Search

Semantic search without answer generation. See the Search guide.

Method	Path
POST	/api/v1/search

Search

POST /api/v1/search

Hybrid semantic search; returns ranked passages without generating an answer.

From the API schema: Hybrid semantic search over the corpus (RAGFlow retrieval). Results are deduplicated per node and point to graph nodes (nodeIndex).

Auth: API key (X-API-Key) or user session

Request body

{
  "case": "cordis",
  "query": "perovskite solar cells",
  "topK": 5
}

cURL

curl -X POST "https://vol.example.com/api/v1/search" \
  -H "X-API-Key: $VOL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"case":"cordis","query":"perovskite solar cells","topK":5}'

TypeScript

import { VolClient } from "@vol/sdk";

const vol = new VolClient({ baseUrl: "https://vol.example.com/api", apiKey: process.env.VOL_API_KEY });
await vol.search({ case: "cordis", query: "perovskite solar cells", topK: 5 });

Python

import os, requests

r = requests.post(
    "https://vol.example.com/api/v1/search",
    headers={"X-API-Key": os.environ["VOL_API_KEY"]},
    json={
      "case": "cordis",
      "query": "perovskite solar cells",
      "topK": 5
    },
    timeout=60,
)
r.raise_for_status()
print(r.json())

Response 200

{
  "results": [
    {
      "nodeIndex": 412,
      "nodeId": "paper_412",
      "title": "Graph-augmented retrieval for scientific QA",
      "snippet": "We combine a citation graph with dense retrieval…",
      "score": 0.87,
      "docName": "paper_412.pdf",
      "chunkId": "8c1e…"
    }
  ]
}

Types

interface SearchRequest { case: CaseId; query: string; topK?: number }

type CaseId = "papers" | "cordis" | "patents" | "trials";

interface SearchResponse { results: Citation[] }

interface Citation {
  nodeIndex: number;
  nodeId: string;
  title: string;
  snippet: string;
  score: number;
  docName?: string;
  chunkId?: string;
}