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

# Convert Document

> Start processing an uploaded document — converts, chunks, and generates embeddings.

Initiate document processing for an uploaded file. The document goes through conversion (PDF/DOCX to markdown), chunking, and embedding generation.

## Endpoint

```
POST /convert-document
```

## Authentication

Required.

## Request body

<ParamField body="agentId" type="string" required>
  The agent ID the document belongs to.
</ParamField>

<ParamField body="documentId" type="string" required>
  The document ID to process.
</ParamField>

## Response

<ResponseField name="success" type="boolean">
  Whether processing was initiated.
</ResponseField>

<ResponseField name="callId" type="string">
  Processing job ID for status polling.
</ResponseField>

<ResponseField name="message" type="string">
  Status message.
</ResponseField>

## Example

```bash theme={null}
curl -X POST https://api.mind-e.co/convert-document \
  -H "Authorization: Bearer sk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "agentId": "agent-id-here",
    "documentId": "doc-id-here"
  }'
```

### Response

```json theme={null}
{
  "success": true,
  "callId": "call-abc123",
  "message": "Document processing started"
}
```

<Note>
  Document processing is asynchronous. Use [Conversion Status](/api-reference/documents/conversion-status) to check progress. Processing typically takes 10–60 seconds depending on document size.
</Note>