mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 16:36:21 +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.
100 lines
3.3 KiB
YAML
100 lines
3.3 KiB
YAML
post:
|
|
tags:
|
|
- Flow Services
|
|
summary: Row Embeddings Query - semantic search on structured data
|
|
description: |
|
|
Query row embeddings to find similar rows by vector similarity on indexed fields.
|
|
Enables fuzzy/semantic matching on structured data.
|
|
|
|
## Row Embeddings Query Overview
|
|
|
|
Find rows whose indexed field values are semantically similar to a query:
|
|
- **Input**: Query embedding vector, schema name, optional index filter
|
|
- **Search**: Compare against stored row index embeddings
|
|
- **Output**: Matching rows with index values and similarity scores
|
|
|
|
Core component of semantic search on structured data.
|
|
|
|
## Use Cases
|
|
|
|
- **Fuzzy name matching**: Find customers by approximate name
|
|
- **Semantic field search**: Find products by description similarity
|
|
- **Data deduplication**: Identify potential duplicate records
|
|
- **Entity resolution**: Match records across datasets
|
|
|
|
## Process
|
|
|
|
1. Obtain query embedding (via embeddings service)
|
|
2. Query stored row index embeddings for the specified schema
|
|
3. Calculate cosine similarity
|
|
4. Return top N most similar index entries
|
|
5. Use index values to retrieve full rows via GraphQL
|
|
|
|
## Response Format
|
|
|
|
Each match includes:
|
|
- `index_name`: The indexed field(s) that matched
|
|
- `index_value`: The actual values for those fields
|
|
- `text`: The text that was embedded
|
|
- `score`: Similarity score (higher = more similar)
|
|
|
|
operationId: rowEmbeddingsQueryService
|
|
security:
|
|
- bearerAuth: []
|
|
parameters:
|
|
- name: flow
|
|
in: path
|
|
required: true
|
|
schema:
|
|
type: string
|
|
description: Flow instance ID
|
|
example: my-flow
|
|
requestBody:
|
|
required: true
|
|
content:
|
|
application/json:
|
|
schema:
|
|
$ref: '../../components/schemas/embeddings-query/RowEmbeddingsQueryRequest.yaml'
|
|
examples:
|
|
basicQuery:
|
|
summary: Find similar customer names
|
|
value:
|
|
vectors: [0.023, -0.142, 0.089, 0.234, -0.067, 0.156, 0.201, -0.178]
|
|
schema_name: customers
|
|
limit: 10
|
|
collection: sales
|
|
filteredQuery:
|
|
summary: Search specific index
|
|
value:
|
|
vectors: [0.1, -0.2, 0.3, -0.4, 0.5]
|
|
schema_name: products
|
|
index_name: description
|
|
limit: 20
|
|
responses:
|
|
'200':
|
|
description: Successful response
|
|
content:
|
|
application/json:
|
|
schema:
|
|
$ref: '../../components/schemas/embeddings-query/RowEmbeddingsQueryResponse.yaml'
|
|
examples:
|
|
similarRows:
|
|
summary: Similar rows found
|
|
value:
|
|
matches:
|
|
- index_name: full_name
|
|
index_value: ["John", "Smith"]
|
|
text: "John Smith"
|
|
score: 0.95
|
|
- index_name: full_name
|
|
index_value: ["Jon", "Smythe"]
|
|
text: "Jon Smythe"
|
|
score: 0.82
|
|
- index_name: full_name
|
|
index_value: ["Jonathan", "Schmidt"]
|
|
text: "Jonathan Schmidt"
|
|
score: 0.76
|
|
'401':
|
|
$ref: '../../components/responses/Unauthorized.yaml'
|
|
'500':
|
|
$ref: '../../components/responses/Error.yaml'
|