feat: add semantic chunker & centralize embeddings in rag-core-lib; helm + deps updates #148
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Outdated suggestions cannot be applied.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.
Adds an optional semantic chunker to the admin pipeline and centralizes embedding implementations in rag-core-lib (with re-exports in rag-core-api). Updates Helm to support chunker selection and preloads NLTK data; bumps deps.
Key points:
New SemanticTextChunker with min/max enforcement & sentence-aware rebalancing.
Select via CHUNKER_CLASS_TYPE_CHUNKER_TYPE (recursive default, semantic optional).
Embeddings moved to rag-core-lib (STACKIT/Ollama), re-exported in rag-core-api.
Helm: new config/secret wiring; NLTK data fetched at startup; values.yaml gains CHUNKER_* knobs.
Deps: add langchain-experimental, nltk; bump fastapi, uvicorn, langfuse; tests for semantic chunker.
Minor: de-dup related IDs in page summaries.