4 commits

Author	SHA1	Message	Date
guangyang1206	2f3a33c9d5	feat(chunker): add table-aware chunk_text_hybrid to prevent mid-row table splits ... Document_chunker currently splits Markdown tables mid-row when the table is larger than a single chunk window, producing garbled rows that are useless for RAG retrieval (issue #1334). Changes: - document_chunker.py: add chunk_text_hybrid() that detects Markdown table blocks with a regex, emits each table as an indivisible single chunk, and feeds the surrounding prose through the normal chunk_text() chunker. - indexing_pipeline_service.py: route normal (non-code) documents through chunk_text_hybrid instead of chunk_text so tables are protected by default. Fixes #1334	2026-05-05 12:48:04 +08:00
DESKTOP-RTLN3BA\$punk	aabc24f82c	feat: enhance performance logging and caching in various components ... - Introduced slow callback logging in FastAPI to identify blocking calls. - Added performance logging for agent creation and tool loading processes. - Implemented caching for MCP tools to reduce redundant server calls. - Enhanced sandbox management with in-process caching for improved efficiency. - Refactored several functions for better readability and performance tracking. - Updated tests to ensure proper functionality of new features and optimizations.	2026-02-26 13:00:31 -08:00
CREDO23	5b616eac5a	fix: plug all gaps found in deep review of indexing pipeline	2026-02-25 02:20:44 +02:00
CREDO23	61e50834e6	feat: implement and test index method	2026-02-25 01:40:30 +02:00