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

# Vectorize Content

> Chunks text, generates embeddings, and stores vectors for semantic search.

Each chunk is embedded using a text embedding model and stored in the board's
vector store. Use the [Search](/api-reference/documents/search) endpoint to
query the stored vectors.

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST "https://api.chatgrid.ai/v1/boards/a1b2c3d4-e5f6-7890-abcd-ef1234567890/documents/vectorize" \
    -H "Authorization: Bearer cgk_live_a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6" \
    -H "Content-Type: application/json" \
    -d '{
      "content": "The quarterly revenue report shows a 15% increase in SaaS subscriptions.\n\nCustomer retention improved to 94% in Q1, up from 91% in Q4.\n\nNew enterprise deals accounted for $2.3M in recurring revenue.",
      "node_id": "e5f6a7b8-c9d0-1234-efab-345678901234",
      "metadata": { "source": "annual-report-2026.pdf", "page": 3 }
    }'
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "object": "vectorize_result",
    "data": {
      "board_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "node_id": "e5f6a7b8-c9d0-1234-efab-345678901234",
      "chunks_stored": 3
    }
  }
  ```
</ResponseExample>