hoangthiencm commited on
Commit
0a4a0fa
·
verified ·
1 Parent(s): 0b6acc2

Update Dockerfile

Browse files
Files changed (1) hide show
  1. Dockerfile +7 -3
Dockerfile CHANGED
@@ -3,9 +3,10 @@ FROM python:3.10-slim
3
  WORKDIR /app
4
 
5
  # --- Cài đặt system dependencies ---
6
- # Pandoc: cần thiết cho pypandoc (Markdown -> Docx)
7
- # Build tools: cần cho một số Python packages
8
- # Image libraries: cần cho Pillow
 
9
  RUN apt-get update && \
10
  apt-get install -y \
11
  pandoc \
@@ -13,6 +14,9 @@ RUN apt-get update && \
13
  libfreetype6-dev \
14
  libjpeg-dev \
15
  zlib1g-dev \
 
 
 
16
  && rm -rf /var/lib/apt/lists/*
17
 
18
  # Upgrade pip first
 
3
  WORKDIR /app
4
 
5
  # --- Cài đặt system dependencies ---
6
+ # Pandoc: cho export Word
7
+ # Build tools: cho Python packages
8
+ # Image libraries: cho Pillow
9
+ # Tesseract OCR: Cho fallback khi Gemini chặn bản quyền
10
  RUN apt-get update && \
11
  apt-get install -y \
12
  pandoc \
 
14
  libfreetype6-dev \
15
  libjpeg-dev \
16
  zlib1g-dev \
17
+ tesseract-ocr \
18
+ tesseract-ocr-vie \
19
+ tesseract-ocr-eng \
20
  && rm -rf /var/lib/apt/lists/*
21
 
22
  # Upgrade pip first