add: Dockerfiles

.github/workflows/docker-package.yml

@@ -1,4 +1,4 @@
-name: Python package
+name: Docker package
 
 on:
   release:
@@ -28,3 +28,4 @@ jobs:
         tags: |
           ghcr.io/scai-bio/index/backend:latest
           ghcr.io/scai-bio/index/backend:${{ steps.version.outputs.VERSION }}
+    - name: Build & push frontend

README.md

@@ -1,68 +1,55 @@
 # INDEX – the Intelligent Data Steward Toolbox
 
-![example workflow](https://github.com/SCAI-BIO/index/actions/workflows/tests.yml/badge.svg) ![GitHub Release](https://img.shields.io/github/v/release/SCAI-BIO/index)
+![example workflow](https://github.com/SCAI-BIO/index/actions/workflows/tests.yml/badge.svg)
+![GitHub Release](https://img.shields.io/github/v/release/SCAI-BIO/index)
 
-INDEX is an intelligent data steward toolbox that leverages Large Language Model embeddings for automated Data-Harmonization. 
+INDEX is an intelligent data steward toolbox that leverages Large Language Model embeddings for automated Data-Harmonization.
 
 ## Table of Contents
 - [Introduction](#introduction)
 - [Installation](#installation)
-- [Usage](#usage)
+  - [Local Development Server](#local-development-server)
+    - [Starting the backend](#starting-the-backend)
+    - [Starting the frontend](#starting-the-frontend)
+  - [Docker](#docker)
 - [Configuration](#configuration)
 
 ## Introduction
 
-INDEX uses vector embeddings from variable descriptions to suggest mappings for datasets based on their semantic 
-similarity. Mappings are stored with their vector representations in a knowledge base, where they can be used for 
-subsequent harmonisation tasks, potentially improving the following suggestions with each iteration. Models for 
-the computation as well as databases for storage are meant to be configurable and extendable to adapt the tool for
-specific use-cases.
+INDEX uses vector embeddings from variable descriptions to suggest mappings for datasets based on their semantic similarity. Mappings are stored with their vector representations in a knowledge base, where they can be used for subsequent harmonisation tasks, potentially improving suggestions with each iteration. The tool is designed to be configurable and extendable, adapting for specific use-cases through customizable models and databases.
 
 ## Installation
 
-```bash
-uvicorn api.routes:app --reload --port 5000
-```
-
-### Run the Backend via Docker
-
-The API can also be run via docker.
-
-You can either build the docker container locally or download the latest build from the index GitHub package registry. 
+### Local Development Server
 
+#### Starting the backend
 
 ```bash
-docker build . -t ghcr.io/scai-bio/api/backend:latest
+cd api
+pip install -r requirements.txt
+uvicorn routes:app --reload --port 5000
 ```
 
-```bash
-docker pull ghcr.io/scai-bio/api/backend:latest
-```
+Navigate to [localhost:5000](http://localhost:5000) to access the backend.
 
-After build/download you will be able to start the container and access the INDEX API per default on [localhost:5000](http://localhost:8000):
+#### Starting the frontend
 
 ```bash
-docker run  -p 8000:80 ghcr.io/api/scai-bio/backend:latest
+cd client
+pip install -r requirements.txt
+uvicorn routes:app --reload --port 5000
 ```
 
-## Configuration
-
-### Description Embeddings
-
-You can configure INDEX to use either a local language model or call OPenAPIs embedding API. While using the OpenAI API
-is significantly faster, you will need to provide an API key that is linked to your OpenAI account. 
+Navigate to [localhost:4200](http://localhost:4200) to access the frontend.
 
-Currently, the following local models are implemented:
-* [Sentence Transformer (MPNet)](https://huggingface.co/docs/transformers/model_doc/mpnet)
+### Docker
 
-The API will default to use a local embedding model. You can adjust the model loaded on start up in the configurations.
+You can start both frontend and API using docker-compose:
 
-### Database
+```bash
+docker-compose -f docker-compose.local.yaml up
+```
 
-INDEX will by default store mappings in a file based db file in the [index/db](api/db) dir. For testing purposes
-the initial SQLLite file based db contains a few of mappings to concepts in SNOMED CT. All available database adapter 
-implementations can be found in [index/repository](api/repository).
+## Configuration
 
-To exchange the DB implementation, load your custom DB adapter or pre-saved file-based DB file on application startup
-[here](https://github.com/SCAI-BIO/index/blob/923601677fd62d50c3748b7f11666420e82df609/index/api/routes.py#L14). 
-The same can be done for any other embedding model.
+_TODO: Add configuration instructions_

api/routes.py

@@ -1,6 +1,6 @@
 import logging
-import json
 import uvicorn
+
 from fastapi import FastAPI, HTTPException
 from starlette.middleware.cors import CORSMiddleware
 from starlette.responses import RedirectResponse, HTMLResponse
@@ -11,7 +11,7 @@
 from datastew.visualisation import get_html_plot_for_current_database_state
 
 logger = logging.getLogger("uvicorn.info")
-repository = SQLLiteRepository(mode="memory")
+repository = SQLLiteRepository(mode="disk", path="snomed.db")
 embedding_model = MPNetAdapter()
 db_plot_html = None
 
@@ -56,6 +56,7 @@
     allow_headers=["*"],
 )
 
+
 @app.get("/", include_in_schema=False)
 def swagger_redirect():
     return RedirectResponse(url='/docs')

client/Dockerfile.dev

@@ -0,0 +1,32 @@
+# FIRST STAGE: Build the Angular Application
+FROM node:20.12.2 as build
+
+# Set the working directory
+WORKDIR /app
+
+# Copy the current directory contents into the working directory
+COPY . .
+
+# Update lock file
+RUN npm install
+
+# Install dependencies
+RUN npm ci
+
+# Install Angular CLI globally
+RUN npm install -g @angular/cli
+
+# Build the Angular application
+RUN ng build --configuration=development
+
+# SECOND STAGE: Serve the application using Nginx
+FROM docker.io/library/nginx:1.26.0
+
+# Copy the built application from the previous stage
+COPY --from=build /app/dist/client/browser /usr/share/nginx/html
+
+# Expose port 80
+EXPOSE 80
+
+# Start Nginx serve
+CMD ["nginx", "-g", "daemon off;"]

client/Dockerfile.prod

@@ -0,0 +1,32 @@
+# FIRST STAGE: Build the Angular Application
+FROM node:20.12.2 as build
+
+# Set the working directory
+WORKDIR /app
+
+# Copy the current directory contents into the working directory
+COPY . .
+
+# Update lock file
+RUN npm install
+
+# Install dependencies
+RUN npm ci
+
+# Install Angular CLI globally
+RUN npm install -g @angular/cli
+
+# Build the Angular application
+RUN ng build --configuration=production
+
+# SECOND STAGE: Serve the application using Nginx
+FROM docker.io/library/nginx:1.26.0
+
+# Copy the built application from the previous stage
+COPY --from=build /app/dist/client/browser /usr/share/nginx/html
+
+# Expose port 80
+EXPOSE 80
+
+# Start Nginx serve
+CMD ["nginx", "-g", "daemon off;"]

client/angular.json

@@ -93,5 +93,8 @@
         }
       }
     }
+  },
+  "cli": {
+    "analytics": false
   }
 }

client/src/environments/environment.development.ts

@@ -1,3 +1,3 @@
 export const environment: { openApiUrl: string } = {
-  openApiUrl: 'http://193.175.165.153:8000',
+  openApiUrl: 'http://localhost:5000',
 };

client/src/environments/environment.production.ts

@@ -1,3 +1,3 @@
-// export const environment: { openApiUrl: string } = {
-//   openApiUrl: 'https://index.bio.scai.fraunhofer.de',
-// };
+export const environment: { openApiUrl: string } = {
+   openApiUrl: 'https://index.bio.scai.fraunhofer.de',
+ };

client/src/environments/environment.ts

@@ -1,4 +1,3 @@
 export const environment: { openApiUrl: string } = {
-  //openApiUrl: 'https://index.bio.scai.fraunhofer.de',
-  openApiUrl: 'http://193.175.165.153:8000',
+  openApiUrl: 'http://localhost:5000',
 };

docker-compose.local.yaml

@@ -0,0 +1,21 @@
+version: "3.12"
+
+services:
+
+  frontend:
+    image: index-client
+    build:
+      context: ./client
+      dockerfile: Dockerfile.dev
+    ports:
+      - "4200:80"
+    depends_on:
+      - backend
+
+  backend:
+    image: index-api
+    build:
+      context: ./api
+      dockerfile: Dockerfile
+    ports:
+      - "5000:80"