leehwui
1376d60ed5
- Add true OPRO system instruction optimization (vs query rewriting) - Implement iterative optimization with performance trajectory - Add new OPRO API endpoints (/opro/create, /opro/generate_and_evaluate, /opro/execute) - Create modern Gemini-style chat UI (frontend/opro.html) - Optimize performance: reduce candidates from 20 to 10 (2x faster) - Add model selector in UI toolbar - Add collapsible sidebar with session management - Add copy button for instructions - Ensure all generated prompts use simplified Chinese - Update README with comprehensive documentation - Add .gitignore for local_docs folder
21 lines
753 B
Python
21 lines
753 B
Python
APP_TITLE = "OPRO Prompt Optimizer API"
|
|
APP_DESCRIPTION = "提供提示优化、候选生成、会话聊天与模型管理的接口"
|
|
APP_VERSION = "0.1.0"
|
|
APP_CONTACT = {"name": "OPRO Team", "url": "http://127.0.0.1:8010/ui/"}
|
|
|
|
# Ollama endpoints
|
|
OLLAMA_HOST = "http://127.0.0.1:11434"
|
|
OLLAMA_GENERATE_URL = f"{OLLAMA_HOST}/api/generate"
|
|
OLLAMA_TAGS_URL = f"{OLLAMA_HOST}/api/tags"
|
|
DEFAULT_CHAT_MODEL = "qwen3:8b"
|
|
DEFAULT_EMBED_MODEL = "qwen3-embedding:4b"
|
|
|
|
# Xinference
|
|
XINFERENCE_EMBED_URL = "http://127.0.0.1:9997/models/bge-base-zh/embed"
|
|
|
|
# Clustering/selection
|
|
GENERATION_POOL_SIZE = 10 # Generate this many candidates before clustering
|
|
TOP_K = 5 # Return this many diverse candidates to user
|
|
CLUSTER_DISTANCE_THRESHOLD = 0.15
|
|
|