goldstein/infoxtractor
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
Async on-prem LLM-powered structured information extraction microservice
60 commits 44 branches 0 tags 765 KiB
Python 98.2%
Shell 1.1%
Dockerfile 0.7%
Find a file
Dirk Riemann 4646180942
All checks were successful
tests / test (push) Successful in 1m13s
Details
tests / test (pull_request) Successful in 1m10s
Details
feat(docker): Dockerfile (CUDA+python3.12) + compose with GPU reservation 
- nvidia/cuda:12.4 runtime base matches the deploy host's driver stack
  (immich-ml / monitoring use the same pattern).
- python3.12 via deadsnakes (Ubuntu 22.04 ships 3.10 only).
- System deps: libmagic1 (python-magic), libgl1/libglib2 (PIL + PyMuPDF
  headless), curl (post-receive /healthz probe), ca-certs (httpx TLS).
- uv sync --frozen --no-dev --extra ocr installs prod + Surya/torch;
  dev tooling stays out of the image.
- CMD runs `alembic upgrade head && uvicorn ix.app:create_app` — idempotent.
- Compose: single service, port 8994, GPU reservation mirroring immich-ml,
  labels for monitoring dashboard auto-discovery + backup opt-in.
- host.docker.internal:host-gateway lets ix reach the host's Ollama and
  postgis containers (same pattern mammon uses).

Task 5.1 of MVP plan.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 12:15:26 +02:00
.forgejo/workflows ci: run on every push (not just main) so feat branches also get CI 2026-04-18 10:40:44 +02:00
alembic feat(store): Alembic scaffolding + initial ix_jobs migration (spec §4) 2026-04-18 11:37:21 +02:00
docs Implementation plan for ix MVP 2026-04-18 10:34:30 +02:00
scripts test(pipeline): end-to-end hermetic test with fakes + synthetic fixture 2026-04-18 11:24:29 +02:00
src/ix feat(app): production wiring — factories, pipeline, /healthz real probes 2026-04-18 12:09:11 +02:00
tests feat(app): production wiring — factories, pipeline, /healthz real probes 2026-04-18 12:09:11 +02:00
.env.example feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +02:00
.gitignore feat(docker): Dockerfile (CUDA+python3.12) + compose with GPU reservation 2026-04-18 12:15:26 +02:00
.python-version feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +02:00
AGENTS.md Initial design: on-prem LLM extraction microservice MVP 2026-04-18 10:23:17 +02:00
alembic.ini feat(store): Alembic scaffolding + initial ix_jobs migration (spec §4) 2026-04-18 11:37:21 +02:00
docker-compose.yml feat(docker): Dockerfile (CUDA+python3.12) + compose with GPU reservation 2026-04-18 12:15:26 +02:00
Dockerfile feat(docker): Dockerfile (CUDA+python3.12) + compose with GPU reservation 2026-04-18 12:15:26 +02:00
pyproject.toml feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +02:00
README.md Initial design: on-prem LLM extraction microservice MVP 2026-04-18 10:23:17 +02:00
uv.lock feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +02:00

README.md

InfoXtractor (ix)

Async, on-prem, LLM-powered structured information extraction microservice.

Given a document (PDF, image, text) and a named use case, ix returns a structured JSON result whose shape matches the use-case schema — together with per-field provenance (OCR segment IDs, bounding boxes, cross-OCR agreement flags) that let the caller decide how much to trust each extracted value.

Status: design phase. Implementation about to start.

Principles

  • On-prem always. LLM = Ollama, OCR = local engines (Surya first). No OpenAI / Anthropic / Azure / AWS / cloud.
  • Grounded extraction, not DB truth. ix returns best-effort fields + provenance; the caller decides what to trust.
  • Transport-agnostic pipeline core. REST + Postgres-queue adapters in parallel on one job store.