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

# Create Knowledge

> Create a new knowledge base item.

# Create Knowledge

Add a new knowledge base item to your project. The content will be automatically chunked, embedded, and made available for agent retrieval.

## Endpoint

```
POST /v1/knowledge
```

## Request Body

| Field         | Type   | Required | Description                |
| ------------- | ------ | -------- | -------------------------- |
| `name`        | string | Yes      | Name of the knowledge item |
| `description` | string | No       | Description or summary     |
| `text`        | string | Yes      | Full text content          |

## Request

```bash theme={null}
curl -X POST "https://api.callem.ai/v1/knowledge" \
  -H "Authorization: Bearer ck_live_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Return Policy 2025",
    "description": "Updated return policy effective January 2025",
    "text": "## Return Policy\nItems can be returned within 30 days of purchase with original receipt.\n\n## Exceptions\nSale items are final sale and cannot be returned.\n\n## Process\nBring the item to any store location or ship it to our returns center."
  }'
```

## Response

```json theme={null}
{
  "id": "new123item456789012345678",
  "name": "Return Policy 2025",
  "description": "Updated return policy effective January 2025",
  "text": "## Return Policy\nItems can be returned within 30 days...",
  "createdAt": "2025-12-15T16:00:00.000Z"
}
```

<Tip>
  Structure your text content with `## Headings` to improve chunking quality. Each heading acts as a natural boundary for the vector embedding process.
</Tip>

## Errors

| Code  | Description                                |
| ----- | ------------------------------------------ |
| `400` | Missing required fields (`name` or `text`) |