Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

POST https://openapi.linkwo.ai/v1/embeddings

Request Body

Parameter	Type	Required	Default	Description
`model`	string	Yes	—	Embedding model ID
`input`	string/array	Yes	—	Text(s) to embed
`encoding_format`	string	No	float	`float` or `base64`
`dimensions`	integer	No	model default	Output dimensions (if supported)

Example Request

curl https://openapi.linkwo.ai/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-v3",
    "input": "The food was delicious and the waiter was friendly."
  }'

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023064255, -0.009327292, ...]
    }
  ],
  "model": "text-embedding-v3",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}
```bash

## Batch Embedding

Pass an array to embed multiple inputs in a single request:

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://openapi.linkwo.ai/v1",
    api_key="YOUR_API_KEY"
)

response = client.embeddings.create(
    model="text-embedding-v3",
    input=[
        "The food was delicious.",
        "The service was excellent.",
        "I would visit again."
    ]
)

for item in response.data:
    print(f"Input {item.index}: {len(item.embedding)} dimensions")

Use Cases

Use Case	Description
Semantic Search	Find documents similar to a query by comparing embedding distances
Clustering	Group similar texts together using vector similarity
Classification	Train classifiers on embedding vectors
Recommendations	Suggest items with similar embeddings

Choosing Dimensions

Some embedding models support adjustable output dimensions via the dimensions parameter. Lower dimensions reduce storage and computation costs at the expense of some representational fidelity.

response = client.embeddings.create(
    model="text-embedding-v3",
    input="Hello world",
    dimensions=256
)
```bash

## Best Practices

- **Pre-process text** — Remove unnecessary whitespace and normalize encoding before embedding
- **Batch requests** — Embed multiple texts in one call for better throughput
- **Cache results** — Store embeddings to avoid recomputing for the same input
- **Truncate long inputs** — Text exceeding the model's context limit will be truncated

## Related

- [Model Overview](/docs/models/model-overview) — Available embedding models
- [Chat Completions](/docs/api-reference/chat-completions) — Text generation API

Chat Completions

Responses API