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
20 commits 44 branches 0 tags 765 KiB
Python 98.2%
Shell 1.1%
Dockerfile 0.7%
Find a file
Dirk Riemann 527fc620fe
All checks were successful
tests / test (pull_request) Successful in 1m0s
Details
tests / test (push) Successful in 1m28s
Details
feat(provenance): normalisers + short-value skip rule (spec §6) 
Pure functions the ReliabilityStep will compose to compare extracted values
against OCR snippets (and context.texts). Kept in one module so every rule
is directly unit-testable without pulling in the step ABC.

Highlights:

- `normalize_string`: NFKC + casefold + strip common punctuation (. , : ; !
  ? () [] {} / \\ ' " `) + collapse whitespace. Substring-compatible.

- `normalize_number`: returns the canonical "[-]DDD.DD" form (always 2dp)
  after stripping currency symbols. Heuristic separator detection handles
  Swiss-German apostrophes ("1'234.56"), de-DE commas ("1.234,56"), and
  plain ASCII ("1234.56" / "1234.5" / "1234"). Accepts native int/float/
  Decimal as well as str.

- `normalize_date`: dateutil parse with dayfirst=True → ISO YYYY-MM-DD.
  Date and datetime objects short-circuit to their isoformat().

- `normalize_iban`: uppercase + strip whitespace. Format validation is the
  call site's job; this is pure canonicalisation.

- `should_skip_text_agreement`: dispatches on type + value. Literal → skip,
  None → skip, numeric |v|<10 → skip, len(str) ≤ 2 → skip. Numeric check
  runs first so `10` (len("10")==2) is treated on the numeric side
  (not skipped) instead of tripping the string length rule.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 10:56:31 +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
docs Implementation plan for ix MVP 2026-04-18 10:34:30 +02:00
src/ix feat(provenance): normalisers + short-value skip rule (spec §6) 2026-04-18 10:56:31 +02:00
tests feat(provenance): normalisers + short-value skip rule (spec §6) 2026-04-18 10:56:31 +02:00
.env.example feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +02:00
.gitignore feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +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
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.