions_into_topics(session_entity_sets(rows))
payload = [
(m.topic_id, m.topic_label, m.session_id, m.weight) for m in memberships
]
return self._store.replace_topic_sessions(brain_id, payload)
def list_topic_memberships(self, brain_id: str) -> list:
from src.core.saving.topic_hyperedges import TopicSession
rows = self._store.list_topic_sessions(brain_id)
return [
TopicSession(
topic_id=tid,
topic_label=label,
session_id=sid,
weight=weight,
)
for tid, label, sid, weight in rows
]
def _records(data: list | Any) -> Any:
if hasattr(data, "records"):
return data
class _R:
def __init__(self, records):
self.records = records
return _R(data if isinstance(data, list) else [])
_networkx_graph_client: Optional[NetworkXGraphClient] = None
def get_networkx_graph_client() -> NetworkXGraphClient:
global _networkx_graph_client
if _networkx_graph_client is None:
_networkx_graph_client = NetworkXGraphClient()
return _networkx_graph_client
|