huggingbay-xyz · Schema
EmbeddingsRequest
Artificial IntelligenceOpen SourceModelsPlatformMachine Learning
Properties
| Name | Type | Description |
|---|---|---|
| model | string | Hugging Face embedding id, or 'auto'. Auto deterministically serves BAAI/bge-small-en-v1.5; other models remain addressable by explicit id. |
| input | object | |
| omit_raw_result | boolean | Compact decision-first face (decision, vector metadata, next_call, weight, receipt) with the vectors omitted. Defaults false here for REST compatibility. |
| encoding_format | string | OpenAI-compatible embedding encoding. 'float' returns JSON number arrays; 'base64' returns a base64 string of the vector's little-endian float32 bytes, which is what OpenAI SDK decoders expect. |
| task_hint | object | |
| namespace | object | Private learned-routing namespace used by model='auto'. |
| routing_mode | string | default permits the bounded same-kind fallback; strict requires a live private proof. |
| prefer_warm | boolean | Prefer a resident compatible specialist when model='auto'. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/huggingbay-xyz/json-schema/huggingbay-xyz-embeddings-request-schema.json",
"title": "EmbeddingsRequest",
"x-generated": "2026-11-10",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/huggingbay-xyz-embeddings-api-openapi.yml#/components/schemas/EmbeddingsRequest",
"properties": {
"model": {
"type": "string",
"title": "Model",
"description": "Hugging Face embedding id, or 'auto'. Auto deterministically serves BAAI/bge-small-en-v1.5; other models remain addressable by explicit id."
},
"input": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
}
],
"title": "Input"
},
"omit_raw_result": {
"type": "boolean",
"title": "Omit Raw Result",
"description": "Compact decision-first face (decision, vector metadata, next_call, weight, receipt) with the vectors omitted. Defaults false here for REST compatibility.",
"default": false
},
"encoding_format": {
"type": "string",
"enum": [
"float",
"base64"
],
"title": "Encoding Format",
"description": "OpenAI-compatible embedding encoding. 'float' returns JSON number arrays; 'base64' returns a base64 string of the vector's little-endian float32 bytes, which is what OpenAI SDK decoders expect.",
"default": "float"
},
"task_hint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Task Hint"
},
"namespace": {
"anyOf": [
{
"type": "string",
"maxLength": 256
},
{
"type": "null"
}
],
"title": "Namespace",
"description": "Private learned-routing namespace used by model='auto'."
},
"routing_mode": {
"type": "string",
"enum": [
"default",
"strict"
],
"title": "Routing Mode",
"description": "default permits the bounded same-kind fallback; strict requires a live private proof.",
"default": "default"
},
"prefer_warm": {
"type": "boolean",
"title": "Prefer Warm",
"description": "Prefer a resident compatible specialist when model='auto'.",
"default": true
}
},
"type": "object",
"required": [
"model",
"input"
]
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/huggingbay-xyz-embeddings-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.