POMA AI ⬣ Docs

Appearance

Poma.get_chunk_result(...) returns plain dictionaries.

Result shape ​

python
from poma import Poma

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

print(type(result["chunks"]).__name__)
print(type(result["chunksets"]).__name__)
print(result.get("images", {}).keys())

The result dictionary typically contains:

  • chunks: a list of chunk dictionaries
  • chunksets: a list of chunkset dictionaries
  • images: a dictionary of extracted images as base64 data URIs

What's inside a .poma archive? ​

For the full embedded archive breakdown, see PomaArchive. That reference page includes the interactive archive explorer and shows which files are core to the SDK versus broader processing artifacts.

Reopen a saved .poma archive ​

python
from poma import Poma

client = Poma()
result = client.unpack_poma_archive(poma_archive_path="store/example.poma")

You can also unpack an archive from in-memory bytes:

python
client = Poma()
result = client.unpack_poma_archive(poma_archive_data=raw_poma_bytes)

The legacy client already returns dictionaries, so no .to_dict() conversion step is required.