Generate embeddings

POST

api

embed

curl http://localhost:11434/api/embed -d '{
 "model": "embeddinggemma",
 "input": "Why is the sky blue?"
}'

{
 "model": "embeddinggemma",
 "embeddings": [
 [
 0.010071029,
 -0.0017594862,
 0.05007221,
 0.04692972,
 0.054916814,
 0.008599704,
 0.105441414,
 -0.025878139,
 0.12958129,
 0.031952348
 ]
 ],
 "total_duration": 14143917,
 "load_duration": 1019500,
 "prompt_eval_count": 8
}

Body

application/json

model

string

required

Model name

input

required

Text or array of texts to generate embeddings for

truncate

boolean

default:true

If true, truncate inputs that exceed the context window. If false, returns an error.

dimensions

integer

Number of dimensions to generate embeddings for

keep_alive

string

Model keep-alive duration

options

object

Runtime options that control text generation

Show child attributes

Response

200 - application/json

Vector embeddings for the input text

model

string

Model that produced the embeddings

embeddings

number[][]

Array of vector embeddings

total_duration

integer

Total time spent generating in nanoseconds

load_duration

integer

Load time in nanoseconds

prompt_eval_count

integer

Number of input tokens processed to generate embeddings

TagsFetch a list of models and their details

curl http://localhost:11434/api/embed -d '{
 "model": "embeddinggemma",
 "input": "Why is the sky blue?"
}'

{
 "model": "embeddinggemma",
 "embeddings": [
 [
 0.010071029,
 -0.0017594862,
 0.05007221,
 0.04692972,
 0.054916814,
 0.008599704,
 0.105441414,
 -0.025878139,
 0.12958129,
 0.031952348
 ]
 ],
 "total_duration": 14143917,
 "load_duration": 1019500,
 "prompt_eval_count": 8
}