Staging: update config files and add github action workflow for docker

.env.example

@@ -1,11 +1,13 @@
 OPENAI_MODEL_ID=gpt-4.1-nano
 OPENAI_API_KEY=<str>
-OLLAMA_MODEL_ID=llama3.2:3b#replace with your model
+# replace with your model
+OLLAMA_MODEL_ID=llama3.2:3b
 # OLLAMA_API_URL=http://localhost:11434
 
 # Huggingface API Config
 HUGGINGFACE_ACCESS_TOKEN=<str>
-HUGGINGFACE_INFERENCE_MODEL_ID=ahmedshahriar/GhostWriterLlama-3.2-1B-DPO#replace with your model
+# replace with your model
+HUGGINGFACE_INFERENCE_MODEL_ID=ahmedshahriar/GhostWriterLlama-3.2-1B-DPO
 
 # Comet ML (during training)
 COMET_API_KEY=<str>

.github/workflows/cd.yml

@@ -0,0 +1,50 @@
+name: Publish Docker image to GHCR
+
+on:
+  push:
+    # Uncomment to restrict to main branch only
+#    branches: ["main"]
+    tags: ["v*"]          # e.g. v1.2.3 --->  release builds
+  workflow_dispatch: {}   # manual trigger if needed
+
+permissions:
+  contents: read
+  packages: write
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }} # -> ghcr.io/<owner>/<repo>
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha
+
+      - name: Build and push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

configs/digital_data_etl_author_name.yaml.example

@@ -1,10 +1,10 @@
 parameters:
   user_full_name: John Doe # [First Name(s)] [Last Name]
   links:
-    # blog Posts
+    # Blog Posts
     - https://johndoe.blog/post1
     - https://johndoe.blog/post2
-    # github Repositories
+    # GitHub Repositories
     - https://github.com/johndoe/repo1
     - https://github.com/johndoe/repo2
     - https://github.com/johndoe/awesome-project

core/settings.py

@@ -46,7 +46,7 @@ class Settings(BaseSettings):
 
     # RAG
     TEXT_EMBEDDING_MODEL_ID: str = "sentence-transformers/all-MiniLM-L6-v2"
-    RERANKING_CROSS_ENCODER_MODEL_ID: str = "cross-encoder/ms-marco-MiniLM-L-4-v2"
+    RERANKING_CROSS_ENCODER_MODEL_ID: str = "cross-encoder/ms-marco-MiniLM-L4-v2"
     RAG_MODEL_DEVICE: str = (
         "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
     )