POMA AI ⬣ Docs

Appearance

POMA AI SDK v1 ​

v1 is the archived SDK line built around the original Poma client.

PrimeCut was introduced later. If you want the current SDK, switch back to Latest.

v1 is deprecated, but it remains available for stable legacy integrations.

Start with the 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)

print(len(result["chunks"]))
print(len(result["chunksets"]))

Getting started ​

  • Installation Install poma and the integration extras you need.
  • Authentication Create a POMA_API_KEY and configure your environment.
  • Quickstart Process your first document with the legacy Poma client.

Core workflow ​

  • Submit a file with Poma.start_chunk_file(...)
  • Poll for the result with Poma.get_chunk_result(...)
  • Work with legacy dictionary responses for chunks and chunksets
  • Save or reopen .poma archives with the legacy archive helpers
  • Generate structure-preserving cheatsheets for retrieval
  • Connect the result to Qdrant, LangChain, or LlamaIndex

Concepts ​

Integrations and reference ​