Hybrid keyword and semantic search across apps, skills, knowledge, and published pages.
→ Search concept — collections, suggest vs search, and workspace discovery
Suggest
GET /suggest or POST /suggest
Unified search for UI autocomplete and discovery. Returns actionable results ranked globally by relevance score across apps, skills, knowledge, and published pages.
Authentication is optional. Without a token, results are limited to public skills and apps. With a token, knowledge entries in your namespace are included.
Query Parameters (GET)
| Field | Type | Required | Description |
|---|---|---|---|
q | string | Yes | Search query |
GET does not accept limit, category, or agent — use POST for those fields.
Request Body (POST)
GET only reads q. Use POST for limit, category, and agent.
1{2 "query": "flux",3 "context": "We were comparing image models for logos.",4 "limit": 10,5 "category": "app",6 "agent": false7}| Field | Type | Default | Description |
|---|---|---|---|
query | string | — | Search query (required). Used for keyword matching |
context | string | empty | Optional conversation context for embedding enrichment. Keyword search uses query only; when present, semantic ranking embeds context + \n\n + query |
limit | integer | 3 (all categories) or 10 (single category) | Per-category cap after global ranking and dedup. When category is empty, each collection (apps, skills, knowledge, pages) may contribute up to limit hits; the response is still one globally ranked list |
category | string | empty = all | Filter to app, skill, or knowledge. Invalid values return 400 |
agent | boolean | false | Agent mode: full descriptions (no 200-rune truncation) for programmatic consumers |
Response
With X-API-Version: 2 (recommended):
1{2 "query": "flux",3 "results": [4 {5 "type": "app",6 "name": "pruna/flux-dev",7 "description": "Advanced text-to-image generation...",8 "command": "belt app run pruna/flux-dev",9 "score": 0.9210 },11 {12 "type": "skill",13 "name": "myteam/code-review",14 "description": "Guidelines for reviewing pull requests",15 "command": "belt skill use myteam/code-review",16 "score": 0.8517 }18 ]19}| Field | Description |
|---|---|
type | Result category: app, skill, knowledge, or page subtype (doc, blog, …) |
name | Display name or namespace/name for entities |
description | Short summary (truncated to 200 runes unless agent: true) |
command | Suggested CLI command or doc URL |
score | Relevance score (0–1) |
Results below the relevance floor (default 0.8) are omitted from /suggest responses. Forks with identical content collapse to the highest-scoring hit via content-hash dedup; when the same base name appears under multiple namespaces with different content, only the highest-scoring variant is returned. When searching all collections, each type is hard-capped at limit results so a single collection cannot dominate the list. Lower-scoring hits may still appear in GET /search when you need broader recall.
Without X-API-Version: 2, the same payload is wrapped in { "success": true, "data": { ... } }. See REST overview — API version.
Example
1curl "https://api.inference.sh/suggest?q=flux" \2 -H "X-API-Version: 2"1curl -X POST https://api.inference.sh/suggest \2 -H "Content-Type: application/json" \3 -H "X-API-Version: 2" \4 -d '{"query": "flux", "limit": 5, "agent": true}'Search
GET /search or POST /search
Direct search with collection and filter control. Returns scored hits with entity metadata.
Query Parameters (GET)
| Field | Type | Required | Description |
|---|---|---|---|
q | string | Yes | Search query |
collections | string | No | Comma-separated collections: apps, skills, knowledge, pages |
limit | integer | No | Max results per collection |
Request Body (POST)
1{2 "query": "payment processing",3 "collections": ["knowledge", "skills"],4 "limit": 205}Response
With X-API-Version: 2 (recommended):
1{2 "query": "payment processing",3 "results": [4 {5 "collection": "knowledge",6 "id": "know_abc123",7 "score": 0.87,8 "fields": {9 "name": "stripe-webhooks",10 "namespace": "myteam",11 "description": "Stripe webhook handling patterns",12 "type": "reference",13 "parent_id": "know_abc123",14 "updated_at": 177073201915 }16 }17 ]18}Without X-API-Version: 2, the same payload is wrapped in { "success": true, "data": { ... } }. See REST overview — API version.
| Field | Description |
|---|---|
collection | Source collection (apps, skills, knowledge, pages) |
id | Entity ID |
score | Relevance score (0–1) |
fields | Collection-specific metadata (name, namespace, description, tags, etc.) |
Example
1curl "https://api.inference.sh/search?q=flux&collections=apps,skills&limit=10" \2 -H "X-API-Version: 2"1curl -X POST https://api.inference.sh/search \2 -H "Authorization: Bearer inf_your_key" \3 -H "X-API-Version: 2" \4 -H "Content-Type: application/json" \5 -d '{6 "query": "payment processing",7 "collections": ["knowledge"],8 "limit": 209 }'Use an API key when searching private knowledge entries. Public apps and skills are searchable without authentication.
Collections
| Collection | Contents |
|---|---|
apps | Apps in the grid |
skills | Skills from the registry and your team |
knowledge | Observations, references, preferences (requires auth for private entries) |
pages | Published documentation and blog posts |
Search combines keyword matching with semantic similarity. Newly created entities are keyword-searchable immediately; semantic ranking improves after background embedding completes.
If query embedding fails or times out, the API returns keyword-only results for that request (no semantic re-ranking).
Related APIs
- Search concept — when to use suggest vs search and what each collection contains
- Skills — list, create, and manage skills
- Knowledge — manage knowledge entries that appear in search