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

# Get Vectors

Retrieve specific vectors from the index by their IDs.

## Authentication

Required - API key via `X-API-Key` header:

```http theme={null}
X-API-Key: cyborg_your_api_key_here
```

You can get an API key from the [CyborgDB Admin Dashboard](https://cyborgdb.co). For more info, follow [this guide](../../../intro/get-api-key).

## Request Body

```json theme={null}
{
  "index_name": "my_index",
  "index_key": "64_character_hex_string_representing_32_bytes",
  "ids": ["item_1", "item_2", "item_3"],
  "include": ["vector", "contents", "metadata"]
}
```

<Expandable title="parameters">
  <ParamField body="index_name" type="string" required="true">
    Name of the target index
  </ParamField>

  <ParamField body="index_key" type="string">
    32-byte encryption key as a hex string. Required for indexes created with the SDK-supplied KEK path; omit for KMS-backed indexes (the service resolves the key via the stored KMSBlob).
  </ParamField>

  <ParamField body="ids" type="array[string]" required="true">
    List of item IDs to retrieve
  </ParamField>

  <ParamField body="include" type="array[string]" default={["vector", "contents", "metadata"]}>
    Fields to include in response:

    <Expandable title="include options">
      <ParamField body="vector" type="string">
        Include the stored rerank vector. Returned at the index's configured `storage_precision` (`float32` by default, or `float16` if set at create time).
      </ParamField>

      <ParamField body="contents" type="string">
        Include text content associated with the vector
      </ParamField>

      <ParamField body="metadata" type="string">
        Include item metadata key-value pairs
      </ParamField>
    </Expandable>
  </ParamField>
</Expandable>

## Response

```json theme={null}
{
  "results": [
    {
      "id": "item_1",
      "vector": [0.1, 0.2, 0.3, 0.4],
      "contents": "Hello world!",
      "metadata": {"category": "greeting", "language": "en"}
    },
    {
      "id": "item_2",
      "vector": [0.5, 0.6, 0.7, 0.8],
      "contents": "Bonjour monde!",
      "metadata": {"category": "greeting", "language": "fr"}
    }
  ]
}
```

If an item ID doesn't exist, it will be omitted from the results.

## Exceptions

* `401`: Authentication failed (invalid API key) **or** wrong `index_key` on SDK-supplied indexes — see [error model](../introduction#error-model-api-keys-index-keys-and-kms)
* `404`: Index not found
* `422`: Invalid request parameters
* `500`: Internal server error

## Example Usage

**Get All Fields:**

```bash theme={null}
curl -X POST "http://localhost:8000/v1/vectors/get" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "my_index",
       "index_key": "your_64_character_hex_key_here",
       "ids": ["item_1", "item_2", "item_3"]
     }'
```

**Get Only Contents:**

```bash theme={null}
curl -X POST "http://localhost:8000/v1/vectors/get" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "my_index",
       "index_key": "your_64_character_hex_key_here",
       "ids": ["doc_1", "doc_2", "doc_3"],
       "include": ["contents"]
     }'
```

**Get Metadata Only:**

```bash theme={null}
curl -X POST "http://localhost:8000/v1/vectors/get" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "my_index",
       "index_key": "your_64_character_hex_key_here",
       "ids": ["user_1", "user_2"],
       "include": ["metadata"]
     }'
```

**Batch Retrieval:**

```bash theme={null}
curl -X POST "http://localhost:8000/v1/vectors/get" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "my_index",
       "index_key": "your_64_character_hex_key_here",
       "ids": [
         "batch_1", "batch_2", "batch_3", "batch_4", "batch_5",
         "batch_6", "batch_7", "batch_8", "batch_9", "batch_10"
       ],
       "include": ["contents", "metadata"]
     }'
```

**Example Response (Contents Only):**

```json theme={null}
{
  "results": [
    {
      "id": "doc_1",
      "contents": "First document content here..."
    },
    {
      "id": "doc_2",
      "contents": "Second document content here..."
    },
    {
      "id": "doc_3",
      "contents": "Third document content here..."
    }
  ]
}
```

**Example Response (Metadata Only):**

```json theme={null}
{
  "results": [
    {
      "id": "user_1",
      "metadata": {
        "name": "Alice Smith",
        "role": "admin",
        "department": "engineering",
        "created": "2024-01-01"
      }
    },
    {
      "id": "user_2",
      "metadata": {
        "name": "Bob Johnson",
        "role": "user",
        "department": "marketing",
        "created": "2024-01-02"
      }
    }
  ]
}
```

## Use Cases

* **Content retrieval**: Get original text content by ID
* **Metadata lookup**: Retrieve item metadata for display
* **Data validation**: Verify stored data integrity
* **Bulk operations**: Retrieve multiple items efficiently
* **Content management**: Extract specific items for editing or processing