Merge pull request #13 from AET-DevOps25/1-setup-rag-repo

Setup genai project structe alogn with github actions and docker file / docker compose

Author: xhulia028

.github/workflows/genai-linters.yml

@@ -0,0 +1,32 @@
+name: GenAI linters
+
+on: ["pull_request", "workflow_dispatch"]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout sources
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: "./genai/.python-version"
+
+      - name: Install dependencies
+        run: |
+          uv pip install -r ./genai/requirements.txt --system
+
+      - name: GenAI lint
+        run: |
+          cd genai
+          ruff check .
+
+      - name: GenAI formatting
+        run: |
+          cd genai
+          ruff format --check .

.github/workflows/genai-tests.yml

@@ -0,0 +1,27 @@
+name: GenAI tests
+
+on: ["pull_request", "workflow_dispatch"]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout sources
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: "./genai/.python-version"
+
+      - name: Install dependencies
+        run: |
+          uv pip install -r ./genai/requirements.txt --system
+
+      - name: GenAI tests
+        run: |
+          cd genai
+          pytest

docker-compose.yml

@@ -59,7 +59,7 @@ services:
       test: "curl -f http://localhost:3000 || exit 1"
       interval: 5s
     ports:
-      - "3000:3000"       
+      - "3000:3000"
     networks:
       - server
 
@@ -83,9 +83,71 @@ services:
     networks:
       - server
 
+  genai:
+    restart: always
+    build:
+      context: ./genai
+      dockerfile: Dockerfile
+    ports:
+      - "8000:8000"
+    environment:
+      DB_HOST: ${DB_HOST:-weaviate}
+      DB_PORT: ${DB_PORT:-9090}
+      DB_GRPC_PORT: ${DB_GRPC_PORT:-50051}
+    depends_on:
+      - weaviate
+    volumes:
+      - ./genai:/app
+    networks:
+      - server
+      - rag
+
+  weaviate:
+    command: [ "--host", "0.0.0.0", "--port", "9090", "--scheme", "http"]
+    image: cr.weaviate.io/semitechnologies/weaviate:1.30.0
+    ports:
+      - "9090:9090"
+      - "50051:50051"
+    volumes:
+      - weaviate-data:/var/lib/weaviate
+    restart: on-failure:0
+    environment:
+      TRANSFORMERS_INFERENCE_API: 'http://t2v-transformers:8080'
+      IMAGE_INFERENCE_API: 'http://i2v-neural:8080'
+      SPELLCHECK_INFERENCE_API: 'http://text-spellcheck:8080'
+      QUERY_DEFAULTS_LIMIT: 25
+      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true'
+      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
+      DEFAULT_VECTORIZER_MODULE: 'text2vec-transformers'
+      ENABLE_MODULES: 'text2vec-transformers,text-spellcheck,img2vec-neural'
+      CLUSTER_HOSTNAME: 'node1'
+    networks:
+      - rag
+
+  t2v-transformers:
+    image: cr.weaviate.io/semitechnologies/transformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1
+    environment:
+      ENABLE_CUDA: '0'
+    networks:
+      - rag
+
+  text-spellcheck:
+    image: cr.weaviate.io/semitechnologies/text-spellcheck-model:pyspellchecker-en
+    networks:
+      - rag
+
+  i2v-neural:
+    image: cr.weaviate.io/semitechnologies/img2vec-pytorch:resnet50
+    environment:
+      ENABLE_CUDA: '0'
+    networks:
+      - rag
+
 networks:
   server:
+  rag:
 
 volumes:
   db-data:
   node-modules-client:
+  weaviate-data:

genai/.gitignore

@@ -0,0 +1 @@
+.venv

genai/.python-version

@@ -0,0 +1 @@
+3.12

genai/Dockerfile

@@ -0,0 +1,13 @@
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
+
+WORKDIR /app
+
+COPY requirements.txt requirements.txt
+
+RUN uv pip install --no-cache-dir -r requirements.txt --system
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]

genai/.gitkeep genai/README.mdgenai/.gitkeep renamed to genai/README.md

@@ -0,0 +1,14 @@
+import os
+from pydantic_settings import BaseSettings
+from dotenv import load_dotenv
+
+
+class Settings(BaseSettings):
+    load_dotenv()
+
+    db_host: str = os.getenv("DB_HOST") or ""
+    db_port: int = int(os.getenv("DB_PORT") or 0)
+    db_grpc_port: int = int(os.getenv("DB_GRPC_PORT") or 0)
+
+
+settings = Settings()