curl --request POST \
--url https://api.friendli.ai/dedicated/v1/embeddings \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "(endpoint-id)"
}
'{
"id": "embd-26a1e10db1311bc2adb488d2d205288b",
"model": "(endpoint-id)",
"object": "list",
"data": [
{
"index": 0,
"object": "embedding",
"embedding": [
0.0023064255,
-0.009327292,
-0.0028842222
]
}
],
"usage": {
"prompt_tokens": 26,
"completion_tokens": 0,
"total_tokens": 26
},
"created": 1735722153
}Dedicated embeddings
Generate text embedding vectors using your Friendli Dedicated Endpoint. Convert text into dense vector representations for search and similarity.
curl --request POST \
--url https://api.friendli.ai/dedicated/v1/embeddings \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "(endpoint-id)"
}
'{
"id": "embd-26a1e10db1311bc2adb488d2d205288b",
"model": "(endpoint-id)",
"object": "list",
"data": [
{
"index": 0,
"object": "embedding",
"embedding": [
0.0023064255,
-0.009327292,
-0.0028842222
]
}
],
"usage": {
"prompt_tokens": 26,
"completion_tokens": 0,
"total_tokens": 26
},
"created": 1735722153
}Authorizations
Headers
ID of team to run requests as (optional parameter).
Body
ID of target endpoint. If you want to send request to specific adapter, use the format "YOUR_ENDPOINT_ID:YOUR_ADAPTER_ROUTE". Otherwise, you can just use "YOUR_ENDPOINT_ID" alone.
"(endpoint-id)"
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.
Either input or tokens field is required.
"The food was delicious and the waiter..."
The tokenized prompt (i.e., input tokens).
Either input or tokens field is required.
Response
Successfully generated embeddings.
A unique ID of the embeddings.
The object type, which is always set to list.
"list"A list of embedding objects.
Hide child attributes
Hide child attributes
The index of the embedding in the list of embeddings.
The object type, which is always set to embedding.
"embedding"The embedding vector, which is a list of floats or a base64-encoded string. The length of vector depends on the model.
Hide child attributes
Hide child attributes
Number of tokens in the prompt.
5
Number of tokens in the generated completions.
7
Total number of tokens used in the request (prompt_tokens + completion_tokens).
12
The Unix timestamp (in seconds) for when the embeddings were created.
The model to generate the embeddings. For dedicated endpoints, it returns the endpoint id.