[Feature Request]: Batch add chunks

[panzi]

Is there an existing issue for the same feature request?

• I have checked the existing issues.

Is your feature request related to a problem?

We do our own automated preprocessing of somewhat big data sets. Uploading it all as a single generated XSLX document would be too big. We need to record the relation of chunk IDs to our own database entries anyway, so we can properly update the chunks without re-doing everything.

Describe the feature you'd like

API method to batch add multiple chunks at once.

Document.add_chunks(chunks: list[str]) -> list[str]

The return value are the new chunk IDs, correctly correlated to the chunks as passed as the parameter.

Alternatively including the important_keywords parameter and returning Chunk objects:

from typing import TypedDict, NotRequired

class ChunkParams(TypedDict):
    content: str
    important_keywords: NotRequired[str]

Document.add_chunks(chunks: list[ChunkParams]) -> list[Chunk]

Describe implementation you've considered

No response

Documentation, adoption, use case

No response

Additional information

No response