Embedding Generation

Text Embedding Models on Sentry Block

Sentry Block supports high-performance text embedding models for a wide range of language-processing applications, including search, semantic understanding, clustering, and classification.

---

Available Models

• UAE-Large-V1 A versatile, general-purpose model designed to generate high-accuracy embeddings across various topics and use cases.

• BGE Large EN v1.5 Fine-tuned specifically for English, this model offers enhanced performance for tasks requiring deeper semantic representation.

---

Using the Models

Through the API Endpoint

You can generate embeddings programmatically using Sentry Block’s API. Below are quick-start examples in multiple languages.

⚠️ Remember to use your Sentry API key. See the [API Reference] for more details on authentication and error handling.

---

cURL Example

bashCopyEditcurl -X POST "https://inference.sentryblock.com/v1/embeddings" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SENTRY_API_KEY" \
--data-raw '{
  "model": "WhereIsAI/UAE-Large-V1",
  "input": [ 
    "Bananas are berries, but strawberries are not, according to botanical classifications.",
    "The Eiffel Tower in Paris was originally intended to be a temporary structure."
  ]
}'

---

Python Example

pythonCopyEditimport requests
import os

url = "https://inference.sentryblock.com/v1/embeddings"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ.get('SENTRY_API_KEY')}"
}

data = {
    "model": "WhereIsAI/UAE-Large-V1",
    "input": [
        "Bananas are berries, but strawberries are not, according to botanical classifications.",
        "The Eiffel Tower in Paris was originally intended to be a temporary structure."
    ]
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

---

JavaScript Example

javascriptCopyEditconst url = 'https://inference.sentryblock.com/v1/embeddings';

const headers = {
  "Content-Type": "application/json",
  "Authorization": `Bearer ${process.env.SENTRY_API_KEY}`
};

const data = {
  model: "WhereIsAI/UAE-Large-V1",
  input: [
    "Bananas are berries, but strawberries are not, according to botanical classifications.",
    "The Eiffel Tower in Paris was originally intended to be a temporary structure."
  ]
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => {
    console.log(JSON.stringify(data, null, 2));
  })
  .catch(error => console.error('Error:', error));

---

Model Mapping

Use the following model identifiers when making API calls:

• UAE-Large-V1 → WhereIsAI/UAE-Large-V1

• BGE Large EN v1.5 → BAAI/bge-large-en-v1.5

---

Response Example

A successful embedding response will return a JSON object with the following structure:

jsonCopyEdit{
  "model": "WhereIsAI/UAE-Large-V1",
  "data": [
    {
      "embedding": [-0.373046875, ..., 0.248046875],
      "index": 0,
      "object": "embedding"
    },
    {
      "embedding": [-0.50390625, ..., 0.01409912109375],
      "index": 1,
      "object": "embedding"
    }
  ],
  "object": "list",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 33,
    "total_tokens": 33
  }
}

🔍 Note: Each input string receives its own embedding. In the example above, two input sentences were provided, and two indexed embeddings were returned accordingly.