File size: 1,002 Bytes
3e2ca02
d2020f6
0914e96
3e2ca02
28f6f67
0914e96
3e2ca02
d2020f6
 
 
b901ed7
d2020f6
 
3e2ca02
 
 
 
b88fafc
 
3e2ca02
b88fafc
 
129a64e
3e2ca02
b901ed7
b88fafc
d2020f6
3e2ca02
0914e96
 
3e2ca02
b901ed7
 
3e2ca02
bc8cf7e
b88fafc
3e2ca02
b901ed7
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
# Start with Python 3.11
FROM python:3.11

# Working Directory Setup
WORKDIR /app

# Install basic tools (Quick step)
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    cmake \
    libgl1 \
    && rm -rf /var/lib/apt/lists/*

# === 🛡️ THE FINAL FIX: CORRECT WHEEL INSTALL ===
# Ye link (jllllll/AVX2/cpu) specially HF jaise servers ke liye hai.
# 1. Compile nahi karega (Fast install).
# 2. 'manylinux' wheel uthayega (No 'musl' error crash).
RUN pip install --upgrade pip && \
    pip install llama-cpp-python==0.2.90 \
    --extra-index-url https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/AVX2/cpu \
    --prefer-binary \
    --no-cache-dir

# Install remaining dependencies from requirements.txt
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy App Code
COPY . .

# Set Permissions
RUN chmod -R 777 /app

# Open Port
EXPOSE 7860

# Launch
CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "7860"]