Estimates token count for any supported source type.
The accepted config keys and their validation rules are described by the `source-types` endpoint.
Authorization
Bearer JWT Authorization header using the Bearer scheme. Enter 'Bearer' [space] and then your token.
In: header
Path Parameters
The tenant identifier
The source type and configuration parameters.
Represents a generalized configuration for an asset, serving as a transport model for storage and cross-system communication.
Auth credentials for an integration — the chosen auth method plus its filled-in parameters (API keys, tokens, …).
Response Body
curl -X POST "https://api.fruxon.com/v1/tenants/string/assets:estimate" \ -H "Content-Type: application/json" \ -d '{ "config": {} }'{
"tokenCount": 0,
"chunkCount": 0,
"documentCount": 0,
"documents": [
{
"fileName": "string",
"tokenCount": 0,
"chunkCount": 0
}
]
}{
"type": "string",
"title": "string",
"status": 0,
"detail": "string",
"instance": "string",
"property1": null,
"property2": null
}Lists supported embedding models.
Returns the embedding models that the RAG service currently accepts for new assets, including their vector dimensions and pricing identifiers. Pair the chosen model with an asset's `embeddingConfig` when calling `POST /assets` or `POST /assets:file`. The list is tenant-agnostic and rarely changes; clients may cache it for the duration of a session.
Uploads a file asset to an agent's knowledge base.
Streams the uploaded file to managed storage, creates an asset backed by that file, and kicks off ingestion. Returns the asset plus a `LongOperation` whose progress is observable via `GET /assets/{asset}/operations`. The `payload` form part is a JSON object: when `Vectorize` is true an `EmbeddingConfig` matching a model from `GET /assets:embeddingModels` is required. Accepted content types are listed by `GET /assets:supportedTypes`; uploads larger than 50 MB are rejected with 413.