Knowledge Share
Technical articles, tutorials, and insights
Open Source Project of the Day (#170): CodeWiki — ACL 2026 Research-Grade Codebase Documentation with Recursive Multi-Agent Architecture
FPT Software's open-source codebase-level documentation generation framework, accepted at ACL 2026. Tree-Sitter AST parsing + recursive multi-agent architecture + hierarchical synthesis, handling codebases from 86K to 1.4M lines across 9 languages. Outputs Markdown docs with Mermaid architecture diagrams. Benchmarked above DeepWiki (68.79% vs 64.06%) on CodeWikiBench. 1.5k Stars, MIT license. Includes comparison with similar open-source projects.
Codebase Knowledge Base Series (04): Three Chunking Strategies — AST Precision Loses?
Comparing fixed-line, file-level, and AST function-level chunking on 266 lines of Python: fixed-line and file-level both score Recall@5=1.000, AST scores 0.958. Counterintuitive finding: precise semantic boundaries hurt because the free-rider effect disappears. Root cause: calculate_order_total piggybacks on create_payment_intent in large chunks, but stands alone — and semantically distant from 'Stripe charge' — in AST chunks. Engineering guidance: AST wins at scale; chunk size trade-offs favor precision in large codebases.
Codebase Knowledge Base Series (01): Technical Landscape — Why Code Understanding Is 10x Harder Than Document Retrieval
A codebase isn't an upgraded document store — it's a fundamentally different knowledge type. Four understanding layers (syntactic/semantic/architectural/intent) map to four retrieval requirements. Traditional grep, vector search, AST symbol indexing, and call graph retrieval each have distinct capability limits. This article builds the complete framework for codebase knowledge systems.
RAG Series (24): Code RAG — Teaching AI to Understand Your Codebase
The final article in the RAG series. Code is not a document — it has structure (functions/classes), semantics (docstrings), and call relationships (call graph). Plain text chunking destroys all three. This article uses AST to parse the llm-in-action codebase (22 Python files, 225 code units), builds a call graph (168 edges), and implements semantic code search plus call chain traversal. Real results: build_self_rag_graph's full downstream chain, main's 54 direct calls, build_index's call tree — all found correctly.