commiting once agin

Dockerfile

@@ -27,10 +27,10 @@ RUN mkdir -p /app/models && chmod 777 /app/models
 COPY requirements.txt .
 
 # Install dependencies
-# We use a PRE-BUILT wheel for llama-cpp-python to avoid compiling from source (Saves ~10 minutes)
+# We forcefully install the specific Linux wheel for Python 3.11 to prevent compilation
 RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir -r requirements.txt && \
-    pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+    pip install https://github.com/abetlen/llama-cpp-python/releases/download/v0.3.2/llama_cpp_python-0.3.2-cp311-cp311-linux_x86_64.whl
 
 # Copy the rest of the application
 COPY . .