HALOWERKModellwerk
document rerank
Embeds a query and at most 20 short documents on local nomic-embed-text, then sorts by cosine similarity with stable input-index tie breaks. Scores are not probabilities. No third-party text transfer; input is not silently truncated.
POST https://modell.halowerk.com/v1/document-rerankEingaben
| Feld | Typ | Pflicht | Beschreibung |
|---|---|---|---|
| query | string | Ja | |
| documents | array | Ja | |
| top_n | integer | Nein | |
| return_documents | boolean | Nein |
Vollständiges Eingabeschema anzeigen
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 1000
},
"documents": {
"type": "array",
"minItems": 1,
"maxItems": 20,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 1000
}
},
"top_n": {
"type": "integer",
"minimum": 1,
"maximum": 20
},
"return_documents": {
"type": "boolean",
"default": false
}
},
"required": [
"query",
"documents"
],
"additionalProperties": false
}Ergebnis & Dokumentation
Maschinenlesbare Dokumentation dieses Hubs
Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.
Weitere Endpunkte dieses Hubs
- Modellwerk0,003 USDC
chat completions
POSThttps://modell.halowerk.com/v1/chat-completionsRuns openai/gpt-oss-20b via GroqCloud. Messages are sent to Groq Inc., USA; payment metadata is not forwarded. At most 8 messages, 8192 UTF-8 bytes overall and 1024 completion tokens including reasoning. A length finish_reason exposes trunc
- Modellwerk0,002 USDC
context plan
POSThttps://modell.halowerk.com/v1/context-planPlans the division of a long input for a given model. It reserves room for the system prompt, the expected answer and a safety margin, then works out how many chunks are needed and where to cut, preferring paragraph boundaries over line and
- Modellwerk0,002 USDC
cost estimate
POSThttps://modell.halowerk.com/v1/cost-estimateWorks out what a call would cost. Give either the text itself or a token count, plus the expected output length, and get input, output, cache-read and cache-write cost per model with the total. Token counts derived from text are estimates f