> ## Documentation Index
> Fetch the complete documentation index at: https://docs.samuraiapi.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Embedding

> Convert text to vector representations for semantic search, RAG, clustering, and classification.

<ParamField body="model" type="string" required>
  Embedding model. Options: `text-embedding-3-small` (1536 dims, fast), `text-embedding-3-large` (3072 dims, best accuracy), `text-embedding-ada-002` (legacy).
</ParamField>

<ParamField body="input" type="string | array" required>
  Text to embed. Pass a single string or an array of strings for batch embedding.
</ParamField>

<ParamField body="encoding_format" type="string" default="float">
  `float` returns an array of numbers. `base64` returns a base64-encoded string (smaller payload).
</ParamField>

<ParamField body="dimensions" type="integer">
  Number of output dimensions (model-dependent). Only for `text-embedding-3-*` models.
</ParamField>

<RequestExample>
  ```bash cURL - Single text theme={null}
  curl https://www.samuraiapi.in/v1/embeddings \
    -H "Authorization: Bearer $SAMURAI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "text-embedding-3-small",
      "input": "The way of the samurai"
    }'
  ```

  ```bash cURL - Batch theme={null}
  curl https://www.samuraiapi.in/v1/embeddings \
    -H "Authorization: Bearer $SAMURAI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "text-embedding-3-small",
      "input": [
        "The way of the samurai",
        "Machine learning is transforming the world",
        "Tokyo is the capital of Japan"
      ]
    }'
  ```

  ```python Python - Semantic search theme={null}
  import numpy as np
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-samurai-YOUR_KEY",
      base_url="https://www.samuraiapi.in/v1"
  )

  def embed(texts):
      res = client.embeddings.create(model="text-embedding-3-small", input=texts)
      return [d.embedding for d in res.data]

  def cosine_sim(a, b):
      return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

  docs = ["Tokyo is the capital of Japan", "Paris is the capital of France"]
  doc_vecs = embed(docs)

  query_vec = embed(["What is the capital of Japan?"])[0]
  scores = [cosine_sim(query_vec, v) for v in doc_vecs]
  print(docs[np.argmax(scores)])
  # => "Tokyo is the capital of Japan"
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "object": "list",
    "data": [
      {
        "index": 0,
        "object": "embedding",
        "embedding": [0.0023064255, -0.009327292, 0.015797656, "...1536 total floats..."]
      }
    ],
    "model": "text-embedding-3-small",
    "usage": {
      "prompt_tokens": 8,
      "total_tokens": 8
    }
  }
  ```
</ResponseExample>