Environment & Config Refactor

.dockerignore

@@ -0,0 +1,9 @@
+.git
+.env
+.idea
+.DS_Store
+.pytest_cache
+.venv
+__pycache__
+*.egg-info
+dist

.env.example

@@ -0,0 +1,70 @@
+# Copy or rename this file to ".env" to use it for environment variable configurations.
+#
+# ATTENTION: The only required environment variables are ORION_STORAGE and ORION_GRAPHS. The rest are optional and it's
+# usually fine to leave them commented out or delete them, as the ORION config module will assign defaults.
+
+# ---- Storage & Output ----
+
+# Directory for source data downloads and ingest pipeline files
+ORION_STORAGE=~/ORION_storage/
+
+# Directory for final graph releases
+ORION_GRAPHS=~/ORION_graphs/
+
+# Directory for log files (if unset, logs go to stdout only)
+# ORION_LOGS=
+
+# Base URL utilized to generate URI identifiers utilized by metadata.
+# For example, ROBOKOP graphs use https://robokop.renci.org/
+# ORION_OUTPUT_URL=https://localhost
+
+# ---- Graph Spec ----
+
+# Local graph spec filename (set one of ORION_GRAPH_SPEC or ORION_GRAPH_SPEC_URL, not both)
+# ORION_GRAPH_SPEC=example-graph-spec.yaml
+
+# URL pointing to a remote graph spec file
+# ORION_GRAPH_SPEC_URL=
+
+# ---- Mode ----
+
+# Enable test/debug mode (sets log level to DEBUG and runs ingests with a smaller subset of data if possible)
+# ORION_TEST_MODE=false
+
+# ---- Biolink Model ----
+
+# Biolink model version (optional - don't set this and ORION will use the latest)
+# BL_VERSION=v4.3.4
+
+# ---- Normalization URLs ----
+
+# Edge normalization / BioLink Lookup URL
+# EDGE_NORMALIZATION_URL=https://bl-lookup-sri.renci.org
+
+# Node normalization URL
+# NODE_NORMALIZATION_URL=https://nodenormalization-sri.renci.org
+
+# ---- LitCoin / Bagel (may be removed in the future) ----
+
+# Name resolution service URL
+# NAMERES_URL=https://name-resolution-sri.renci.org
+
+# SapBERT service URL
+# SAPBERT_URL=https://babel-sapbert.apps.renci.org
+
+# Shared source data path for LitCoin pipeline
+# SHARED_SOURCE_DATA_PATH=/tmp/shared_data
+
+# LitCoin predicate mapping service URL
+# LITCOIN_PRED_MAPPING_URL=https://pred-mapping.apps.renci.org
+
+# Bagel service URL
+# BAGEL_URL=https://bagel.apps.renci.org
+
+# Bagel service credentials
+# BAGEL_SERVICE_USERNAME=
+# BAGEL_SERVICE_PASSWORD=
+
+# OpenAI credentials for LitCoin GPT features
+# OPENAI_API_KEY=
+# OPENAI_API_ORGANIZATION=

.github/workflows/release.yml

@@ -11,29 +11,28 @@ jobs:
     push_to_registry:
         name: Push Docker image to GitHub Packages tagged with "latest" and version number.
         runs-on: ubuntu-latest
+        permissions:
+            contents: read
+            packages: write
         steps:
             - name: Check out the repo
               uses: actions/checkout@v4
-            - name: Get the version
-              id: get_version
-              run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\//}
             - name: Login to ghcr
-              uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a
+              uses: docker/login-action@v3
               with:
                   registry: ${{ env.REGISTRY }}
                   username: ${{ github.actor }}
                   password: ${{ secrets.GITHUB_TOKEN }}
             - name: Extract metadata (tags, labels) for Docker
               id: meta
-              uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
+              uses: docker/metadata-action@v5
               with:
                 images:
                   ghcr.io/${{ github.repository }}
             - name: Push to GitHub Packages
-              uses: docker/build-push-action@3b5e8027fcad23fda98b2e3ac259d8d67585f671
+              uses: docker/build-push-action@v6
               with:
                   context: .
                   push: true
                   tags: ${{ steps.meta.outputs.tags }}
-                  labels: ${{ steps.meta.outputs.labels }}
-                  build-args: VERSION=${{ steps.get_version.outputs.VERSION }}
+                  labels: ${{ steps.meta.outputs.labels }}

.github/workflows/test.yml

@@ -14,10 +14,8 @@ jobs:
       - name: create env params
         run: |
           echo "ROBOKOP_HOME=$PWD" >> $GITHUB_ENV
-          mkdir -p $PWD/tests/workspace/logs
           mkdir -p $PWD/tests/workspace/storage
           mkdir -p $PWD/tests/workspace/graphs
-          echo "ORION_LOGS=$PWD/tests/workspace/logs" >> $GITHUB_ENV
           echo "ORION_STORAGE=$PWD/tests/workspace/storage" >> $GITHUB_ENV
           echo "ORION_GRAPHS=$PWD/tests/workspace/graphs" >> $GITHUB_ENV
 

README.md

@@ -42,31 +42,34 @@ After installation, the following commands are available (prefix with `uv run` i
 
 ### Configuring ORION
 
-ORION uses three directories for its data, configured via environment variables:
+ORION is configured via environment variables, which can be set directly or through an `.env` file. 
 
-| Variable | Purpose                              |
-|---|--------------------------------------|
-| `ORION_STORAGE` | Data ingest pipeline storage |
-| `ORION_GRAPHS` | Knowledge graph outputs              |
-| `ORION_LOGS` | Log files                            |
-
-You can set these up manually or use the provided script:
+In most cases, you can simply use this provided script to set up a local environment. It will create directories for ORION outputs next to where ORION was installed and set env vars pointing to them.
 
 ```bash
-source ./set_up_test_env.sh
+source ./set_up_dev_env.sh
 ```
 
-#### Graph Spec
+For more customization and settings, use an .env file. Copy or rename the `.env.example` file to `.env`.
 
-A Graph Spec yaml file defines which sources to include in a knowledge graph. Set one of the following environment variables (not both):
+Then uncommment and edit `.env` as desired to set values for your environment.
 
-```bash
-# Option 1: Name of a file in the graph_specs/ directory
-export ORION_GRAPH_SPEC=example-graph-spec.yaml
+| Variable | Purpose                                                    | Default |
+|---|------------------------------------------------------------|---|
+| `ORION_STORAGE` | Path to a directory for data ingest pipeline storage       | (required) |
+| `ORION_GRAPHS` | Path to a directory for Knowledge Graph outputs            | (required) |
+| `ORION_LOGS` | Path to a Log file directory (if unset, logs go to stdout) | `None` |
+| `ORION_GRAPH_SPEC` | Graph Spec filename from `graph_specs/`                    | `example-graph-spec.yaml` |
+| `ORION_GRAPH_SPEC_URL` | URL to a remote Graph Spec file                            | |
 
-# Option 2: URL pointing to a Graph Spec yaml file
-export ORION_GRAPH_SPEC_URL=https://stars.renci.org/var/data_services/graph_specs/default-graph-spec.yaml
-```
+Configuration is managed by [pydantic-settings](https://docs.pydantic.dev/latest/concepts/pydantic_settings/) — environment variables override `.env` file values, and sensible defaults are provided where possible. See `orion/config.py` for the full list of settings.
+
+#### Graph Spec
+
+A Graph Spec yaml file defines which sources to include in a knowledge graph. Set one of the following (not both):
+
+- `ORION_GRAPH_SPEC` - name of a file in the `graph_specs/` directory
+- `ORION_GRAPH_SPEC_URL` - URL pointing to a Graph Spec yaml file
 
 Here is a simple Graph Spec example:
 
@@ -100,6 +103,8 @@ See the `graph_specs/` directory for more examples.
 
 ### Running with Docker
 
+Make sure environment variables are set or an `.env` file is configured with at least `ORION_STORAGE`, and `ORION_GRAPHS` pointing to valid host directories. The compose file reads these env vars and mounts those directories as volumes in the container.
+
 Build the image:
 
 ```bash
@@ -115,19 +120,19 @@ docker compose up
 Build a specific graph:
 
 ```bash
-docker compose run --rm orion orion-build Example_Graph
+docker compose run orion orion-build Example_Graph
 ```
 
 Run the ingest pipeline for a single data source:
 
 ```bash
-docker compose run --rm orion orion-ingest DrugCentral
+docker compose run orion orion-ingest DrugCentral
 ```
 
 See available data sources and options:
 
 ```bash
-docker compose run --rm orion orion-ingest -h
+docker compose run orion orion-ingest -h
 ```
 
 ### Development

docker-compose-worker.yml

@@ -5,40 +5,24 @@ services:
       dockerfile: Dockerfile
     container_name: orion-worker
     command: [celery, "-A", "celery_worker.celery_app", "worker", "--loglevel=info", "-Q", "orion"]
+    env_file:
+      - path: .env
+        required: false
     environment:
-      - CELERY_BROKER_URL=redis://redis:6379/0
-      - CELERY_RESULT_BACKEND=redis://redis:6379/0
-      - SHARED_SOURCE_DATA_PATH=/tmp/shared_data
+      # override paths from env, use paths volumes are mounted to inside the container
       - ORION_STORAGE=/ORION_storage
       - ORION_GRAPHS=/ORION_graphs
       - ORION_LOGS=/ORION_logs
-      - BAGEL_SERVICE_USERNAME=fake-username-do-not-commit-a-real-one!!!
-      - BAGEL_SERVICE_PASSWORD=fake-password-do-not-commit-a-real-one!!!  
-      - ORION_GRAPH_SPEC
-      - ORION_GRAPH_SPEC_URL
-      - ORION_OUTPUT_URL
-      - EDGE_NORMALIZATION_ENDPOINT
-      - NODE_NORMALIZATION_ENDPOINT
-      - NAMERES_URL
-      - SAPBERT_URL
-      - LITCOIN_PRED_MAPPING_URL
-      - BL_VERSION
-      - PHAROS_DB_HOST
-      - PHAROS_DB_USER
-      - PHAROS_DB_PASSWORD
-      - PHAROS_DB_NAME
-      - PHAROS_DB_PORT
-      - DRUGCENTRAL_DB_HOST
-      - DRUGCENTRAL_DB_USER
-      - DRUGCENTRAL_DB_PASSWORD
-      - DRUGCENTRAL_DB_NAME
-      - DRUGCENTRAL_DB_PORT
+      - SHARED_SOURCE_DATA_PATH=/tmp/shared_data
+      # specific to celery
+      - CELERY_BROKER_URL=redis://redis:6379/0
+      - CELERY_RESULT_BACKEND=redis://redis:6379/0
     volumes:
       - .:/ORION
-      - "${SHARED_SOURCE_DATA_PATH}:/tmp/shared_data"
       - "${ORION_STORAGE}:/ORION_storage"
       - "${ORION_GRAPHS}:/ORION_graphs"
       - "${ORION_LOGS}:/ORION_logs"
+      - "${SHARED_SOURCE_DATA_PATH}:/tmp/shared_data"
     user: 1000:7474
     networks:
       - app-network

docker-compose.yml

@@ -3,33 +3,15 @@ services:
     build:
       context: .
     command: [orion-build, all]
+    env_file:
+      - path: .env
+        required: false
     environment:
+      # override paths from env, use paths volumes are mounted to inside the container
       - ORION_STORAGE=/ORION_storage
       - ORION_GRAPHS=/ORION_graphs
-      - ORION_LOGS=/ORION_logs
-      - ORION_GRAPH_SPEC
-      - ORION_GRAPH_SPEC_URL
-      - ORION_OUTPUT_URL
-      - EDGE_NORMALIZATION_ENDPOINT
-      - NODE_NORMALIZATION_ENDPOINT
-      - NAMERES_URL
-      - SAPBERT_URL
-      - BL_VERSION
-      - PHAROS_DB_HOST
-      - PHAROS_DB_USER
-      - PHAROS_DB_PASSWORD
-      - PHAROS_DB_NAME
-      - PHAROS_DB_PORT
-      - DRUGCENTRAL_DB_HOST
-      - DRUGCENTRAL_DB_USER
-      - DRUGCENTRAL_DB_PASSWORD
-      - DRUGCENTRAL_DB_NAME
-      - DRUGCENTRAL_DB_PORT
     volumes:
       - .:/ORION
       - "${ORION_STORAGE}:/ORION_storage"
       - "${ORION_GRAPHS}:/ORION_graphs"
-      - "${ORION_LOGS}:/ORION_logs"
     user: 7474:7474
-
-

docs/ORION.ipynb

@@ -85,7 +85,11 @@
   {
    "cell_type": "code",
    "id": "g6i460bvtda",
-   "source": "%%bash\ncd ~/ORION_root/ORION/\nsource ./set_up_test_env.sh",
+   "source": [
+    "%%bash\n",
+    "cd ~/ORION_root/ORION/\n",
+    "source ./set_up_dev_env.sh"
+   ],
    "metadata": {},
    "execution_count": null,
    "outputs": []
@@ -130,4 +134,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

helm/orion/templates/graph-builder.yaml

@@ -70,15 +70,15 @@ spec:
             - name: BL_VERSION
               value: {{ .Values.orion.normalization.bl_version }}
             {{- if .Values.orion.normalization.nodeNormEndpoint }}
-            - name: NODE_NORMALIZATION_ENDPOINT
+            - name: NODE_NORMALIZATION_URL
               value: {{ .Values.orion.normalization.nodeNormEndpoint }}
             {{- end }}
             {{- if .Values.orion.normalization.edgeNormEndpoint }}
-            - name: EDGE_NORMALIZATION_ENDPOINT
+            - name: EDGE_NORMALIZATION_URL
               value: {{ .Values.orion.normalization.edgeNormEndpoint }}
             {{- end }}
             {{- if .Values.orion.normalization.nameResolverEndpoint }}
-            - name: NAMERES_ENDPOINT
+            - name: NAMERES_URL
               value: {{ .Values.orion.normalization.nameResolverEndpoint }}
             {{- end }}
             {{- if .Values.orion.normalization.sapbertEndpoint }}
@@ -157,15 +157,15 @@ spec:
             - name: BL_VERSION
               value: {{ .Values.orion.normalization.bl_version }}
             {{- if .Values.orion.normalization.nodeNormEndpoint }}
-            - name: NODE_NORMALIZATION_ENDPOINT
+            - name: NODE_NORMALIZATION_URL
               value: {{ .Values.orion.normalization.nodeNormEndpoint }}
             {{- end }}
             {{- if .Values.orion.normalization.edgeNormEndpoint }}
-            - name: EDGE_NORMALIZATION_ENDPOINT
+            - name: EDGE_NORMALIZATION_URL
               value: {{ .Values.orion.normalization.edgeNormEndpoint }}
             {{- end }}
             {{- if .Values.orion.normalization.nameResolverEndpoint }}
-            - name: NAMERES_ENDPOINT
+            - name: NAMERES_URL
               value: {{ .Values.orion.normalization.nameResolverEndpoint }}
             {{- end }}
             {{- if .Values.orion.normalization.sapbertEndpoint }}

orion/biolink_utils.py

@@ -6,7 +6,9 @@
 from requests.adapters import HTTPAdapter, Retry
 from functools import cache
 
-BIOLINK_MODEL_VERSION = os.environ.get("BL_VERSION", "v4.3.4")
+from orion.config import config
+
+BIOLINK_MODEL_VERSION = config.BL_VERSION
 
 def get_biolink_model_toolkit(biolink_version: str = None) -> Toolkit:
     version = biolink_version if biolink_version else BIOLINK_MODEL_VERSION