remove build part of the code and minor refactor

Dockerfile

@@ -3,13 +3,10 @@ FROM python:3.12-slim
 
 # Install dependencies and Poetry
 RUN apt-get update &&  \
-    apt-get install -y --fix-missing build-essential docker.io && \
+    apt-get install -y --fix-missing build-essential && \
     pip install --no-cache-dir poetry && \
     apt-get clean && rm -rf /var/lib/apt/lists/*
 
-# Upgrade pip to the latest version
-RUN pip install --upgrade pip
-
 # Set the working directory in the container
 WORKDIR /app
 
@@ -24,13 +21,13 @@ ENV POETRY_VIRTUALENVS_CREATE=false
 COPY pyproject.toml poetry.lock ./
 
 # Install only non-development dependencies
-RUN poetry install --no-dev --no-root
+RUN poetry install --only main --no-root
 
 # Copy the rest of the application code into the container
 COPY src ./src
 
 # Add source directory to python path
 ENV PYTHONPATH="${PYTHONPATH}:/app/src"
 
-# Run the application
-CMD ["poetry", "run", "python", "src/main.py"]
+# Set default command
+CMD ["bash"]

pyproject.toml

@@ -9,7 +9,6 @@ package-mode = false
 [tool.poetry.dependencies]
 python = "^3.12"
 mlflow = "^2.16.2"
-docker = "^7.1.0"
 pydantic-settings = "^2.5.2"
 
 

src/generate_mlflow_docker_image.py

@@ -0,0 +1,71 @@
+"""Generate Dockerfile to create deployable mlflow model base image."""
+
+import argparse
+import os
+
+from mlflow.pyfunc.backend import PyFuncBackend
+
+from src.utils import envs, set_mlflow_tracking_uri
+
+
+def generate_docker_file(model_uri: str, out_dir: str = "./mlflow-dockerfile"):
+    """Generate mlflow model Dockerfile for deployment."""
+    print("Generating Dockerfile using python api...")
+    # Create an instance of the PyFuncBackend class
+    backend = PyFuncBackend(config={}, env_manager="conda")
+    backend.generate_dockerfile(
+        model_uri=model_uri, output_dir=out_dir, enable_mlserver=True
+    )
+
+    print(f"MLFlow model Dockerfile generated in `./{out_dir}/`")
+
+
+def update_dockerfile(dockerfile_dir: str = "./mlflow-dockerfile/"):
+    """Add dependency installation instructions to the dockerfile."""
+    # Command to install dependencies
+    command_to_install_deps = (
+        "RUN apt-get -y update && apt-get install "
+        "-y --no-install-recommends gcc libc-dev\n"
+    )
+
+    # Insert the dependency installation line after the FROM line
+    dockerfile_path = os.path.join(dockerfile_dir, "Dockerfile")
+    with open(dockerfile_path, "r") as file:
+        lines = file.readlines()
+    for index, line in enumerate(lines):
+        if line.startswith("FROM"):
+            lines.insert(index + 1, command_to_install_deps)
+            break
+
+    # Update Dockerfile
+    with open(dockerfile_path, "w") as file:
+        file.writelines(lines)
+
+    print(f"Updated {dockerfile_path} with necessary dependencies.")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_uri",
+        type=str,
+        required=True,
+        help="MLFlow model uri",
+    )
+
+    parser.add_argument(
+        "--out_dir", type=str, required=False, default="./mlflow-dockerfile"
+    )
+
+    args = parser.parse_args()
+
+    set_mlflow_tracking_uri(envs.mlflow_tracking_uri)
+
+    model_uri = args.model_uri
+
+    # Generate a docker file with artefacts and dependencies gathered
+    # from the mlflow remote registry
+    generate_docker_file(model_uri, out_dir=args.out_dir)
+
+    # Add missing dependencies to the generated dockerfile
+    update_dockerfile(dockerfile_dir=args.out_dir)

src/main.py

@@ -1,16 +1,14 @@
 """Main entry point."""
 
-from src.build_mlflow_docker_image import (build_from_dockerfile,
-                                           generate_docker_file,
-                                           modify_dockerfile)
+from src.generate_mlflow_docker_image import (generate_docker_file,
+                                              update_dockerfile)
 from src.get_mlflow_model_details import get_model_run_uri
-from src.push_image_to_cr import push_image_to_docker_registry
 from src.utils import envs, set_mlflow_tracking_uri
 
 if __name__ == "__main__":
 
     # Set the output directory for docker files and artefacts
-    out_dir = "./mlflow-dockerfile"
+    out_dir = envs.mlflow_docker_out_dir
 
     # Set the mlflow tracking uri before getting the model details
     set_mlflow_tracking_uri(envs.mlflow_tracking_uri)
@@ -26,14 +24,4 @@
     generate_docker_file(model_uri, out_dir=out_dir)
 
     # Add missing dependencies to the generated dockerfile
-    modify_dockerfile(dockerfile_dir=out_dir)
-
-    # Build docker image to be used as the base image for deployment
-    docker_image = build_from_dockerfile(
-        image_name=envs.mlflow_built_image_name,
-        docker_registry=envs.docker_registry,
-        image_tag=envs.mlflow_built_image_tag,
-    )
-
-    # Push the built image to local container registry
-    push_image_to_docker_registry(docker_image)
+    update_dockerfile(dockerfile_dir=out_dir)

src/utils.py

@@ -20,6 +20,7 @@ class Envs(BaseSettings):
     docker_registry: str = "localhost:5000"
     mlflow_built_image_name: str = "mlflow_model"
     mlflow_built_image_tag: str = "latest"
+    mlflow_docker_out_dir: str = "./mlflow-dockerfile"
 
     class Config:
         env_prefix = ""