Denkwerk
hybrid search
Ranks up to 100 supplied documents twice: lexically with BM25 (same implementation and defaults as bm25-search) and semantically by cosine similarity of embeddings computed locally (multilingual: intfloat/multilingual-e5-small, MIT, with the required "query: "/"passage: " prefixes, truncation at 512 tokens; english: sentence-transformers/all-MiniLM-L6-v2, Apache-2.0, truncation at 256 word pieces; mean pooling and L2 normalization, int8 ONNX exports from the model repositories, pinned and.
POST https://denk.halowerk.com/v1/hybrid-searchInputs
| Field | Type | Required | Description |
|---|---|---|---|
| query | string | Yes | |
| documents | array | Yes | Strings or objects {id, text}. |
| model | string | No | |
| fusion | string | No | |
| rrf_k | integer | No | |
| alpha | number | No | weighted: share of the vector score. |
| top_k | integer | No | |
| stemming | string | No | |
| max_length | integer | No | Token limit per text for the embedding model (default and maximum: 512 multilingual, 256 english). |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"required": [
"query",
"documents"
],
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 2000
},
"documents": {
"type": "array",
"minItems": 1,
"maxItems": 100,
"description": "Strings or objects {id, text}.",
"items": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"maxLength": 4000
},
{
"type": "object",
"additionalProperties": false,
"required": [
"text"
],
"properties": {
"id": {
"type": "string",
"maxLength": 128
},
"text": {
"type": "string",
"minLength": 1,
"maxLength": 4000
},
"score": {
"type": "number"
}
}
}
]
}
},
"model": {
"type": "string",
"enum": [
"multilingual",
"english"
],
"default": "multilingual"
},
"fusion": {
"type": "string",
"enum": [
"rrf",
"weighted"
],
"default": "rrf"
},
"rrf_k": {
"type": "integer",
"minimum": 1,
"maximum": 1000,
"default": 60
},
"alpha": {
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.5,
"description": "weighted: share of the vector score."
},
"top_k": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 10
},
"stemming": {
"type": "string",
"enum": [
"none",
"german"
],
"default": "none"
},
"max_length": {
"type": "integer",
"minimum": 32,
"maximum": 512,
"description": "Token limit per text for the embedding model (default and maximum: 512 multilingual, 256 english)."
}
}
}Published input example
{
"query": "Wie hoch ist die Mehrwertsteuer?",
"documents": [
"Der allgemeine Umsatzsteuersatz in Deutschland beträgt 19 Prozent.",
"Die Hauptstadt ist Berlin."
]
}Result & documentation
Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.
More endpoints in this hub
- Denkwerk0.003 USDC
agent card generate
POSThttps://denk.halowerk.com/v1/agent-card-generateBuilds an Agent2Agent protocol Agent Card with protocolVersion, name, description, url, version, capabilities, default input/output modes and skills. Skills come from the supplied list or are derived from OpenAPI operations (operationId, su
- Denkwerk0.003 USDC
agent permission diff
POSThttps://denk.halowerk.com/v1/agent-permission-diffTakes the tool names (with optional descriptions) and permission scopes of an agent before and after a change and reports added and removed tools and scopes, classifies new capabilities by risk (payments, sending messages, deleting or writi
- Denkwerk0.003 USDC
annotation guide draft
POSThttps://denk.halowerk.com/v1/annotation-guide-draftTakes example texts per label and derives, without a language model, the most distinguishing terms per label (TF-IDF contrast against the other labels), representative examples, cross-label example pairs with high similarity that need a wri