infoxtractor/.env.example
Dirk Riemann 5ee74f367c
All checks were successful
tests / test (push) Successful in 1m52s
tests / test (pull_request) Successful in 1m45s
chore(model): switch default IX_DEFAULT_MODEL to qwen3:14b (already on host)
The home server's Ollama doesn't have gpt-oss:20b pulled; qwen3:14b is
already there and is what mammon's chat agent uses. Switching the default
now so the first deploy passes the /healthz ollama probe without an extra
`ollama pull` step. The spec lists gpt-oss:20b as a concrete example;
qwen3:14b is equally on-prem and Ollama-structured-output-compatible.

Touched: AppConfig default, BankStatementHeader Request.default_model,
.env.example, setup_server.sh ollama-list check, AGENTS.md, deployment.md,
live tests. Unit tests that hard-coded the old model string but don't
assert the default were left alone.

Also: ASCII en-dash in e2e_smoke.py Paperless-style text (ruff RUF001).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 12:20:23 +02:00

41 lines
1.6 KiB
Text

# InfoXtractor runtime configuration.
# Every variable is optional; defaults are suitable for running against the
# on-prem stack (Ollama on :11434, postgis on :5431). Copy to .env and fill in
# the Postgres password.
# --- Job store -----------------------------------------------------------
IX_POSTGRES_URL=postgresql+asyncpg://infoxtractor:<password>@host.docker.internal:5431/infoxtractor
# --- LLM backend ---------------------------------------------------------
IX_OLLAMA_URL=http://host.docker.internal:11434
IX_DEFAULT_MODEL=qwen3:14b
# --- OCR -----------------------------------------------------------------
IX_OCR_ENGINE=surya
# --- Pipeline behavior ---------------------------------------------------
IX_PIPELINE_WORKER_CONCURRENCY=1
IX_PIPELINE_REQUEST_TIMEOUT_SECONDS=2700
IX_GENAI_CALL_TIMEOUT_SECONDS=1500
IX_RENDER_MAX_PIXELS_PER_PAGE=75000000
# --- File fetching -------------------------------------------------------
IX_TMP_DIR=/tmp/ix
IX_FILE_MAX_BYTES=52428800
IX_FILE_CONNECT_TIMEOUT_SECONDS=10
IX_FILE_READ_TIMEOUT_SECONDS=30
# --- Transport / callbacks ----------------------------------------------
IX_CALLBACK_TIMEOUT_SECONDS=10
# --- Observability -------------------------------------------------------
IX_LOG_LEVEL=INFO
# --- Test-only -----------------------------------------------------------
# Set IX_TEST_MODE=fake to have the pipeline factory build FakeOCRClient /
# FakeGenAIClient instead of real ones (used by integration tests).
# IX_TEST_MODE=fake
# Set IX_TEST_OLLAMA=1 on the Mac to enable tests that require a real
# Ollama / Surya instance (tests/live/).
# IX_TEST_OLLAMA=1