liyizhouAI d5a908077a perf: upgrade Graphiti LLM to Qwen 32B + improve progress feedback ... - Upgrade from Qwen2.5-7B to Qwen2.5-32B-Instruct (faster, better quality) - Add real-time progress messages: "正在处理第 X/Y 个文本块" - Log per-episode processing time - Expand progress range from 15-55% to 15-90% (no more episode polling step) - Add GRAPHITI_LLM_* separate config for graph building LLM Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering>		2026-04-13 15:31:16 +08:00
..
api	perf: upgrade Graphiti LLM to Qwen 32B + improve progress feedback	2026-04-13 15:31:16 +08:00
models	feat(i18n): replace hardcoded Chinese in backend SSE progress messages	2026-04-01 16:32:10 +08:00
services	perf: upgrade Graphiti LLM to Qwen 32B + improve progress feedback	2026-04-13 15:31:16 +08:00
utils	feat: merge upstream i18n + rebrand MiroFish → Foresight 先见之明	2026-04-11 16:40:13 +08:00
__init__.py	feat: merge upstream i18n + rebrand MiroFish → Foresight 先见之明	2026-04-11 16:40:13 +08:00
config.py	fix: use SiliconFlow free LLM+embedding for Graphiti	2026-04-13 14:09:26 +08:00