Update Dockerfile

Dockerfile

@@ -1,31 +1,53 @@
 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 \
-    gcc \
-    g++ \
-    wget \
-    curl \
+    build-essential \
     git \
-    libfaiss-dev \
+    curl \
+    libopenblas-dev \
+    libomp-dev \
     && rm -rf /var/lib/apt/lists/*
 
-WORKDIR /app
 
 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
 
-RUN mkdir -p /app/hf_cache && chmod -R 777 /app/hf_cache
+# Created cache dir and set permissions
+RUN mkdir -p /models/huggingface && chmod -R 777 /models/huggingface
 
-ENV HF_HOME=/app/hf_cache
-ENV TRANSFORMERS_CACHE=/app/hf_cache
-ENV HF_DATASETS_CACHE=/app/hf_cache
-ENV HF_HUB_CACHE=/app/hf_cache
+# 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
 
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "2"]
+# Run FastAPI app with uvicorn (1 workers for concurrency)
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]