We present a sentence similarity model based on the Sentence Transformers architecture, which maps sentences to a 384-dimensional dense vector space. The model uses a pre-trained BERT encoder and applies mean pooling on top of the contextualized word embeddings to obtain sentence embeddings. We evaluate the model on the Sentence Embeddings Benchmark.
We present a sentence similarity model based on the Sentence Transformers architecture, which maps sentences to a 384-dimensional dense vector space. The model uses a pre-trained BERT encoder and applies mean pooling on top of the contextualized word embeddings to obtain sentence embeddings. We evaluate the model on the Sentence Embeddings Benchmark.
DeepInfra supports the OpenAI embeddings API. The following creates an embedding vector representing the input text
curl "https://api.deepinfra.com/v1/openai/embeddings" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPINFRA_TOKEN" \
-d '{
"input": "The food was delicious and the waiter...",
"model": "sentence-transformers/paraphrase-MiniLM-L6-v2",
"encoding_format": "float"
}'
which will return something similar to
{
"object":"list",
"data":[
{
"object": "embedding",
"index":0,
"embedding":[
-0.010480394586920738,
-0.0026091758627444506
...
0.031979579478502274,
0.02021978422999382
]
}
],
"model": "sentence-transformers/paraphrase-MiniLM-L6-v2",
"usage": {
"prompt_tokens":12,
"total_tokens":12
}
}
dimensions
integerThe number of dimensions in the embedding. If not provided, the model's default will be used.If provided bigger than model's default, the embedding will be padded with zeros.
Range: 32 ≤ dimensions