Generate embeddings for text input | PrivateGPT

Generate vector embeddings from input text. This endpoint converts text into high-dimensional vector representations that capture semantic meaning. These embeddings preserve semantic relationships between texts and can be used for various machine learning tasks. Notes: - Empty strings or arrays are not accepted - Results include index numbers for mapping back to original inputs - All embeddings are generated as query vectors. If the embeddings have two modes (e.g., query and document), this endpoint only returns query vectors.

Generate vector embeddings from input text.

This endpoint converts text into high-dimensional vector representations that capture semantic meaning. These embeddings preserve semantic relationships between texts and can be used for various machine learning tasks.

Notes:

Empty strings or arrays are not accepted
Results include index numbers for mapping back to original inputs
All embeddings are generated as query vectors. If the embeddings have two modes (e.g., query and document), this endpoint only returns query vectors.

Request

This endpoint expects an object.

inputstring or list of stringsRequired

The text(s) to generate embeddings for. Can be a single string or an array of strings. Each text should be a meaningful unit of text (sentence, paragraph, etc).

modelstringOptionalDefaults to default

Model identifier or alias.

Response

This endpoint returns an object.

datalist of objects

List of embeddings, one for each input text

object"list"

The type of object returned

model"private-gpt"

The model used to generate embeddings

Errors

401

Unauthorized

422

Unprocessable Entity

Generate vector embeddings from input text.

Notes:

Empty strings or arrays are not accepted
Results include index numbers for mapping back to original inputs
All embeddings are generated as query vectors. If the embeddings have two modes (e.g., query and document), this endpoint only returns query vectors.

This endpoint expects an object.

The text(s) to generate embeddings for. Can be a single string or an array of strings. Each text should be a meaningful unit of text (sentence, paragraph, etc).

Model identifier or alias.

This endpoint returns an object.

List of embeddings, one for each input text

The type of object returned

The model used to generate embeddings

$	curl -X POST https://host.com/v1/embeddings \
>	-H "Content-Type: application/json" \
>	-d '{
>	"input": "input"
>	}'

1	{
2	"data": [
3	{
4	"index": 0,
5	"embedding": [
6	0.123,
7	-0.456,
8	0.789,
9	0.234,
10	-0.567,
11	0.891,
12	-0.123,
13	0.445,
14	-0.678,
15	0.901
16	],
17	"object": "embedding"
18	}
19	],
20	"object": "list",
21	"model": "private-gpt"
22	}

$	curl -X POST https://host.com/v1/embeddings \
>	-H "Content-Type: application/json" \
>	-d '{
>	"input": "input"
>	}'

1	{
2	"data": [
3	{
4	"index": 0,
5	"embedding": [
6	0.123,
7	-0.456,
8	0.789,
9	0.234,
10	-0.567,
11	0.891,
12	-0.123,
13	0.445,
14	-0.678,
15	0.901
16	],
17	"object": "embedding"
18	}
19	],
20	"object": "list",
21	"model": "private-gpt"
22	}