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

Use the top-level generate_cheatsheets(...) helper for new code:

from poma import PrimeCut, generate_cheatsheets

client = PrimeCut()
result = client.ingest("example.pdf")

relevant_chunksets = [result.chunksets[0].to_dict()]
all_chunks = [chunk.to_dict() for chunk in result.chunks]

cheatsheets = generate_cheatsheets(
    relevant_chunksets=relevant_chunksets,
    all_chunks=all_chunks,
)

cheatsheet = cheatsheets[0]["content"]
print(cheatsheet)

When your retrieved chunksets span multiple documents, generate_cheatsheets(...) returns one cheatsheet per document:

cheatsheets = generate_cheatsheets(
    relevant_chunksets=relevant_chunksets,
    all_chunks=all_chunks,
)

PrimeCut.create_cheatsheet(...) and PrimeCut.create_cheatsheets(...) still exist for compatibility, but both are deprecated.

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.