trustgraph/specs/api/paths/flow/document-rag.yaml
cybermaggedon e899370d98
Update docs for 2.2 release (#766)
- Update protocol specs
- Update protocol docs
- Update API specs
2026-04-07 22:24:59 +01:00

127 lines
4.5 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
- **user**: Multi-tenant isolation
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?
user: alice
collection: research
streamingQuery:
summary: Streaming query
value:
query: Summarize the main conclusions
user: alice
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'