Embeddings

Generate vector embeddings for text input. Embeddings are numerical representations of text that capture semantic meaning, useful for search, clustering, classification, and retrieval-augmented generation (RAG).

Endpoint

POST https://api.tensoras.ai/v1/embeddings

Authentication

Authorization: Bearer tns_your_key_here

Request Body

Parameter	Type	Required	Default	Description
`model`	string	Yes	—	The embedding model to use. Currently supported: `bge-large-en-v1.5`.
`input`	string or array	Yes	—	The text to embed. Can be a single string or an array of strings. Maximum of 2048 tokens per string.
`encoding_format`	string	No	`"float"`	The format of the returned embeddings. Either `"float"` or `"base64"`.

Response Body

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023064255, -0.009327292, 0.015797347, ...]
    }
  ],
  "model": "bge-large-en-v1.5",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Field	Type	Description
`object`	string	Always `"list"`.
`data`	array	A list of embedding objects.
`data[].object`	string	Always `"embedding"`.
`data[].index`	integer	The index of the embedding in the input array.
`data[].embedding`	array	The embedding vector. A list of floats with 1024 dimensions for `bge-large-en-v1.5`.
`model`	string	The model used to generate the embeddings.
`usage`	object	Token usage statistics.
`usage.prompt_tokens`	integer	Number of tokens in the input.
`usage.total_tokens`	integer	Total tokens processed.

Examples

Single Text Embedding

curl

curl https://api.tensoras.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tns_your_key_here" \
  -d '{
    "model": "bge-large-en-v1.5",
    "input": "The quick brown fox jumps over the lazy dog."
  }'

Python

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.tensoras.ai/v1",
    api_key="tns_your_key_here",
)
 
response = client.embeddings.create(
    model="bge-large-en-v1.5",
    input="The quick brown fox jumps over the lazy dog.",
)
 
embedding = response.data[0].embedding
print(f"Embedding dimensions: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")

Node.js

import OpenAI from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.tensoras.ai/v1",
  apiKey: "tns_your_key_here",
});
 
const response = await client.embeddings.create({
  model: "bge-large-en-v1.5",
  input: "The quick brown fox jumps over the lazy dog.",
});
 
const embedding = response.data[0].embedding;
console.log(`Embedding dimensions: ${embedding.length}`);
console.log(`First 5 values: ${embedding.slice(0, 5)}`);

Batch Embeddings

Generate embeddings for multiple texts in a single request.

curl

curl https://api.tensoras.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tns_your_key_here" \
  -d '{
    "model": "bge-large-en-v1.5",
    "input": [
      "What is machine learning?",
      "How does natural language processing work?",
      "Explain deep neural networks."
    ]
  }'

Python

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.tensoras.ai/v1",
    api_key="tns_your_key_here",
)
 
texts = [
    "What is machine learning?",
    "How does natural language processing work?",
    "Explain deep neural networks.",
]
 
response = client.embeddings.create(
    model="bge-large-en-v1.5",
    input=texts,
)
 
for item in response.data:
    print(f"Text {item.index}: {len(item.embedding)} dimensions")

Node.js

import OpenAI from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.tensoras.ai/v1",
  apiKey: "tns_your_key_here",
});
 
const texts = [
  "What is machine learning?",
  "How does natural language processing work?",
  "Explain deep neural networks.",
];
 
const response = await client.embeddings.create({
  model: "bge-large-en-v1.5",
  input: texts,
});
 
for (const item of response.data) {
  console.log(`Text ${item.index}: ${item.embedding.length} dimensions`);
}

Computing Similarity

Use cosine similarity to measure the semantic similarity between two texts.

Python

import numpy as np
from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.tensoras.ai/v1",
    api_key="tns_your_key_here",
)
 
def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
 
response = client.embeddings.create(
    model="bge-large-en-v1.5",
    input=[
        "I love programming in Python",
        "Python is my favorite coding language",
        "The weather is nice today",
    ],
)
 
emb_a = response.data[0].embedding
emb_b = response.data[1].embedding
emb_c = response.data[2].embedding
 
print(f"Similarity (a, b): {cosine_similarity(emb_a, emb_b):.4f}")  # High similarity
print(f"Similarity (a, c): {cosine_similarity(emb_a, emb_c):.4f}")  # Low similarity

Error Handling

{
  "error": {
    "message": "Input text exceeds maximum token limit of 2048",
    "type": "invalid_request_error",
    "param": "input",
    "code": "token_limit_exceeded"
  }
}

Completions (Legacy)Rerank