Agentic Platform
Documentation API reference Tools Skills

Tools

Embed

embed

Generate embeddings from text

Generate embeddings from text input. Currently supports text-multilingual-embedding-002 model. Returns a vector representation of the input text that can be used for semantic search, similarity comparison, and other machine learning tasks.

Playground

Your organization, project and token stay in this browser's local storage and are sent straight to the API — this page never sees them.

POST
item
text required The text to generate an embedding for
config
model The embedding model to use

Billing

Fixed cost per text requested, plus semantic indexing on every token embedded. Submitted as a background batch it is billed at the async rate, which is cheaper than indexing while you wait.

These usage SKUs can be charged on a call.

SKU Credits Description
Tool call 1 per request Charged once per successful item, on top of any usage below.
Semantic indexing 25 per million tokens Turns text into vectors so it can be matched by meaning rather than by keyword.
Semantic indexing (async) 20 per million tokens The same indexing, submitted as a background batch.

Schemas

item is what you send, config how the tool behaves, and the response is what you get back.

Item

object
Properties
text string required

The text to generate an embedding for

Example
{
  "text": "string"
}

Configuration

object
Properties
model string

The embedding model to use

Default: "text-multilingual-embedding-002"

Example
{
  "model": "text-multilingual-embedding-002"
}

Response

object
Properties
embedding array required

The embedding vector as a list of floats

Example
{
  "embedding": [
    0.0
  ]
}

Endpoints

POST http://agents.botify.com/{organization}/{project}/embed/process
POST http://agents.botify.com/{organization}/{project}/embed/batch_process
POST http://agents.botify.com/{organization}/{project}/embed/async_process
POST http://agents.botify.com/{organization}/{project}/embed/async_batch_process

See running a long job in the background for the polling flow.

cURL

curl -X POST "http://agents.botify.com/{organization}/{project}/embed/process" \
  -H "Authorization: Bearer $BOTIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "text": "<text>"
  }
}'

Raw metadata