2 Commits

Author	SHA1	Message	Date
leehwui	6426b73a5e	fix: export only required models instead of entire Ollama directory ... - Changed export-ollama-models.sh to selectively copy only qwen3:14b and qwen3-embedding:4b - Parses manifest files to identify required blob files - Significantly reduces Docker image size by excluding unrelated models - Added summary showing which models were skipped This prevents accidentally including other models (like deepseek-r1, bge-m3, etc.) that may exist in the user's Ollama directory but are not needed for the project.	2025-12-08 12:00:11 +08:00
leehwui	26f8e0c648	feat: add Docker support for offline deployment with qwen3:14b ... Major additions: - All-in-One Docker image with Ollama + models bundled - Separate deployment option for existing Ollama installations - Changed default model from qwen3:8b to qwen3:14b - Comprehensive deployment documentation Files added: - Dockerfile: Basic app-only image - Dockerfile.allinone: Complete image with Ollama + models - docker-compose.yml: Easy deployment configuration - docker-entrypoint.sh: Startup script for all-in-one image - requirements.txt: Python dependencies - .dockerignore: Exclude unnecessary files from image Scripts: - export-ollama-models.sh: Export models from local Ollama - build-allinone.sh: Build complete offline-deployable image - build-and-export.sh: Build and export basic image Documentation: - DEPLOYMENT.md: Comprehensive deployment guide - QUICK_START.md: Quick reference for common tasks Configuration: - Updated config.py: DEFAULT_CHAT_MODEL = qwen3:14b - Updated frontend/opro.html: Page title to 系统提示词优化	2025-12-08 10:10:38 +08:00