Create embeddings (PydanticAI - Cohere format)
Creates embeddings using Cohere-compatible format via PydanticAI.
Bearer token authentication. Use your MPilot virtual-key JWT or admin JWT.
Virtual keys (prefixed with sk-bf-) can also be passed here.
In: header
ID of an available embedding model
Specifies the type of input passed to the model. Required for embedding models v3 and higher.
Array of strings to embed. Maximum 96 texts per call. At least one of texts, images, or inputs is required.
items <= 96Array of image data URIs for multimodal embedding. Maximum 1 image per call. Supports JPEG, PNG, WebP, GIF up to 5MB.
items <= 1Array of mixed text/image components for embedding. Maximum 96 per call.
items <= 96Specifies the return format types (float, int8, uint8, binary, ubinary, base64). Defaults to float if unspecified.
Number of dimensions for output embeddings (256, 512, 1024, 1536). Available only for embed-v4 and newer models.
Maximum tokens to embed per input before truncation.
Handling for inputs exceeding token limits. Defaults to END.
Response Body
curl -X POST "https://loading/{AI_GATEWAY_URL}/pydanticai/cohere/v2/embed" \ -H "Content-Type: application/json" \ -d '{ "model": "embed-english-v3.0", "input_type": "string" }'{
"id": "string",
"embeddings": {
"float": [
[
0
]
],
"int8": [
[
0
]
],
"uint8": [
[
0
]
],
"binary": [
[
0
]
],
"ubinary": [
[
0
]
],
"base64": [
"string"
]
},
"response_type": "string",
"texts": [
"string"
],
"images": [
{
"width": 0,
"height": 0,
"format": "string",
"bit_depth": 0
}
],
"meta": {
"api_version": {
"version": "string",
"is_deprecated": true,
"is_experimental": true
},
"billed_units": {
"input_tokens": 0,
"output_tokens": 0,
"search_units": 0,
"classifications": 0
},
"tokens": {
"input_tokens": 0,
"output_tokens": 0
},
"warnings": [
"string"
]
}
}{
"type": "string",
"message": "string",
"code": "string"
}{
"type": "string",
"message": "string",
"code": "string"
}