matthias
7678d28717
Self-hosted, verifiable pipeline for extracting structured data (station, date/time, price per litre, litres, discount, total) from German fuel receipt photos: grayscale + mild bilateral filter + contrast stretch, Tesseract OCR, then LLM structuring via a small local model (Qwen 2.5, served by Ollama). Each step is independently runnable and inspectable through numbered scripts against a shared tooling container. Ollama runs as its own long-lived container (0_run_ollama.sh), separate from the stateless per-receipt pipeline steps, so the model stays loaded in memory between runs. Includes a containerized ground-truth batch test (test_batch.sh) that reproduces the full pipeline over the test receipts and reports per-field accuracy. Targets eventual deployment on a Raspberry Pi 4 k3s cluster.
65 lines
2.0 KiB
Bash
65 lines
2.0 KiB
Bash
#!/usr/bin/env bash
|
|
# Step 0: start the Ollama inference server that the pipeline's
|
|
# structuring step (3_extract_data.sh) talks to. Runs the official
|
|
# ollama/ollama image as a long-lived container with model weights kept
|
|
# in a named Docker volume - deliberately separate from the
|
|
# tooling-container (which is stateless and one-shot per receipt), so the
|
|
# model stays loaded in memory between pipeline runs instead of being
|
|
# reloaded on every receipt.
|
|
#
|
|
# Usage: ./0_run_ollama.sh [-model <name>]
|
|
set -euo pipefail
|
|
|
|
cd "$(dirname "${BASH_SOURCE[0]}")"
|
|
|
|
fail() { echo "FAIL: $*" >&2; exit 1; }
|
|
|
|
command -v docker >/dev/null 2>&1 || fail "docker not found in PATH"
|
|
|
|
MODEL="qwen2.5:3b"
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
-model) MODEL="${2:-}"; shift 2 ;;
|
|
*) fail "unknown argument: $1" ;;
|
|
esac
|
|
done
|
|
|
|
CONTAINER=gastronomy-ollama
|
|
VOLUME=gastronomy-ollama-data
|
|
PORT=11434
|
|
|
|
if docker ps --format '{{.Names}}' | grep -qx "$CONTAINER"; then
|
|
echo "== $CONTAINER already running =="
|
|
elif docker ps -a --format '{{.Names}}' | grep -qx "$CONTAINER"; then
|
|
echo "== Starting existing $CONTAINER container =="
|
|
docker start "$CONTAINER" >/dev/null
|
|
else
|
|
echo "== Creating $CONTAINER (model weights kept in volume $VOLUME) =="
|
|
docker run -d \
|
|
--name "$CONTAINER" \
|
|
-p "127.0.0.1:$PORT:11434" \
|
|
-v "$VOLUME:/root/.ollama" \
|
|
--restart unless-stopped \
|
|
ollama/ollama >/dev/null
|
|
fi
|
|
|
|
echo "== Waiting for Ollama to become ready =="
|
|
ready=0
|
|
for _ in $(seq 1 30); do
|
|
if curl -s --max-time 2 "http://127.0.0.1:$PORT/api/tags" >/dev/null 2>&1; then
|
|
ready=1
|
|
break
|
|
fi
|
|
sleep 1
|
|
done
|
|
[ "$ready" = "1" ] || fail "Ollama did not become ready on port $PORT"
|
|
|
|
if ! docker exec "$CONTAINER" ollama list | awk 'NR>1{print $1}' | grep -qx "$MODEL"; then
|
|
echo "== Pulling model $MODEL =="
|
|
docker exec "$CONTAINER" ollama pull "$MODEL"
|
|
fi
|
|
|
|
echo "== Done =="
|
|
echo "Ollama running at http://127.0.0.1:$PORT (model: $MODEL)"
|
|
echo "Next: ./1_preprocess_image.sh -in <photo> -out <scratch-dir>"
|