Source: http://www.poma-ai.com/docs/sdk/migration/legacy-poma

# Legacy Poma Client Migration Guide

> `Poma` is the legacy client. It still ships in the SDK for compatibility. New code should use `PrimeCut`.

Use this page only when you need to maintain an older integration.

`Poma` stays dict-based and relies on polling helpers rather than the newer SSE-first collection flow.

## Legacy flow

```python
from poma import Poma

client = Poma()
job = client.start_chunk_file("example.pdf")
result = client.get_chunk_result(job["job_id"], show_progress=True)
```

## What stays available

- `start_chunk_file(...)`
- `start_chunk_file_eco(...)`
- `get_chunk_result(...)`
- `unpack_poma_archive(...)`
- `extract_chunks_and_chunksets_from_poma_archive(...)`
- `create_cheatsheet(...)`
- `create_cheatsheets(...)`
- `download_file(...)`
- `download_bytes(...)`

For a full migration map, see [Migrate from Poma to PrimeCut](/sdk/migration/poma-to-primecut).