From 31ba51626f066a2eec884eb18e985dc74d3e7f52 Mon Sep 17 00:00:00 2001
From: mohiit1502 <mohiit1502@gmail.com>
Date: Sat, 3 Jan 2026 14:37:34 +0530
Subject: [PATCH] feat: Base image strategy to avoid 489MB downloads on every
 build

- Dockerfile.base: contains TensorFlow, FAISS (build once, ~7min)
- Dockerfile: uses base from Harbor (build fast, ~30s)
- Jenkinsfile: BUILD_BASE=true parameter to rebuild base when needed

First run: trigger with BUILD_BASE=true to create base image
Subsequent runs: automatic, only copies app code
---
 Dockerfile      | 30 ++----------------------------
 Dockerfile.base | 26 ++++++++++++++++++++++++++
 Jenkinsfile     | 17 +++++++++++++----
 3 files changed, 41 insertions(+), 32 deletions(-)
 create mode 100644 Dockerfile.base

diff --git a/Dockerfile b/Dockerfile
index 1f2edb1..6ed53fc 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,36 +1,10 @@
 # Visual Search Engine - API (8081) + Streamlit UI (3000)
-# Single image serving both endpoints
+# Uses pre-built base image from Harbor (has TensorFlow, FAISS, etc.)
 
-FROM python:3.11-slim as builder
+FROM harbor.armco.dev/library/visualsearch-base:latest
 
 WORKDIR /app
 
-# Install build dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential \
-    && rm -rf /var/lib/apt/lists/*
-
-# Copy requirements and install dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir --user -r requirements.txt
-
-# Production stage
-FROM python:3.11-slim
-
-WORKDIR /app
-
-# Install runtime dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    libgomp1 \
-    && rm -rf /var/lib/apt/lists/*
-
-# FAISS OpenMP threads
-ENV OMP_NUM_THREADS=8
-
-# Copy installed packages from builder
-COPY --from=builder /root/.local /root/.local
-ENV PATH=/root/.local/bin:$PATH
-
 # Copy application code
 COPY api/ ./api/
 COPY config.py .
diff --git a/Dockerfile.base b/Dockerfile.base
new file mode 100644
index 0000000..62a09a6
--- /dev/null
+++ b/Dockerfile.base
@@ -0,0 +1,26 @@
+# Base image with TensorFlow and heavy dependencies
+# Build this ONCE and push to Harbor, then app builds use it
+# Trigger rebuild only when requirements.txt changes
+
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install build + runtime dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    libgomp1 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies (the heavy 489MB download)
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Clean up build dependencies
+RUN apt-get purge -y build-essential && apt-get autoremove -y && apt-get clean
+
+# Environment
+ENV OMP_NUM_THREADS=8
+ENV PATH=/root/.local/bin:$PATH
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
diff --git a/Jenkinsfile b/Jenkinsfile
index 3ef1410..6fea360 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -1,11 +1,20 @@
 @Library('jenkins-shared@main') _
 
-// Single image serves both API (8081) and Streamlit UI (3000)
+// Build base image (with TensorFlow) only when requirements.txt changes
+// Then app builds are fast (~30s) using the cached base image
+
+def buildBase = params.BUILD_BASE ?: false
+
+def builds = []
+if (buildBase) {
+  // Build base image first - contains all heavy dependencies
+  builds.add([imageName: 'visualsearch-base', dockerfile: 'Dockerfile.base'])
+}
+// Always build app image - uses base from Harbor
+builds.add([imageName: 'visualsearch', dockerfile: 'Dockerfile'])
 
 kanikoPipeline(
   repoName: 'visual-search-engine',
   branch: env.BRANCH_NAME ?: 'main',
-  builds: [
-    [imageName: 'visualsearch', dockerfile: 'Dockerfile']
-  ]
+  builds: builds
 )