Arke
BuildSearch & Query

Argo Queries

The Argo query DSL -- combining semantic search with graph traversal.

Overview

The Argo query engine combines semantic search (Pinecone) with graph traversal (Neo4j) in a single query language.

Query Syntax

ENTRY_POINT [ENTRY_FILTER] [-[RELATION]{DEPTH}-> TARGET_FILTER]...

Examples

Find entities matching a text query:

"medical college"

Semantic + Type Filter

"george" type:person

Graph Traversal

Start from a semantic match and traverse relationships:

"alice" -[*]{,4}-> type:file

Find entities matching "alice", then traverse 1-4 hops of any relationship type to reach file entities.

Exact ID Entry Point

Start from a specific entity:

@01JENTITY... -[*]{,2}-> type:person

Relationship Type Filter

Traverse only specific relationship types:

@01JENTITY... -[contains]{,3}-> type:file

Query Components

ComponentSyntaxExample
Semantic entry"query text""climate policy"
ID entry@<entity_id>@01JENTITY...
Type filtertype:<type>type:file
Traversal-[predicate]{min,max}->-[*]{,4}->
Any predicate*-[*]{,2}->
Depth range{min,max}{1,3}

API Endpoint

POST /query
Content-Type: application/json
Authorization: Bearer <token>

{
  "query": "\"climate policy\" type:file -[*]{,3}-> type:collection"
}

On this page