mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-07-24 23:41:10 +02:00
fdef50e78d
- Add three-tier LLM architecture (Mistral NeMo, TildeOpen, Gemini fallback) - Fix context window handling for mistral-nemo (128K tokens) - Add LiteLLM context override to prevent 1M token bug - Remove Google Analytics tracking from frontend - Add migration and installation documentation - Optimize for CPU-only inference on 32GB RAM servers Performance improvements: - 95% reduction in API costs - Response times: 5-25 seconds (down from 30-120s) - Better Latvian language quality with TildeOpen - Eliminated timeout errors Architecture changes: - Primary: Mistral NeMo 12B (France, local via Ollama) - Grammar: TildeOpen 30B (Latvia, local via Ollama) - Fallback: Gemini 2.0 Flash (Google API, emergency only) Technical fixes: - Fixed LiteLLM reporting incorrect 1M token context (actual: 128K) - Created mistral-nemo:128k model with proper num_ctx parameter - Added context window override in backend utils - Comprehensive security patterns in .gitignore Documentation: - MIGRATION_LOCAL_LLM.md: Complete architecture and history - INSTALLATION_LOCAL_LLM.md: Step-by-step deployment guide - PR_DESCRIPTION.md: Detailed PR description - sync-from-production.sh: Secure deployment script Tested on production at https://ai.kapteinis.lv since November 17, 2025. Co-authored-by: Ojārs Kapteiņš <ojars@kapteinis.lv> Co-authored-by: Claude AI Assistant <code@anthropic.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| connector_service.py | ||
| docling_service.py | ||
| grammar_check.py | ||
| kokoro_tts_service.py | ||
| language_detector.py | ||
| llm_service.py | ||
| page_limit_service.py | ||
| query_service.py | ||
| reranker_service.py | ||
| streaming_service.py | ||
| stt_service.py | ||
| task_logging_service.py | ||