trustgraph/trustgraph-base/trustgraph/messaging/translators/embeddings_query.py
cybermaggedon d35473f7f7
feat: workspace-based multi-tenancy, replacing user as tenancy axis (#840)
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.
2026-04-21 23:23:01 +01:00

154 lines
5.1 KiB
Python

from typing import Dict, Any, Tuple
from ...schema import (
DocumentEmbeddingsRequest, DocumentEmbeddingsResponse,
GraphEmbeddingsRequest, GraphEmbeddingsResponse,
RowEmbeddingsRequest, RowEmbeddingsResponse, RowIndexMatch
)
from .base import MessageTranslator
from .primitives import ValueTranslator
class DocumentEmbeddingsRequestTranslator(MessageTranslator):
"""Translator for DocumentEmbeddingsRequest schema objects"""
def decode(self, data: Dict[str, Any]) -> DocumentEmbeddingsRequest:
return DocumentEmbeddingsRequest(
vector=data["vector"],
limit=int(data.get("limit", 10)),
collection=data.get("collection", "default")
)
def encode(self, obj: DocumentEmbeddingsRequest) -> Dict[str, Any]:
return {
"vector": obj.vector,
"limit": obj.limit,
"collection": obj.collection
}
class DocumentEmbeddingsResponseTranslator(MessageTranslator):
"""Translator for DocumentEmbeddingsResponse schema objects"""
def decode(self, data: Dict[str, Any]) -> DocumentEmbeddingsResponse:
raise NotImplementedError("Response translation to Pulsar not typically needed")
def encode(self, obj: DocumentEmbeddingsResponse) -> Dict[str, Any]:
result = {}
if obj.chunks is not None:
result["chunks"] = [
{
"chunk_id": chunk.chunk_id,
"score": chunk.score
}
for chunk in obj.chunks
]
return result
def encode_with_completion(self, obj: DocumentEmbeddingsResponse) -> Tuple[Dict[str, Any], bool]:
"""Returns (response_dict, is_final)"""
return self.encode(obj), True
class GraphEmbeddingsRequestTranslator(MessageTranslator):
"""Translator for GraphEmbeddingsRequest schema objects"""
def decode(self, data: Dict[str, Any]) -> GraphEmbeddingsRequest:
return GraphEmbeddingsRequest(
vector=data["vector"],
limit=int(data.get("limit", 10)),
collection=data.get("collection", "default")
)
def encode(self, obj: GraphEmbeddingsRequest) -> Dict[str, Any]:
return {
"vector": obj.vector,
"limit": obj.limit,
"collection": obj.collection
}
class GraphEmbeddingsResponseTranslator(MessageTranslator):
"""Translator for GraphEmbeddingsResponse schema objects"""
def __init__(self):
self.value_translator = ValueTranslator()
def decode(self, data: Dict[str, Any]) -> GraphEmbeddingsResponse:
raise NotImplementedError("Response translation to Pulsar not typically needed")
def encode(self, obj: GraphEmbeddingsResponse) -> Dict[str, Any]:
result = {}
if obj.entities is not None:
result["entities"] = [
{
"entity": self.value_translator.encode(match.entity),
"score": match.score
}
for match in obj.entities
]
return result
def encode_with_completion(self, obj: GraphEmbeddingsResponse) -> Tuple[Dict[str, Any], bool]:
"""Returns (response_dict, is_final)"""
return self.encode(obj), True
class RowEmbeddingsRequestTranslator(MessageTranslator):
"""Translator for RowEmbeddingsRequest schema objects"""
def decode(self, data: Dict[str, Any]) -> RowEmbeddingsRequest:
return RowEmbeddingsRequest(
vector=data["vector"],
limit=int(data.get("limit", 10)),
collection=data.get("collection", "default"),
schema_name=data.get("schema_name", ""),
index_name=data.get("index_name")
)
def encode(self, obj: RowEmbeddingsRequest) -> Dict[str, Any]:
result = {
"vector": obj.vector,
"limit": obj.limit,
"collection": obj.collection,
"schema_name": obj.schema_name,
}
if obj.index_name:
result["index_name"] = obj.index_name
return result
class RowEmbeddingsResponseTranslator(MessageTranslator):
"""Translator for RowEmbeddingsResponse schema objects"""
def decode(self, data: Dict[str, Any]) -> RowEmbeddingsResponse:
raise NotImplementedError("Response translation to Pulsar not typically needed")
def encode(self, obj: RowEmbeddingsResponse) -> Dict[str, Any]:
result = {}
if obj.error is not None:
result["error"] = {
"type": obj.error.type,
"message": obj.error.message
}
if obj.matches is not None:
result["matches"] = [
{
"index_name": match.index_name,
"index_value": match.index_value,
"text": match.text,
"score": match.score
}
for match in obj.matches
]
return result
def encode_with_completion(self, obj: RowEmbeddingsResponse) -> Tuple[Dict[str, Any], bool]:
"""Returns (response_dict, is_final)"""
return self.encode(obj), True