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

# Add Knowledge (Manual)

> Add content directly without a URL

Add knowledge by uploading content directly, bypassing URL crawling. Useful for internal documentation, transcripts, or content not available on the web.

## Request Body

<ParamField body="title" type="string" required>
  Title for the knowledge source
</ParamField>

<ParamField body="content" type="string">
  Text content to add (minimum 50 characters). Required if not uploading a file.
</ParamField>

<ParamField body="file" type="file">
  File to upload (PDF, TXT, or MD). Maximum 500KB. Required if not providing content.
</ParamField>

## Response

<ResponseField name="id" type="string">
  Unique knowledge source identifier
</ResponseField>

<ResponseField name="title" type="string">
  The provided title
</ResponseField>

<ResponseField name="sync_status" type="string">
  Status: `completed` on success
</ResponseField>

<ResponseField name="chunk_count" type="integer">
  Number of text chunks created
</ResponseField>

<ResponseField name="crawl_mode" type="string">
  Source type: `manual`, `pdf`, or `text`
</ResponseField>

<RequestExample>
  ```bash cURL (Text Content) theme={null}
  curl -X POST "https://api.magpipe.ai/functions/v1/knowledge-source-manual" \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "title": "Company FAQ",
      "content": "Q: What are your business hours?\nA: We are open Monday through Friday, 9 AM to 5 PM.\n\nQ: Where are you located?\nA: Our office is at 123 Main Street, San Francisco, CA."
    }'
  ```

  ```bash cURL (File Upload) theme={null}
  curl -X POST "https://api.magpipe.ai/functions/v1/knowledge-source-manual" \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -F "title=Product Manual" \
    -F "file=@manual.pdf"
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "id": "123e4567-e89b-12d3-a456-426614174000",
    "title": "Company FAQ",
    "sync_status": "completed",
    "chunk_count": 2,
    "crawl_mode": "manual",
    "created_at": "2026-01-15T10:30:00Z"
  }
  ```

  ```json 400 theme={null}
  {
    "error": "Content must be at least 50 characters"
  }
  ```
</ResponseExample>

## Notes

* Manual sources don't auto-sync (no `sync_period`)
* PDF text extraction works best with text-based PDFs (not scanned images)
* Supported file types: `.pdf`, `.txt`, `.md`
* Maximum file size: 500KB