Spaces:
Running
Running
Update Dockerfile
Browse files- Dockerfile +21 -17
Dockerfile
CHANGED
@@ -1,34 +1,38 @@
|
|
1 |
-
#
|
2 |
-
# ✅ Dockerfile for SmartManuals-AI
|
3 |
-
# ============================
|
4 |
-
|
5 |
FROM python:3.10-slim
|
6 |
|
7 |
-
#
|
8 |
RUN apt-get update && apt-get install -y \
|
9 |
-
build-essential \
|
10 |
-
poppler-utils \
|
11 |
tesseract-ocr \
|
12 |
libglib2.0-0 \
|
|
|
|
|
|
|
13 |
libsm6 \
|
14 |
libxext6 \
|
15 |
libxrender-dev \
|
16 |
-
|
|
|
|
|
|
|
17 |
|
18 |
-
# Set
|
19 |
-
|
|
|
|
|
20 |
|
21 |
-
#
|
22 |
-
|
23 |
|
24 |
-
#
|
|
|
25 |
RUN pip install --upgrade pip && pip install -r requirements.txt
|
26 |
|
27 |
-
# Copy
|
28 |
COPY . .
|
29 |
|
30 |
-
#
|
31 |
-
|
32 |
|
33 |
-
#
|
34 |
CMD ["python", "app.py"]
|
|
|
1 |
+
# Base image
|
|
|
|
|
|
|
2 |
FROM python:3.10-slim
|
3 |
|
4 |
+
# System dependencies for OCR, PDF, DOCX, fonts, and more
|
5 |
RUN apt-get update && apt-get install -y \
|
|
|
|
|
6 |
tesseract-ocr \
|
7 |
libglib2.0-0 \
|
8 |
+
libgl1 \
|
9 |
+
libpoppler-cpp-dev \
|
10 |
+
poppler-utils \
|
11 |
libsm6 \
|
12 |
libxext6 \
|
13 |
libxrender-dev \
|
14 |
+
ffmpeg \
|
15 |
+
build-essential \
|
16 |
+
git \
|
17 |
+
&& rm -rf /var/lib/apt/lists/*
|
18 |
|
19 |
+
# Set environment variables
|
20 |
+
ENV PIP_NO_CACHE_DIR=1 \
|
21 |
+
PYTHONUNBUFFERED=1 \
|
22 |
+
HF_HUB_DISABLE_SYMLINKS_WARNING=1
|
23 |
|
24 |
+
# Set working directory
|
25 |
+
WORKDIR /home/user/app
|
26 |
|
27 |
+
# Copy requirements and install
|
28 |
+
COPY requirements.txt .
|
29 |
RUN pip install --upgrade pip && pip install -r requirements.txt
|
30 |
|
31 |
+
# Copy app files
|
32 |
COPY . .
|
33 |
|
34 |
+
# Download NLTK data
|
35 |
+
RUN python -m nltk.downloader punkt
|
36 |
|
37 |
+
# Start the app
|
38 |
CMD ["python", "app.py"]
|