add img build

.github/workflows/build-ollama-serve.yml

@@ -0,0 +1,96 @@
+name: Build and deploy ollama server
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - ".github/workflows/build-ollama-serve.yml"
+      - "ollama-serve/**"
+
+  pull_request:
+    branches:
+      - main
+    paths:
+      - ".github/workflows/build-ollama-serve.yml"
+      - "ollama-serve/**"
+
+permissions:
+  id-token: write
+  contents: read
+
+defaults:
+  run:
+    shell: bash
+    working-directory: ./ollama-serve/
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.11.1
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.11.1
+    - name: Setup
+      run: make setup
+    - name: Init Model Cache
+      run: make download.models
+    - name: Lints
+      run: make check
+    - name: Tests
+      run: make test
+  build_and_push:
+    name: Build and push images
+    needs: tests
+    runs-on:
+      - self-hosted
+      - dind
+      - large-8x8
+    outputs:
+      short_sha: ${{ steps.versions.outputs.SHORT_SHA }}
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v3
+      - name: Set version strings
+        id: versions
+        run: |
+          echo "SHORT_SHA=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Quay
+        uses: docker/login-action@v2
+        with:
+          registry: quay.io/tembo
+          username: ${{ secrets.QUAY_USER_TEMBO }}
+          password: ${{ secrets.QUAY_PASSWORD_TEMBO }}
+
+      - name: Build and push -- Commit
+        # push a build for every commit
+        uses: docker/build-push-action@v5
+        with:
+          file: ./ollama-serve/Dockerfile
+          context: .
+          platforms: linux/amd64, linux/arm64
+          push: true
+          tags: |
+            quay.io/tembo/ollama-serve:${{ steps.versions.outputs.SHORT_SHA }}
+
+      - name: Build and push -- Latest
+        # only push latest off main
+        if: github.ref == 'refs/heads/main'
+        uses: docker/build-push-action@v5
+        with:
+          file: ./ollama-serve/Dockerfile
+          context: .
+          platforms: linux/amd64, linux/arm64
+          push: true
+          tags: |
+            quay.io/tembo/ollama-serve:latest

.github/workflows/build-vector-serve.yml

@@ -1,4 +1,4 @@
-name: Build and deploy server
+name: Build and deploy embedding server
 
 on:
   push:

docker-compose.yml

@@ -15,7 +15,7 @@ services:
       - 3000:3000
   ollama-serve:
     build:
-      context: ./ollama-serve
+      context: .
       dockerfile: Dockerfile
     ports:
       - 3001:3001

ollama-serve/Dockerfile

@@ -1,7 +1,7 @@
 FROM ollama/ollama:0.1.32
 
 ARG MODEL=wizardlm2:7b
-COPY pull-model.sh .
+COPY ./ollama-serve/pull-model.sh .
 RUN chmod +x ./pull-model.sh
 RUN echo cat
 RUN ./pull-model.sh ${MODEL}