iints-sdk-python35 1.1.1

A pre-clinical Edge-AI SDK for diabetes management validation.

IINTS-AF SDK

IINTS-AF is a safety-first SDK for insulin-algorithm research. It lets you simulate, validate, and report results with reproducible artifacts.

Docs (GitHub Pages): python35.github.io/IINTS-SDK

What You Can Do

• Run virtual patient simulations.
• Test algorithm safety gates (deterministic supervisor).
• Add optional AI glucose forecasting.
• Validate datasets before training/evaluation.
• Generate audit-ready CSV/JSON/PDF/HTML outputs.

Quick Start

python3 -m venv .venv
source .venv/bin/activate
python -m pip install -U pip
pip install iints-sdk-python35

iints doctor --smoke-run
iints quickstart --project-name iints_quickstart
cd iints_quickstart
iints presets run --name baseline_t1d --algo algorithms/example_algorithm.py

AI Assistant (Ministral 3 Open-Weight via Ollama)

The SDK now includes a research-only AI assistant layer for explanations and run summaries. It is gated by MDMP verification before any LLM call is allowed.

Use an active virtual environment for the full flow:

python3 -m venv .venv
source .venv/bin/activate
python -m pip install -U pip
python -m pip install -e ".[mdmp]"

Run the open local Mistral model locally with Ollama:

python -m pip install -e ".[mdmp]"
ollama pull ministral-3:8b
iints ai models

Recommended first-time setup:

ollama pull ministral-3:8b
iints ai local-check --model ministral-3:8b

Example commands:

iints ai explain results/step.json \
  --mdmp-cert results/report.signed.mdmp

iints ai report results/simulation_run.json \
  --mdmp-cert results/report.signed.mdmp \
  --output results/ai_report.md

Notes:

• AI analysis is blocked if the MDMP artifact is invalid.
• Minimum required MDMP grade defaults to research_grade.
• The SDK now targets the open local Ministral 3 Ollama model by default.
• Users can choose a larger or smaller local Mistral-family model with --model ....
• Large JSON payloads are clipped automatically before prompt generation to keep local inference stable.
• Output is research-only and not medical advice.

MDMP (Short)

MDMP is the data-quality protocol used by IINTS.

• Contract: defines expected columns, types, units, and bounds.
• Validation: checks a dataset against the contract.
• Fingerprint + Grade: writes deterministic hashes and a grade (draft, research_grade, clinical_grade).
• Visualizer: builds a single-file HTML report for audits.

Use the dedicated namespace:

iints mdmp template --output-path mdmp_contract.yaml
iints mdmp validate mdmp_contract.yaml data/my_cgm.csv --output-json results/mdmp_report.json
iints mdmp visualizer results/mdmp_report.json --output-html results/mdmp_dashboard.html

Use standalone MDMP backend (optional):

export IINTS_MDMP_BACKEND=mdmp_core

Staleness / lineage checks (standalone MDMP CLI):

mdmp fingerprint-record data/my_cgm.csv --output-json results/fingerprint.json --expires-days 365
mdmp fingerprint-check results/fingerprint.json data/my_cgm.csv
mdmp lineage-card-refresh results/mdmp_model_card.yaml
mdmp registry init --registry registry/mdmp_registry.json
mdmp registry push --registry registry/mdmp_registry.json --report results/mdmp_report.json

Dual Repo Workflow

• SDK repo: python35/IINTS-SDK
• MDMP repo: python35/MDMP

Local helper scripts:

• tools/dev/dual_repo_status.sh
• tools/dev/dual_repo_commit_push.sh

Full process: docs/DUAL_REPO_WORKFLOW.md

MDMP sync CI gate:

• .github/workflows/mdmp-sync.yml
• Uses private-repo checkout when MDMP_REPO_TOKEN is configured.
• Falls back to mdmp-protocol from PyPI when checkout is unavailable.
• Auto dependency updates for MDMP are handled via Dependabot (.github/dependabot.yml).

Tools Layout

Repository helpers are now grouped by purpose:

• scripts/: simple user-facing shortcuts like test, lint, and demo entrypoints
• tools/ci/: CI gates and policy checks
• tools/dev/: maintainer workflows and multi-repo helpers
• tools/docs/: manual and documentation builders
• tools/data/: dataset import and conversion utilities
• tools/analysis/: plotting, diagnostics, and report helpers
• tools/assets/: branding and asset generation helpers

Reference: tools/README.md

Typical Workflow

1. Prepare or import data.
2. Validate data with MDMP.
3. Run simulation or forecast evaluation.
4. Review report artifacts and metrics.

Key Commands

iints run-full --algo algorithms/example_algorithm.py --scenario-path scenarios/clinic_safe_baseline.json --output-dir results/run_full
iints scorecard --algo algorithms/example_algorithm.py --profile research_default --output-dir results/scorecard
iints study-ready --algo algorithms/example_algorithm.py --output-dir results/study_ready
iints sources --output-json results/source_manifest.json

Documentation

• Docs site: python35.github.io/IINTS-SDK
• Plain guide: docs/PLAIN_LANGUAGE_GUIDE.md
• Comprehensive guide: docs/COMPREHENSIVE_GUIDE.md
• MDMP draft: docs/MDMP.md
• Demos: examples/demos
• Notebooks: examples/notebooks

Safety Notice

For research use only. Not a medical device. No clinical dosing advice.