Conversation
The HierarchicalChunker was treating entire sections as single chunks regardless of paragraph count. This adds SPLIT_BY_PARAGRAPHS strategy that splits on blank lines, merges short paragraphs (<20 words), and falls back to size-based splitting for oversized paragraphs. Also fixes an infinite loop in _chunk_text when overlap sent current_pos backwards on the last chunk. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the entire Python stack (src/kb_engine/, src/kdd/, tests/, docker/, migrations/) with a single TypeScript/Bun package. The new implementation covers indexing (16 extractors, paragraph chunking, embeddings via @huggingface/transformers), 6 query types (hybrid, graph, impact, semantic, coverage, violations), CLI (citty, 7 subcommands), and MCP server (@modelcontextprotocol/sdk, 7 tools). Key changes: - Runtime: Python 3.11+ → Bun/TypeScript - Graph: FalkorDB/NetworkX → graphology (in-memory) - Vectors: ChromaDB/HNSWLib → brute-force cosine (in-memory) - Embeddings: sentence-transformers → @huggingface/transformers - Storage: SQLite/PostgreSQL → .kdd-index/ JSON artifacts - CLI: Click → citty - MCP: FastMCP (Python) → @modelcontextprotocol/sdk (TS) - Docs: README, architecture doc, CI workflow rewritten; ADRs superseded Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
refactor the complete project to typescript.
Previoulsy we write the specs using our own method.