trustgraph/specs/api/paths/flow/document-rag.yaml
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

124 lines
4.4 KiB
YAML

post:
tags:
- Flow Services
summary: Document RAG - retrieve and generate from documents
description: |
Retrieval-Augmented Generation over document embeddings.
## Document RAG Overview
Document RAG combines:
1. **Retrieval**: Search document embeddings using semantic similarity
2. **Generation**: Use LLM to synthesize answer from retrieved documents
This provides grounded answers based on your document corpus.
## Query Process
1. Convert query to embedding
2. Search document embeddings for most similar chunks
3. Retrieve top N document chunks (configurable via doc-limit)
4. Pass query + retrieved context to LLM
5. Generate answer grounded in documents
## Streaming
Enable `streaming: true` to receive the answer as it's generated:
- Multiple `chunk` messages with `response` content
- `explain` messages with inline provenance triples (`explain_triples`)
- Final message with `end-of-stream: true`
- Session ends with `end_of_session: true`
Explain events carry `explain_id`, `explain_graph`, and `explain_triples`
inline in the stream, so no follow-up knowledge graph query is needed.
Without streaming, returns complete answer in single response.
## Parameters
- **doc-limit**: Controls retrieval depth (1-100, default 20)
- Higher = more context but slower
- Lower = faster but may miss relevant info
- **collection**: Target specific document collection
operationId: documentRagService
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/rag/DocumentRagRequest.yaml'
examples:
basicQuery:
summary: Basic document query
value:
query: What are the key findings in the research papers?
collection: research
streamingQuery:
summary: Streaming query
value:
query: Summarize the main conclusions
collection: research
doc-limit: 15
streaming: true
limitedRetrieval:
summary: Query with limited retrieval
value:
query: What is quantum entanglement?
doc-limit: 5
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '../../components/schemas/rag/DocumentRagResponse.yaml'
examples:
completeResponse:
summary: Complete non-streaming response
value:
response: |
The research papers present three key findings:
1. Quantum entanglement exhibits non-local correlations
2. Bell's inequality is violated in experimental tests
3. Applications in quantum cryptography are promising
end-of-stream: false
streamingChunk:
summary: Streaming response chunk
value:
response: "The research papers present three"
end-of-stream: false
explainEvent:
summary: Explain event with inline provenance triples
value:
message_type: explain
explain_id: urn:trustgraph:question:abc123
explain_graph: urn:graph:retrieval
explain_triples:
- s: {t: i, i: "urn:trustgraph:question:abc123"}
p: {t: i, i: "http://www.w3.org/1999/02/22-rdf-syntax-ns#type"}
o: {t: i, i: "https://trustgraph.ai/ns/DocumentRagQuestion"}
- s: {t: i, i: "urn:trustgraph:question:abc123"}
p: {t: i, i: "https://trustgraph.ai/ns/query"}
o: {t: l, v: "What are the key findings in the research papers?"}
end-of-stream: false
end_of_session: false
streamingComplete:
summary: Streaming complete marker
value:
response: ""
end-of-stream: true
'401':
$ref: '../../components/responses/Unauthorized.yaml'
'500':
$ref: '../../components/responses/Error.yaml'