README.md

metadata

title: Elder Paperwork Co-Pilot
emoji: 📄
colorFrom: blue
colorTo: green
sdk: docker
pinned: false
app_port: 7860
tags:
  - track:backyard
  - sponsor:openbmb
  - sponsor:nvidia
  - sponsor:cohere
  - achievement:offgrid
  - achievement:offbrand
  - achievement:fieldnotes
  - achievement:llama

Elder Paperwork Co-Pilot

An offline AI assistant that securely summarizes complex medical paperwork.

📝 Read our Article

Check out our detailed article about this project here: Elder Care Copilot: Organizing the Chaos of Caregiving Paperwork

About this Project

Idea: An offline-first AI assistant that securely summarizes complex medical paperwork for elder care. Tech: Powered entirely locally to ensure privacy, the app utilizes MiniCPM-V for vision/OCR tasks, MiniCPM-5-1B for triage, NeMoTRON-PARS for table extraction, and Co-Transcribe for ASR. It includes custom themes, Llama.cpp smoke tests, and runs without any outbound network connections.

Standalone Hugging Face Space repo for the elder-paperwork demo.

What this repo contains:

• the split app entrypoint for this repo only
• the shared helper modules needed by the app and its eval runner
• only the demo packs that belong to this split repo

Local run

From the repo root:

python app.py

If you prefer an isolated environment:

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
python app.py

The app listens on PORT when set; otherwise app.py picks an available local port for local runs.

Trace artifacts are written on every demo-pack load or eval run. Use the Load sample data button in the UI or the eval runner JSON trace_path field to find the file under data/artifacts/<project>/traces/.

Off-brand UI

Custom styling lives in assets/theme.css. Edit that file to tune the accessible high-contrast palette, spacing, and typography. The app loads it at launch via Gradio css_paths.

Llama Champion smoke

The main app stays on its normal offline-first path; the badge is satisfied by a dedicated local GGUF smoke that exercises llama-cpp-python end-to-end and writes a small verification artifact.

uses openbmb/MiniCPM5-1B-GGUF (MiniCPM5-1B-Q4_K_M.gguf) as the preferred local GGUF because it matches the registry's MiniCPM-5-1B family.

Install dependencies with your normal venv flow; requirements.txt already points pip at the CPU wheel index for llama-cpp-python==0.3.28.

Download the model into models/:

mkdir -p models
huggingface-cli download openbmb/MiniCPM5-1B-GGUF MiniCPM5-1B-Q4_K_M.gguf --local-dir models

Direct smoke from the repo root:

LLAMA_CHAMPION_MODEL=models/MiniCPM5-1B-Q4_K_M.gguf python scripts/llama_champion_smoke.py --artifact-path artifacts/verification/$(date +%F)/llama_champion_smoke.json

The script writes artifacts/verification/<YYYY-MM-DD>/llama_champion_smoke.json by default if you omit --artifact-path.

Pytest wrapper:

LLAMA_CHAMPION_MODEL=models/MiniCPM5-1B-Q4_K_M.gguf .venv/bin/python -m pytest -q tests/test_llama_champion_smoke.py

If the pytest env does not already have llama_cpp, set LLAMA_CHAMPION_PYTHON to the interpreter that does.

Docker

Build the image:

docker build -t all4- .

Run the app container:

docker run --rm -p 7860:7860 all4-

Optional: run the bundled llama.cpp server from the same image with the same GGUF used above:

docker run --rm -p 8080:8080 -v "$PWD/models:/models" --entrypoint llama-server all4-   --model /models/MiniCPM5-1B-Q4_K_M.gguf --host 0.0.0.0 --port 8080

Notes:

• The image is CPU-only and multi-stage; it builds llama.cpp in a builder stage and keeps the runtime stage lean.
• .venv/ is ignored by the Docker build context, so local virtualenvs do not get baked into the image.
• The app and llama-server share the same image but are launched separately.

Offline verification

Run the bundled offline smoke check from the repo root:

bash scripts/offline_smoke.sh

CI-friendly pytest wrapper:

python -m pytest -q tests/test_offline_smoke.py

Docker variant with outbound networking disabled:

docker run --rm --network none -v "$PWD:/repo" -w /repo all4- bash scripts/offline_smoke.sh

The smoke check loads a bundled demo pack, blocks socket/HTTP client creation, and fails if any runtime code tries to reach the network.

Sponsor model policy gate

Run the repo-local sponsor gate without Docker:

python scripts/check_sponsor_model_policy.py
pytest -q tests/test_sponsor_model_policy.py

The gate checks that the registry matches the four planned sponsor components before any packaging or Docker verification step.

Field notes

See FIELD_NOTES.md for the badge artifact, evidence notes, and next steps.

Sharing traces

Use python scripts/share_traces_to_hf_dataset.py <traces-dir> to materialize a deterministic JSONL + metadata bundle under artifacts/verification/<YYYY-MM-DD>/sharing_is_caring/all4--elder-paperwork/.

• The default mode is local-only; pass --push plus --repo-id and HF_TOKEN to publish a Hugging Face Dataset bundle.
• --dry-run forces offline materialization even when --push is present.
• See CHANGELOG.md for the latest trace-sharing notes.

Submission assets

Fill these TODO fields before final submission; they are placeholders only and do not imply the assets already exist.

• TODO Hugging Face Space URL (build-small org): <SPACE_URL>
• TODO Public GitHub repo URL: <REPO_URL>
• TODO Demo video URL: <VIDEO_URL>
• TODO Social post URL: <SOCIAL_POST_URL>
• TODO Concise disclaimer: synthetic/repo-authored demo packs only; no PII/PHI.
• TODO Sponsor model attribution list:
  • OpenBMB MiniCPM-V 4.6: openbmb/MiniCPM-V-4_6 for ocr_vlm
  • OpenBMB MiniCPM-5 1B: openbmb/MiniCPM-5-1B for triage_llm
  • NVIDIA NeMoTRON-PARS: nvidia/NeMoTRON-PARS for table_parser
  • CoExpression Labs Co-Transcribe 2B: CoExpressionLabs/co-transcribe-2b for asr

Models and data attributions

• The bundled demo packs are synthetic or repo-authored and are licensed CC0-1.0 unless a subfolder README says otherwise.
• The sponsor-required registry entries are the four models listed above; keep configs/model_registry.yaml and configs/sponsor_model_policy.yaml aligned if you change them.
• The shared summary_llm helper also uses openbmb/MiniCPM-5-1B, but it is not part of the sponsor gate.
• The sample GGUF above is only an example; use a model whose license and size are suitable for your deployment.
• No PII/PHI is included in the shipped demo packs.