fix(setup,docs): rebuild locally built images, name OCR_DEEPSEEK_URL

Both setup scripts start with `compose pull && compose up -d`. In the local
compose file backend and worker are build-only services, so `up -d` builds
only when no image exists yet: a rerun that switches OCR on wrote
INSTALL_TESSERACT=true to .env and then reused the image built without it,
leaving OCR_ENABLED=true with no engine. Build explicitly on the local
compose path; the hub path stays pull-only, its services have no build stage.

The OCR message named OCR_ENGINE=deepseek but not OCR_DEEPSEEK_URL, whose
default (localhost:11434) resolves to the container, not the host.

deployment/sandbox/README.md still described Docling as already present in
application/requirements.txt.
This commit is contained in:
Alex committed 2026-09-04 15:28:29 +01:00
1 parent 2a9a02427f
commit b473498baf
3 files changed
+22 -6

No files matched your search

+9 -2
View File
@@ -523,7 +523,7 @@ function Configure-DocProcessing {
# Bakes tesseract into the locally built images (docker compose
# --env-file .env build).
"INSTALL_TESSERACT=true" | Add-Content -Path $ENV_FILE -Encoding utf8
Write-ColorText "OCR enabled. tesseract will be built into the images (INSTALL_TESSERACT=true); set OCR_ENGINE=deepseek in .env for a DeepSeek-OCR endpoint instead." -ForegroundColor "Green"
Write-ColorText "OCR enabled. tesseract will be built into the images (INSTALL_TESSERACT=true); for a DeepSeek-OCR endpoint instead, set OCR_ENGINE=deepseek and OCR_DEEPSEEK_URL=<endpoint> in .env." -ForegroundColor "Green"
$docling_ocr = Read-Host "Also install the Docling layout engine for OCR (better tables/reading order, several GB heavier)? (y/N)"
if ($docling_ocr -eq "y" -or $docling_ocr -eq "Y") {
# Locally built images include docling via this build arg; it becomes
@@ -647,7 +647,14 @@ function Use-DocsPublicAPIEndpoint {
throw "Docker compose pull failed with exit code $LASTEXITCODE"
}
& docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" up -d
# Locally built images must be rebuilt rather than reused:
# INSTALL_TESSERACT and INSTALL_DOCLING are build args, so a rerun that
# switches OCR on would otherwise keep the image built without them.
$up_args = @("up", "-d")
if ($COMPOSE_FILE -eq $COMPOSE_FILE_LOCAL) {
$up_args = @("up", "--build", "-d")
}
& docker compose --env-file "$ENV_FILE" -f "$COMPOSE_FILE" @up_args
if ($LASTEXITCODE -ne 0) {
throw "Docker compose up failed with exit code $LASTEXITCODE"
}