mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 16:36:21 +02:00
127 lines
4.3 KiB
YAML
127 lines
4.3 KiB
YAML
post:
|
|
tags:
|
|
- Flow Services
|
|
summary: Graph RAG - retrieve and generate from knowledge graph
|
|
description: |
|
|
Retrieval-Augmented Generation over knowledge graph.
|
|
|
|
## Graph RAG Overview
|
|
|
|
Graph RAG combines:
|
|
1. **Retrieval**: Find relevant entities and subgraph from knowledge graph
|
|
2. **Generation**: Use LLM to reason over graph structure and generate answer
|
|
|
|
This provides graph-aware answers that leverage relationships and structure.
|
|
|
|
## Query Process
|
|
|
|
1. Identify relevant entities from query (using embeddings)
|
|
2. Retrieve connected subgraph around entities
|
|
3. Optionally traverse paths up to max-path-length hops
|
|
4. Limit subgraph size to stay within context window
|
|
5. Pass query + graph structure to LLM
|
|
6. Generate answer incorporating graph relationships
|
|
|
|
## Streaming
|
|
|
|
Enable `streaming: true` to receive the answer as it's generated:
|
|
- Multiple messages with `response` content
|
|
- Final message with `end-of-stream: true`
|
|
|
|
Without streaming, returns complete answer in single response.
|
|
|
|
## Parameters
|
|
|
|
Control retrieval scope with multiple knobs:
|
|
- **entity-limit**: How many starting entities to find (1-200, default 50)
|
|
- **triple-limit**: Triples per entity (1-100, default 30)
|
|
- **max-subgraph-size**: Total subgraph cap (10-5000, default 1000)
|
|
- **max-path-length**: Graph traversal depth (1-5, default 2)
|
|
|
|
Higher limits = more context but:
|
|
- Slower retrieval
|
|
- Larger context for LLM
|
|
- May hit context window limits
|
|
|
|
## Use Cases
|
|
|
|
Best for queries requiring:
|
|
- Relationship understanding ("How are X and Y connected?")
|
|
- Multi-hop reasoning ("What's the path from A to B?")
|
|
- Structural analysis ("What are the main entities related to X?")
|
|
|
|
operationId: graphRagService
|
|
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/GraphRagRequest.yaml'
|
|
examples:
|
|
basicQuery:
|
|
summary: Basic graph query
|
|
value:
|
|
query: What connections exist between quantum physics and computer science?
|
|
user: alice
|
|
collection: research
|
|
streamingQuery:
|
|
summary: Streaming query with custom limits
|
|
value:
|
|
query: Trace the historical development of AI from Turing to modern LLMs
|
|
user: alice
|
|
collection: research
|
|
entity-limit: 40
|
|
triple-limit: 25
|
|
max-subgraph-size: 800
|
|
max-path-length: 3
|
|
streaming: true
|
|
focusedQuery:
|
|
summary: Focused query with tight limits
|
|
value:
|
|
query: What is the immediate relationship between entity A and B?
|
|
entity-limit: 10
|
|
triple-limit: 15
|
|
max-subgraph-size: 200
|
|
max-path-length: 1
|
|
responses:
|
|
'200':
|
|
description: Successful response
|
|
content:
|
|
application/json:
|
|
schema:
|
|
$ref: '../../components/schemas/rag/GraphRagResponse.yaml'
|
|
examples:
|
|
completeResponse:
|
|
summary: Complete non-streaming response
|
|
value:
|
|
response: |
|
|
Quantum physics and computer science intersect primarily through quantum computing.
|
|
The knowledge graph shows connections through:
|
|
- Quantum algorithms (Shor's algorithm, Grover's algorithm)
|
|
- Quantum information theory
|
|
- Computational complexity theory
|
|
end-of-stream: false
|
|
streamingChunk:
|
|
summary: Streaming response chunk
|
|
value:
|
|
response: "Quantum physics and computer science intersect"
|
|
end-of-stream: false
|
|
streamingComplete:
|
|
summary: Streaming complete marker
|
|
value:
|
|
response: ""
|
|
end-of-stream: true
|
|
'401':
|
|
$ref: '../../components/responses/Unauthorized.yaml'
|
|
'500':
|
|
$ref: '../../components/responses/Error.yaml'
|