Feature/auto chunking#191
Open
donhardman wants to merge 2 commits into
Open
Conversation
- Implement token-accurate chunking for local models - Add character-based heuristic chunking for remote API models - Support configurable strategies, overlap, and maximum chunk limits - Add utility to snap chunk boundaries to natural text separators - Introduce ChunkSettings, ChunkSpan, and DocChunks structs - Add make_vect_embeddings_chunked and free_chunked_result to EmbedLib - Implement ChunkedVecResult for flat embeddings and byte-offset spans - Export chunking functionality via FFI interface - Fix memory leak by freeing CString error pointers in knn bindings - Bump supported embeddings library version to 5 BREAKING CHANGE: Updated EmbedLib version and added new FFI function pointers for chunked embeddings
- Add unicode-segmentation dependency for boundary detection - Implement UAX #29 sentence-based splitting and greedy grouping - Introduce chunk_text dispatcher with token budgets and overlap - Define ChunkSettings, ChunkSpan, and DocChunks for FFI compatibility - Implement ChunkedVecResult for grouped embedding outputs - Add token counting helpers for local and remote models - Unify chunking logic across model implementations - Add comprehensive tests for sentence splitting and edge cases
5 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.