feat: centralize embeddings in rag-core-lib and add semantic chunker #1
Conversation
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
robodev-r2d2
changed the title
- Added optional max/min chunk size enforcement to SemanticTextChunker using RecursiveCharacterTextSplitter. - Introduced new parameters: `breakpoint_threshold_amount`, `overlap`, and `recursive_text_splitter`. - Implemented logic to rebalance chunks to meet minimum size requirements. - Updated chunking logic to handle oversized chunks and ensure they are split appropriately. - Enhanced documentation for clarity on new features and parameters. fix: Ensure related metadata is unique in PageSummaryEnhancer - Modified PageSummaryEnhancer to ensure the "related" metadata list contains unique IDs. refactor: Update ChunkerSettings to reflect new chunking parameters - Removed deprecated parameters and added `breakpoint_threshold_amount`, `buffer_size`, and `min_size`. - Adjusted validation logic to accommodate changes in chunking strategy. chore: Update dependencies and improve project structure - Updated FastAPI, langchain, and other dependencies to their latest versions. - Introduced ChunkerType enumeration for better chunker type management. - Created ChunkerClassTypeSettings for environment-based configuration of chunker implementations. test: Add comprehensive tests for chunking behavior - Implemented tests to validate max/min chunk size enforcement and rebalance logic. - Ensured existing tests are updated to reflect changes in parameter names and functionality.
…and enhance semantic chunking settings
…S_TYPE_CHUNKER_TYPE
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary
Testing
https://chatgpt.com/codex/tasks/task_e_68f223af44b8832689386cfff962f6e7