Skip to content

feat(chunking): implement holistic chunking mechanism #575

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
badmonster0 merged 2 commits into from
May 30, 2025
Merged

feat(chunking): implement holistic chunking mechanism #575

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
37484bc
feat(chunking): implement holistic chunking mechanism
badmonster0 May 28, 2025
d305ebd
docs: update docs for `SplitRecursively`.
badmonster0 May 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions docs/docs/ops/functions.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,17 @@ Input data:

* `text` (type: `str`, required): The text to split.
* `chunk_size` (type: `int`, required): The maximum size of each chunk, in bytes.
* `min_chunk_size` (type: `int`, optional): The minimum size of each chunk, in bytes. If not provided, default to `chunk_size / 2`.

:::note

`SplitRecursively` will do its best to make the output chunks sized between `min_chunk_size` and `chunk_size`.
However, it's possible that some chunks are smaller than `min_chunk_size` or larger than `chunk_size` in rare cases, e.g. too short input text, or non-splittable large text.

Please avoid setting `min_chunk_size` to a value too close to `chunk_size`, to leave more rooms for the function to plan the optimal chunking.

:::

* `chunk_overlap` (type: `int`, optional): The maximum overlap size between adjacent chunks, in bytes.
* `language` (type: `str`, optional): The language of the document.
Can be a langauge name (e.g. `Python`, `Javascript`, `Markdown`) or a file extension (e.g. `.py`, `.js`, `.md`).
Expand Down
3 changes: 2 additions & 1 deletion examples/code_embedding/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ def code_to_embedding(
@cocoindex.flow_def(name="CodeEmbedding")
def code_embedding_flow(
flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.DataScope
):
) -> None:
"""
Define an example flow that embeds files into a vector database.
"""
Expand All @@ -46,6 +46,7 @@ def code_embedding_flow(
cocoindex.functions.SplitRecursively(),
language=file["extension"],
chunk_size=1000,
min_chunk_size=300,
chunk_overlap=300,
)
with file["chunks"].row() as chunk:
Expand Down
Loading