Offline Adventures - lets start journey with AI

说明与用途

Offline Adventures 是一个本地优先的活动推荐器，利用 Streamlit 和本地 Llama 模型，根据时间、能量、天气和兴趣快速推荐活动，确保隐私和确定性约束。

问题

Users need a quick, privacy‑preserving way to find suitable local activities based on time, energy, weather, and interests.

结果

The system provides privacy‑preserving, deterministic‑constraint‑aware activity recommendations with semantic ranking, achieving 30 outdoor, 8 sheltered, and 12 indoor‑bridge activities in a curated catalog.

工作流

• Collect user inputs (time, energy, weather, place types, group, interests).
• Apply deterministic Python filters for hard constraints (time, energy, weather, place types, group, candidate ID validation, session diversity).
• Select up to 15 approved candidates.
• Send candidates to local llama3.1:8b-instruct-q4_K_M via Ollama for semantic ranking and personalization.
• Validate structured JSON output with Pydantic.
• Present recommendation with mission and notes in Streamlit.

证据

Offline Adventures is a local-first activity recommender designed to make choosing an activity quick, then get out of the way.

来源

The application uses a deliberately hybrid architecture.

来源

Deterministic Python code handles hard constraints: available time; energy level; current weather; accessible place types; group type; candidate ID validation; session diversity.

来源

After filtering, up to 15 approved candidates are sent to a local llama3.1:8b-instruct-q4_K_M model through Ollama.

来源

The repository includes the curated 50-activity catalog, automated tests, a catalog validator, and a real Ollama smoke test.

来源

At submission time the project had 19 passing tests and a validated catalog distribution of 30 outdoor, 8 sheltered, and 12 indoor-bridge activities.

来源