Skip to content
SolidRusT.ai

Hybrid search

POST
/data/v1/query/hybrid

Combines semantic similarity search with knowledge graph relationships. Extracts entities from the query using a dictionary-based extractor, then merges and re-scores vector + graph results with configurable weighting.

Authorizations

Request Body required

object
query
required

The search query text

string
How do I use Python SDK for embeddings?
semantic_weight

Weight for semantic search results in final scoring

number
default: 0.7 <= 1
graph_weight

Weight for knowledge graph results in final scoring

number
default: 0.3 <= 1
sources

Filter results to specific sources

Array<string>
entity_boost

Entity names to boost in results ranking

Array<string>
limit
integer
default: 10 >= 1 <= 100
use_entity_extraction

Whether to extract entities from the query before searching

boolean
default: true
game

Game domain for entity extraction (e.g. ‘eve’, ‘valorant’)

string
use_graph

Whether to use Neo4j graph traversal for entity expansion

boolean
default: true
graph_depth

Maximum graph traversal depth when use_graph is enabled

integer
default: 2 >= 1 <= 5

Responses

200

Successful response

object
query
string
entities_found

Entity names extracted from the query

Array<string>
results
Array<object>

A single result from hybrid search with source attribution

object
id
string
title
string
content
string
source
string
source_id
string
content_type
string
url
string
score

Combined relevance score (0-1)

number
origin

Source of this result

string
Allowed values: vector graph both
total
integer
vector_count

Number of results from vector search

integer
graph_count

Number of results from graph traversal

integer
merged_count

Number of results after merging and deduplication

integer
latency_ms
number

400

Invalid request

object
error
object
message
string
type
string
code
string
param
string

401

Invalid or missing API key

object
error
object
message
string
type
string
code
string
param
string