Cheatsheets turn retrieved chunksets into concise, structure-aware prompt context.

Use Poma.create_cheatsheet(...) when you want one cheatsheet for one document:

from poma import Poma

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

relevant_chunksets = [result["chunksets"][0]]
all_chunks = result["chunks"]

cheatsheet = client.create_cheatsheet(
    relevant_chunksets=relevant_chunksets,
    all_chunks=all_chunks,
)

print(cheatsheet)

Use Poma.create_cheatsheets(...) when your retrieved chunksets span multiple documents:

cheatsheets = client.create_cheatsheets(
    relevant_chunksets=relevant_chunksets,
    all_chunks=all_chunks,
)

Input rules

• relevant_chunksets must contain a chunks list
• all_chunks must contain the matching chunk content
• file_id should identify the source document
• Duplicate chunk_index values within one document will fail validation

This same cheatsheet logic is also used by the bundled Qdrant, LangChain, and LlamaIndex integrations.