Skip to content

v1.0.1

Latest
Latest

Choose a tag to compare

View all tags
@rvong65 rvong65 released this 13 Jul 17:06
v1.0.1
e8ab39e

Summary

Compatibility release: migrated Groq cloud models to openai/gpt-oss-20b and openai/gpt-oss-120b before llama-3.1-8b-instant and llama-3.3-70b-versatile are decommissioned (2026-08-16). The public demo uses production Groq models only (preview/evaluation models excluded). Simulated mode — labeled mock fallback when the API is unavailable — is unchanged from v1.0.0.

Live demo: https://ethical-decision-simulator.streamlit.app/

What's new

Groq model migration

  • Removed deprecated llama-3.1-8b-instant and llama-3.3-70b-versatile from the model picker
  • Cloud lineup: openai/gpt-oss-20b (fast baseline, Explore default) and openai/gpt-oss-120b (high-reasoning tier)
  • Default Compare selection: GPT-OSS 20B + GPT-OSS 120B (same two-model audit pattern as before)
  • Groq’s recommended 1:1 replacements per model deprecations

Production models only

  • Excluded qwen/qwen3.6-27b — Groq preview models are for evaluation, may be discontinued without notice, and are not suitable for the public Streamlit Cloud demo
  • README Data Sources notes that preview models are intentionally omitted

UI & docs

  • Compare model multiselect caps at available models (max_selections=len(models) — two on Groq cloud)
  • Glossary and architecture docs updated for the two-model cloud lineup
  • Tech stack, attribution table, and version history refreshed

Tests

  • Offline tests updated for new model display names and API IDs (GPT-OSS 20B, GPT-OSS 120B)
  • 46 offline tests pass in CI (no API key required)
  • Live API smoke tests exercise GPT-OSS 20B single-run and 20B + 120B parallel compare when GROQ_API_KEY is set

Quick start

Unchanged from v1.0.0 — see README Quick Start.

Local (Groq):

git clone https://github.com/rvong65/ethical-decision-simulator.git
cd ethical-decision-simulator
python -m venv .venv
source .venv/bin/activate   # Windows: .\.venv\Scripts\activate
pip install -r requirements.txt
cp .streamlit/secrets.toml.example .streamlit/secrets.toml   # add GROQ_API_KEY
streamlit run app.py

Local Ollama (no Groq):

export LLM_PROVIDER=ollama   # Windows: $env:LLM_PROVIDER = "ollama"
streamlit run app.py

Docker:

git clone https://github.com/rvong65/ethical-decision-simulator.git
cd ethical-decision-simulator
docker compose up --build
# open http://localhost:8501

Try it: Home → Explore or Compare → pick a curated scenario → Run analysis or Run comparison.

Full changelog

See CHANGELOG.md#101---2026-07-13

Assets 2
Loading