Update Dockerfile

Dockerfile

@@ -1,23 +1,41 @@
 FROM ghcr.io/ggml-org/llama.cpp:server
 
 USER root
-RUN apt-get update && apt-get install -y python3 python3-pip curl && rm -rf /var/lib/apt/lists/*
-RUN pip3 install --no-cache-dir fastapi uvicorn duckduckgo-search requests
+
+# Install Python and core build tools
+RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-pip \
+    python3-venv \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Force install the specific libraries we need to the system python
+RUN pip3 install --no-cache-dir --break-system-packages \
+    fastapi \
+    uvicorn \
+    duckduckgo-search \
+    requests \
+    python-multipart
+
+# Download Gemma-3-4B-it (The high-speed 2026 champ)
 RUN mkdir -p /models && \
     curl -L https://huggingface.co/unsloth/gemma-3-4b-it-GGUF/resolve/main/gemma-3-4b-it-Q4_K_M.gguf -o /models/model.gguf && \
     chown -R 1000:1000 /models
 
+WORKDIR /app
 COPY --chown=1000:1000 . .
 
+# Set Python Path to ensure modules are found
+ENV PYTHONPATH=/usr/local/lib/python3.10/dist-packages:/usr/lib/python3/dist-packages
+
 USER 1000
 
-# High-concurrency settings
+# High-concurrency settings for your 1M user goal
 ENV LLAMA_ARG_MODEL=/models/model.gguf
 ENV LLAMA_ARG_HOST=127.0.0.1
 ENV LLAMA_ARG_PORT=8080
 ENV LLAMA_ARG_THREADS=8
-ENV LLAMA_ARG_CTX_SIZE=2048
-ENV LLAMA_ARG_BATCH_SIZE=512
+ENV LLAMA_ARG_CTX_SIZE=1024
 
-# Run our Python orchestrator
 ENTRYPOINT ["python3", "app.py"]