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

# Create Embeddings

> Generate vector embeddings for input text using AI models

Create embeddings for the given input text(s).

This endpoint creates vector embeddings, typically for the purpose of "RAG" (Retrieval Augemented Generation) storage. It automatically manages sessions and routes requests to the appropriate embedding model.

### Headers

<ParamField header="Authorization" type="string" required>
  API key in format: `Bearer sk-xxxxxx`
</ParamField>

### Body

<ParamField body="input" type="string" required>
  Input text to generate embeddings for. Can be a single string or an array of strings.

  **Single text example:**

  ```json theme={null}
  "input": "The quick brown fox jumps over the lazy dog"
  ```

  **Multiple texts example (batch processing):**

  ```json theme={null}
  "input": ["First text", "Second text", "Third text"]
  ```

  <Warning>
    When using the interactive playground, it may show `"input": {}` - ignore this and manually edit the generated cURL command to use either a string `"text"` or array `["text1", "text2"]` format.
  </Warning>
</ParamField>

<ParamField body="model" type="string" required>
  Model ID to use for embedding generation (blockchain hex address or name)

  <Note>
    Use the [List Models](/api-reference/models/list) endpoint to see available embedding models.
  </Note>
</ParamField>

<ParamField body="encoding_format" type="string" default="float">
  Format for the embedding vectors. Options: `float` or `base64`
</ParamField>

<ParamField body="user" type="string">
  Unique identifier representing your end-user for monitoring and abuse detection
</ParamField>

### Response

<ResponseField name="object" type="string">
  Always returns `"list"`
</ResponseField>

<ResponseField name="data" type="array">
  Array of embedding objects

  <Expandable title="Embedding Object">
    <ResponseField name="object" type="string">
      Always `"embedding"`
    </ResponseField>

    <ResponseField name="embedding" type="array">
      Vector representation of the input text as an array of floats (or base64 if specified)
    </ResponseField>

    <ResponseField name="index" type="integer">
      Index of the embedding in the array (corresponds to the input array position)
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="model" type="string">
  Model used for generating the embeddings
</ResponseField>

<ResponseField name="usage" type="object">
  Token usage statistics

  <Expandable title="Usage Object">
    <ResponseField name="prompt_tokens" type="integer">
      Number of tokens in the input
    </ResponseField>

    <ResponseField name="total_tokens" type="integer">
      Total tokens processed
    </ResponseField>
  </Expandable>
</ResponseField>

## Example Request

<CodeGroup>
  ```python Python theme={null}
  import openai

  client = openai.OpenAI(
      api_key="sk-xxxxxx",
      base_url="https://api.mor.org/api/v1"
  )

  response = client.embeddings.create(
      model="text-embedding-model",
      input="The quick brown fox jumps over the lazy dog"
  )

  print(response.data[0].embedding)
  ```

  ```javascript Node.js theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
    apiKey: 'sk-xxxxxx',
    baseURL: 'https://api.mor.org/api/v1'
  });

  const response = await client.embeddings.create({
    model: 'text-embedding-model',
    input: 'The quick brown fox jumps over the lazy dog'
  });

  console.log(response.data[0].embedding);
  ```

  ```curl cURL theme={null}
  curl -X POST https://api.mor.org/api/v1/embeddings \
    -H "Authorization: Bearer sk-xxxxxx" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "text-embedding-model",
      "input": "The quick brown fox jumps over the lazy dog"
    }'
  ```
</CodeGroup>

## Use Cases

<CardGroup cols={2}>
  <Card title="Semantic Search" icon="magnifying-glass">
    Generate embeddings for documents and queries to enable similarity-based search
  </Card>

  <Card title="Clustering" icon="object-group">
    Group similar texts together by comparing embedding vectors
  </Card>

  <Card title="Recommendations" icon="stars">
    Build recommendation systems by finding similar items based on embeddings
  </Card>

  <Card title="Classification" icon="tags">
    Use embeddings as features for text classification models
  </Card>
</CardGroup>

<Tip>
  The API is fully compatible with the OpenAI SDK. Simply change the `base_url` to point to the Morpheus Gateway.
</Tip>

<Warning>
  Embedding dimensions vary by model. Ensure your application can handle different vector sizes when switching models.
</Warning>