Structured data 2 (#645)

* Structured data refactor - multi-index tables, remove need for manual mods to the Cassandra tables

* Tech spec updated to track implementation

trustgraph-base/trustgraph/schema/knowledge/embeddings.py

@@ -60,3 +60,23 @@ class StructuredObjectEmbedding:
     field_embeddings: dict[str, list[float]] = field(default_factory=dict)  # Per-field embeddings
 
 ############################################################################
+
+# Row embeddings are embeddings associated with indexed field values
+# in structured row data. Each index gets embedded separately.
+
+@dataclass
+class RowIndexEmbedding:
+    """Single row's embedding for one index"""
+    index_name: str = ""              # The indexed field name(s)
+    index_value: list[str] = field(default_factory=list)  # The field value(s)
+    text: str = ""                    # Text that was embedded
+    vectors: list[list[float]] = field(default_factory=list)
+
+@dataclass
+class RowEmbeddings:
+    """Batched row embeddings for a schema"""
+    metadata: Metadata | None = None
+    schema_name: str = ""
+    embeddings: list[RowIndexEmbedding] = field(default_factory=list)
+
+############################################################################

trustgraph-base/trustgraph/schema/services/__init__.py

@@ -9,7 +9,7 @@ from .library import *
 from .lookup import *
 from .nlp_query import *
 from .structured_query import *
-from .objects_query import *
+from .rows_query import *
 from .diagnosis import *
 from .collection import *
 from .storage import *

trustgraph-base/trustgraph/schema/services/query.py

@@ -59,4 +59,39 @@ document_embeddings_request_queue = topic(
 )
 document_embeddings_response_queue = topic(
     "document-embeddings-response", qos='q0', tenant='trustgraph', namespace='flow'
+)
+
+############################################################################
+
+# Row embeddings query - for semantic/fuzzy matching on row index values
+
+@dataclass
+class RowIndexMatch:
+    """A single matching row index from a semantic search"""
+    index_name: str = ""                    # The indexed field(s)
+    index_value: list[str] = field(default_factory=list)  # The index values
+    text: str = ""                          # The text that was embedded
+    score: float = 0.0                      # Similarity score
+
+@dataclass
+class RowEmbeddingsRequest:
+    """Request for row embeddings semantic search"""
+    vectors: list[list[float]] = field(default_factory=list)  # Query vectors
+    limit: int = 10                         # Max results to return
+    user: str = ""                          # User/keyspace
+    collection: str = ""                    # Collection name
+    schema_name: str = ""                   # Schema name to search within
+    index_name: str | None = None           # Optional: filter to specific index
+
+@dataclass
+class RowEmbeddingsResponse:
+    """Response from row embeddings semantic search"""
+    error: Error | None = None
+    matches: list[RowIndexMatch] = field(default_factory=list)
+
+row_embeddings_request_queue = topic(
+    "row-embeddings-request", qos='q0', tenant='trustgraph', namespace='flow'
+)
+row_embeddings_response_queue = topic(
+    "row-embeddings-response", qos='q0', tenant='trustgraph', namespace='flow'
 )

trustgraph-base/trustgraph/schema/services/rows_query.py

@@ -6,7 +6,7 @@ from ..core.topic import topic
 
 ############################################################################
 
-# Objects Query Service - executes GraphQL queries against structured data
+# Rows Query Service - executes GraphQL queries against structured data
 
 @dataclass
 class GraphQLError:
@@ -15,7 +15,7 @@ class GraphQLError:
     extensions: dict[str, str] = field(default_factory=dict)   # Additional error metadata
 
 @dataclass
-class ObjectsQueryRequest:
+class RowsQueryRequest:
     user: str = ""              # Cassandra keyspace (follows pattern from TriplesQueryRequest)
     collection: str = ""        # Data collection identifier (required for partition key)
     query: str = ""             # GraphQL query string
@@ -23,7 +23,7 @@ class ObjectsQueryRequest:
     operation_name: Optional[str] = None    # Operation to execute for multi-operation documents
 
 @dataclass
-class ObjectsQueryResponse:
+class RowsQueryResponse:
     error: Error | None = None              # System-level error (connection, timeout, etc.)
     data: str = ""              # JSON-encoded GraphQL response data
     errors: list[GraphQLError] = field(default_factory=list) # GraphQL field-level errors