From 764613bd86f54d64a70532ce68dd57707cce7c97 Mon Sep 17 00:00:00 2001
From: hailin <hailin.zhao@gdzx.xyz>
Date: Sat, 7 Feb 2026 07:16:20 -0800
Subject: [PATCH] fix(docling): use standalone script for model pre-download

Inline Python one-liner had syntax errors (try/except/finally can't be
single-line). Move to scripts/preload_models.py for reliable execution.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 packages/services/docling-service/Dockerfile  | 14 ++-----
 .../docling-service/scripts/preload_models.py | 41 +++++++++++++++++++
 2 files changed, 44 insertions(+), 11 deletions(-)
 create mode 100644 packages/services/docling-service/scripts/preload_models.py

diff --git a/packages/services/docling-service/Dockerfile b/packages/services/docling-service/Dockerfile
index 70d4e9d..f556e69 100644
--- a/packages/services/docling-service/Dockerfile
+++ b/packages/services/docling-service/Dockerfile
@@ -11,18 +11,10 @@ COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
 COPY app/ ./app/
+COPY scripts/ ./scripts/
 
-# 构建时预下载模型（需要实际转换才会触发 HuggingFace 模型下载）
-RUN python -c "\
-import tempfile, os; \
-pdf = b'%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj\n2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj\n3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Parent 2 0 R/Contents 4 0 R/Resources<</Font<</F1 5 0 R>>>>>>endobj\n4 0 obj<</Length 44>>stream\nBT /F1 12 Tf 100 700 Td (hello) Tj ET\nendstream\nendobj\n5 0 obj<</Type/Font/Subtype/Type1/BaseFont/Helvetica>>endobj\nxref\n0 6\n0000000000 65535 f \n0000000009 00000 n \n0000000058 00000 n \n0000000115 00000 n \n0000000266 00000 n \n0000000360 00000 n \ntrailer<</Size 6/Root 1 0 R>>\nstartxref\n454\n%%EOF'; \
-f = tempfile.NamedTemporaryFile(suffix='.pdf', delete=False); f.write(pdf); f.close(); \
-from docling.document_converter import DocumentConverter; \
-conv = DocumentConverter(); \
-try: conv.convert(f.name) \
-except: pass \
-finally: os.unlink(f.name); \
-print('Models pre-downloaded successfully')"
+# 构建时预下载模型（实际执行一次 PDF 转换触发 HuggingFace 模型下载）
+RUN python scripts/preload_models.py
 
 EXPOSE 3007
 
diff --git a/packages/services/docling-service/scripts/preload_models.py b/packages/services/docling-service/scripts/preload_models.py
new file mode 100644
index 0000000..c33e9ed
--- /dev/null
+++ b/packages/services/docling-service/scripts/preload_models.py
@@ -0,0 +1,41 @@
+"""构建时预下载 Docling 模型到镜像缓存"""
+import tempfile
+import os
+
+# 创建最小 PDF 文件
+pdf = (
+    b"%PDF-1.4\n"
+    b"1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj\n"
+    b"2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj\n"
+    b"3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Parent 2 0 R/Contents 4 0 R"
+    b"/Resources<</Font<</F1 5 0 R>>>>>>endobj\n"
+    b"4 0 obj<</Length 44>>stream\n"
+    b"BT /F1 12 Tf 100 700 Td (hello) Tj ET\n"
+    b"endstream\nendobj\n"
+    b"5 0 obj<</Type/Font/Subtype/Type1/BaseFont/Helvetica>>endobj\n"
+    b"xref\n0 6\n"
+    b"0000000000 65535 f \n"
+    b"0000000009 00000 n \n"
+    b"0000000058 00000 n \n"
+    b"0000000115 00000 n \n"
+    b"0000000266 00000 n \n"
+    b"0000000360 00000 n \n"
+    b"trailer<</Size 6/Root 1 0 R>>\n"
+    b"startxref\n454\n%%EOF"
+)
+
+tmp = tempfile.NamedTemporaryFile(suffix=".pdf", delete=False)
+tmp.write(pdf)
+tmp.close()
+
+try:
+    from docling.document_converter import DocumentConverter
+
+    conv = DocumentConverter()
+    conv.convert(tmp.name)
+    print("Models pre-downloaded successfully")
+except Exception as e:
+    print(f"Conversion failed (expected for minimal PDF): {e}")
+    print("Models should still be cached")
+finally:
+    os.unlink(tmp.name)