Search

Search Ideas

GET /api/v1/ideas/search

Search across all ideas using keyword matching or AI-powered semantic search.

Query Parameters

Parameter	Type	Required	Description
q	string	Yes	Search query
mode	string	No	keyword or semantic (default: automatic — uses semantic search with full-text search fallback)

Keyword Search

Keyword mode performs a text match against idea titles and bodies. Results are ordered by relevance.

curl

curl "https://neuralrepo.com/api/v1/ideas/search?q=dark+mode&mode=keyword" \
  -H "X-API-Key: nrp_YOUR_KEY"

JavaScript

const params = new URLSearchParams({
  q: "dark mode",
  mode: "keyword",
});
const res = await fetch(
  `https://neuralrepo.com/api/v1/ideas/search?${params}`,
  { headers: { "X-API-Key": "nrp_YOUR_KEY" } }
);
const results = await res.json();

Semantic Search

Semantic mode converts the query into a vector embedding and finds ideas with similar meaning, even if they use different words. This is useful for finding conceptually related ideas.

curl "https://neuralrepo.com/api/v1/ideas/search?q=user+interface+theming&mode=semantic" \
  -H "X-API-Key: nrp_YOUR_KEY"

Response

200 OK

The response includes a query echo and a search_type field indicating which mode was used (semantic or fts) and a score on each result representing relevance.

{
  "query": "user interface theming",
  "search_type": "semantic",
  "results": [
    {
      "id": 42,
      "title": "Add dark mode support",
      "body": "Users have requested a dark theme...",
      "status": "exploring",
      "source": "web",
      "source_url": null,
      "tags": ["ui", "feature-request"],
      "score": 0.92,
      "created_at": "2026-03-20T10:00:00Z",
      "updated_at": "2026-03-22T14:30:00Z"
    },
    {
      "id": 18,
      "title": "Theme customization options",
      "body": "Allow users to pick accent colors...",
      "status": "building",
      "source": "web",
      "source_url": null,
      "tags": ["ui"],
      "score": 0.85,
      "created_at": "2026-03-18T08:00:00Z",
      "updated_at": "2026-03-19T11:00:00Z"
    }
  ]
}

Score Field

The score field is a floating-point number between 0 and 1:

Mode	Score meaning
keyword	null — full-text search does not produce a numeric score
semantic	Cosine similarity between query and idea embeddings

Higher scores indicate stronger matches. Results are always sorted by descending score.

Comparison

Feature	Keyword	Semantic
Matches exact words	Yes	Not necessarily
Finds conceptual matches	No	Yes
Requires vector index	No	Yes
Speed	Faster	Slightly slower

Status Codes

Status	Meaning
200 OK	Search completed
400 Bad Request	Missing q parameter or invalid mode
401 Unauthorized	Missing or invalid auth