File size: 1,762 Bytes
815b4f4
 
377328d
 
 
 
 
 
 
 
 
815b4f4
377328d
815b4f4
377328d
 
 
815b4f4
 
 
 
 
 
377328d
 
 
 
 
 
 
 
815b4f4
377328d
 
ea5fa96
377328d
 
 
 
815b4f4
377328d
 
 
 
815b4f4
377328d
ea5fa96
 
377328d
815b4f4
 
377328d
 
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
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
FROM python:3.10-slim


ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1


WORKDIR /code

# System Dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    git \
    curl \
    libopenblas-dev \
    libomp-dev \
    && rm -rf /var/lib/apt/lists/*


COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Hugging Face + model tools
RUN pip install --no-cache-dir huggingface-hub sentencepiece accelerate fasttext

# Hugging Face cache environment
ENV HF_HOME=/models/huggingface \
    TRANSFORMERS_CACHE=/models/huggingface \
    HUGGINGFACE_HUB_CACHE=/models/huggingface \
    HF_HUB_CACHE=/models/huggingface

# Created cache dir and set permissions
RUN mkdir -p /models/huggingface && chmod -R 777 /models/huggingface

# Pre-download models at build time
RUN python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='Remostart/Plutus_Tutor_model')" \
 && python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')" \
 && find /models/huggingface -name '*.lock' -delete

# Preload tokenizers (avoid runtime delays)
RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('Remostart/Plutus_Tutor_model', use_fast=True)" \
 && python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2', use_fast=True)" 
 

# Copy project files
COPY . .

# Expose FastAPI port
EXPOSE 7860

# Run FastAPI app with uvicorn (1 workers for concurrency)
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]