Embedding
The Embeddings API allows you to transform text into numerical vectors that capture the semantic meaning of the text. These vectors are highly optimized for searching, clustering, and classifying data within vector databases.
Creating an Embedding
To generate a vector embedding from a string of text, make a POST request to the /v1/embeddings endpoint.
https://api.geodd.io/inference/v1/embeddings
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/jsonID of the model to use for embeddings.
geodd-text-embedding-v2
Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays.
Responses
Authorization header.Example Request:
{
"model": "geodd-text-embedding-v2",
"input": "Geodd AI infrastructure is built for high performance scale."
}Response:
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
0.0023064255,
-0.009327292,
0.0157973...
]
}
],
"model": "geodd-text-embedding-v2",
"usage": {
"prompt_tokens": 10,
"total_tokens": 10
}
}Models
You can use standard Geodd embedding models, or specify any open-source embedding model hosted on your Geodd deployment. Ensure the dimensions expected by your vector database match the output length of the embedding model used.