xxm/opro_demo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add Docker support for offline deployment with qwen3:14b

Browse Source 
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
This commit is contained in:
leehwui
2025-12-08 10:10:38 +08:00
parent 65cdcf29dc
commit 26f8e0c648
13 changed files with 897 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
requirements.txt Normal file
View File

@@ -0,0 +1,7 @@
fastapi==0.109.0
uvicorn==0.27.0
requests==2.31.0
numpy==1.26.3
scikit-learn==1.4.0
pydantic==2.5.3