issue #51: implement pipeline switching in back end

.devcontainer/devcontainer.json

@@ -5,7 +5,7 @@
 	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
 	"image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
 	"features": {
-		"ghcr.io/devcontainers/features/azure-cli:1": {},
+		"ghcr.io/devcontainers/features/azure-cli:1": {}
 	},
 
 	// Features to add to the dev container. More info: https://containers.dev/features.
@@ -25,6 +25,7 @@
 			"GitHub.vscode-pull-request-github",
 			"ms-python.python",
 			"ms-python.black-formatter",
+			"stkb.rewrap"
 		  ]
 		}
 	  }

.env.template

@@ -1,9 +1,6 @@
 NACHET_AZURE_STORAGE_CONNECTION_STRING=
-NACHET_MODEL_ENDPOINT_REST_URL=
-NACHET_MODEL_ENDPOINT_ACCESS_KEY=
 NACHET_DATA=
-NACHET_SUBSCRIPTION_ID=
-NACHET_RESOURCE_GROUP=
-NACHET_WORKSPACE=
-NACHET_MODEL=
+NACHET_BLOB_PIPELINE_NAME=
+NACHET_BLOB_PIPELINE_VERSION=
+NACHET_BLOB_PIPELINE_DECRYPTION_KEY=
 NACHET_MAX_CONTENT_LENGTH=

.github/workflows/workflows.yml

@@ -0,0 +1,36 @@
+name: Docker build and push to ghcr.io/ai-cfia and lint test
+
+on:
+  pull_request:
+    types:
+      - opened
+      - closed
+      - synchronize
+
+jobs:
+  lint-test:
+    uses:
+      ai-cfia/github-workflows/.github/workflows/workflow-lint-test-python.yml@main
+    secrets: inherit
+
+  deploy:
+    uses:
+      ai-cfia/github-workflows/.github/workflows/workflow-build-push-container-github-registry.yml@main
+    with:
+      container-name: ${{ github.event.repository.name }}
+      tag: ${{ github.sha }}
+      registry: ghcr.io/ai-cfia
+    secrets: inherit
+
+  repo-standard:
+    uses:
+      ai-cfia/github-workflows/.github/workflows/workflow-repo-standards-validation.yml@main
+    secrets: inherit
+
+  markdown-check:
+    uses:
+      ai-cfia/github-workflows/.github/workflows/workflow-markdown-check.yml@main
+
+  yaml-check:
+    uses:
+      ai-cfia/github-workflows/.github/workflows/workflow-yaml-check.yml@main

.gitignore

@@ -3,4 +3,4 @@
 .vscode/settings.json
 *.pyc
 .vscode/settings.json
-output.*
+output.*

README.md

@@ -30,7 +30,7 @@ frontend-->>-Client: display inference res.
 backend->>+AzureStorageAPI: (async) upload_inference_result(json)
 ```
 
-**Details**
+### Details
 
 - The backend was built with the [Quart](http://pgjones.gitlab.io/quart/) framework
 - Quart is an asyncio reimplementation of Flask
@@ -41,35 +41,61 @@ backend->>+AzureStorageAPI: (async) upload_inference_result(json)
 ****
 
 ### RUNNING NACHET-BACKEND FROM DEVCONTAINER
-When you are developping, you can run the program while in the devcontainer by using this command:
-```
+
+When you are developping, you can run the program while in the devcontainer by
+using this command:
+
+```bash
 hypercorn -b :8080 app:app
 ```
 
 ### RUNNING NACHET-BACKEND AS A DOCKER CONTAINER
+
 If you want to run the program as a Docker container (e.g., for production), use:
-```
+
+```bash
 docker build -t nachet-backend .
 docker run -p 8080:8080 -v $(pwd):/app nachet-backend
 ```
 
 ### TESTING NACHET-BACKEND
+
 To test the program, use this command:
-```
+
+```bash
 python -m unittest discover -s tests
 ```
 
 ****
+
 ### ENVIRONMENT VARIABLES
-Start by making a copy of `.env.template` and renaming it `.env`. For the backend to function, you will need to add the missing values:
 
-* **NACHET_AZURE_STORAGE_CONNECTION_STRING**: Connection string to access external storage (Azure Blob Storage).
-* **NACHET_MODEL_ENDPOINT_REST_URL**: Endpoint to communicate with deployed model for inferencing.
-* **NACHET_MODEL_ENDPOINT_ACCESS_KEY**: Key used when consuming online endpoint.
-* **NACHET_DATA**: Url to access nachet-data repository
-* **NACHET_HEALTH_MESSAGE**: Health check message for the server.
-* **NACHET_MAX_CONTENT_LENGTH**: Set the maximum size of the file that can be uploaded to the backend. Needs to be the same size as the `client_max_body_size` [value](https://github.com/ai-cfia/howard/blob/dedee069f051ba743122084fcb5d5c97c2499359/kubernetes/aks/apps/nachet/base/nachet-ingress.yaml#L13) set from the deployment in Howard.
+Start by making a copy of `.env.template` and renaming it `.env`. For the
+backend to function, you will need to add the missing values:
+
+- **NACHET_AZURE_STORAGE_CONNECTION_STRING**: Connection string to access
+  external storage (Azure Blob Storage).
+- **NACHET_MODEL_ENDPOINT_REST_URL**: Endpoint to communicate with deployed
+  model for inferencing.
+- **NACHET_MODEL_ENDPOINT_ACCESS_KEY**: Key used when consuming online endpoint.
+- **NACHET_DATA**: Url to access nachet-data repository
+- **NACHET_HEALTH_MESSAGE**: Health check message for the server.
+- **NACHET_MAX_CONTENT_LENGTH**: Set the maximum size of the file that can be
+  uploaded to the backend. Needs to be the same size as the
+  `client_max_body_size`
+  [value](https://github.com/ai-cfia/howard/blob/dedee069f051ba743122084fcb5d5c97c2499359/kubernetes/aks/apps/nachet/base/nachet-ingress.yaml#L13)
+  set from the deployment in Howard.
+- **NACHET_SUBSCRIPTION_ID**
+- **NACHET_RESOURCE_GROUP**
+- **NACHET_WORKSPACE**
+- **NACHET_MODEL**
+- **NACHET_BLOB_PIPELINE_NAME**
+- **NACHET_BLOB_PIPELINE_VERSION**
+- **NACHET_BLOB_PIPELINE_DECRYPTION_KEY**
 
 ****
+
 ### DEPLOYING NACHET
-If you need help deploying Nachet for your own needs, please contact us at [email protected].
+
+If you need help deploying Nachet for your own needs, please contact us at
+<[email protected]>.

TESTING.md

@@ -0,0 +1,103 @@
+# Testing documentation
+
+To start the automatic test, you can use the following command:
+
+```bash
+python -m unittest discover -s tests
+```
+
+You also have the option to run automatic test in run_test.py or manually test
+the functionality with the frontend. [See frontend testing
+documentation](https://github.com/ai-cfia/nachet-frontend/blob/main/TESTING.md)
+
+To perform the following test, you will need the frontend repository for the
+Nachet Interactive's application. The frontend can be found at: [Nachet Frontend
+GitHub Repository](https://github.com/ai-cfia/nachet-frontend).
+
+You will also need the list of the available pipelines. The list can be found
+[here](https://github.com/ai-cfia/nachet-backend/blob/51-implementing-2-models/docs/nachet-inference-documentation.md#available-version-of-the-json-file).
+
+---
+
+## Test Case: Populate model selection with pipelines information
+
+**Objective**: Verify that the model selection component gets populated with the
+pipeline information.
+
+**Preconditions:**
+
+- [ ] Nachet backend is set up and running. Use the command `hypercorn -b :8080
+  app:app` to start the quartz server.
+- [ ] The environment variables are all set.
+- [ ] :exclamation: The frontend is not running yet
+
+**Test Steps:**
+
+1. Start the frontend application
+1. Click on the model selection button
+1. Validate that the current pipeline is selectable.
+
+**Expected Results:**
+
+- [ ] If a problem occurs while retrieving the data, an error should prevent the
+  server from starting.
+- [ ] If a problem occurs while retrieving the data, but no error was raised,
+  the model selection component should be empty.
+- [ ] If everything went correctly while retrieving the data, the model
+  selection component should display the pipeline metadata.
+
+**Actual Results:**
+
+- [ ] Describe the actual outcome of the test
+
+**Pass/Fail Criteria:**
+
+- [ ] Pass if the metadata from the available pipeline is displayed.
+- [ ] Fail if the metadata from the available pipeline is not displayed and no
+  error was raised.
+
+---
+
+## Test Case: Inference Request
+
+**Objective**: Verify that the inference request endpoint `/inf` behaves as
+expected.
+
+**Preconditions:**
+
+- [ ] Nachet backend is set up and running. Use the command `hypercorn -b :8080
+  app:app` to start the quartz server.
+- [ ] The environment variables are all set.
+- [ ] The frontend is running.
+- [ ] Start the frontend application
+- [ ] Click on the model selection button
+- [ ] Validate that the current pipeline is selectable
+
+**Test Steps:**
+
+1. Upload a seed image
+1. Select the first model (pipeline)
+1. Click on the classify button
+1. Wait until the results populated on the canvas
+1. Repeat the process for every model (pipeline)
+
+|:boom: Warning| |:--:| |Displaying results from two different models will
+overlap and become unreadable.|
+
+**Expected Results:**
+
+- [ ] The data populates both the canvas and the results components with the
+  prediction data from the model (pipeline).
+- [ ] An alert with an error from port 3000 or 8080 is displayed.
+
+**Actual Results:**
+
+- [ ] Describe the actual outcome of the test
+
+**Pass/Fail Criteria:**
+
+- [ ] Pass if the data populates both the canvas and the results components with
+  the prediction of the model (pipeline).
+- [ ] Fail if an alert is displayed with an error message.
+- [ ] Fail if the data does not populates the canvas and the results component
+- [ ] Fail if the inference is stuck in an infinite loop