RES-731: add queues per tenant

.dvc/config

@@ -5,4 +5,4 @@
     url = ssh://vector.iqser.com/research/image-prediction/
     port = 22
 ['remote "azure_remote"']
-    url = azure://ic-sa-dvc/
+    url = azure://image-classification-dvc/

.gitlab-ci.yml

@@ -1,31 +1,53 @@
 include:
   - project: "Gitlab/gitlab"
-    ref: 0.3.0
+    ref: main
-    file: "/ci-templates/research/dvc-versioning-build-release.gitlab-ci.yml"
+    file: "/ci-templates/research/dvc.gitlab-ci.yml"
+  - project: "Gitlab/gitlab"
+    ref: main
+    file: "/ci-templates/research/versioning-build-test-release.gitlab-ci.yml"
 
 variables:
   NEXUS_PROJECT_DIR: red
   IMAGENAME: "${CI_PROJECT_NAME}"
   INTEGRATION_TEST_FILE: "${CI_PROJECT_ID}.pdf"
+  FF_USE_FASTZIP: "true" # enable fastzip - a faster zip implementation that also supports level configuration.
+  ARTIFACT_COMPRESSION_LEVEL: default # can also be set to fastest, fast, slow and slowest. If just enabling fastzip is not enough try setting this to fastest or fast.
+  CACHE_COMPRESSION_LEVEL: default # same as above, but for caches
+  # TRANSFER_METER_FREQUENCY: 5s # will display transfer progress every 5 seconds for artifacts and remote caches. For debugging purposes.
+
+stages:
+  - data
+  - setup
+  - tests
+  - sonarqube
+  - versioning
+  - build
+  - integration-tests
+  - release
+
+docker-build:
+  extends: .docker-build
+  script:
+    - !reference [.docker-kaniko-build-config, script]
+    - !reference [.docker-kaniko-build-script, script]
+  needs:
+    - job: dvc-pull
+      artifacts: true
   
-#################################
+###################
-# temp. disable integration tests, b/c they don't cover the CV analysis case yet
+# INTEGRATION TESTS
-trigger integration tests:
+trigger-integration-tests:
+  extends: .integration-tests
+  # ADD THE MODEL BUILD WHICH SHOULD TRIGGER THE INTEGRATION TESTS
+  # needs:
+  #   - job: docker-build::model_name
+  #     artifacts: true
   rules:
     - when: never
 
-release build:
+#########
-  stage: release
+# RELEASE
+release:
+  extends: .release
   needs:
-  - job: set custom version
+    - !reference [.needs-versioning, needs] # leave this line as is
-    artifacts: true
-    optional: true
-  - job: calculate patch version
-    artifacts: true
-    optional: true
-  - job: calculate minor version
-    artifacts: true
-    optional: true
-  - job: build docker nexus
-    artifacts: true
-#################################

Dockerfile

@@ -1,11 +1,17 @@
-FROM python:3.10
+FROM python:3.10-slim AS builder
+
+ARG GITLAB_USER
+ARG GITLAB_ACCESS_TOKEN
 
-ARG USERNAME
-ARG TOKEN
 ARG PYPI_REGISTRY_RESEARCH=https://gitlab.knecon.com/api/v4/groups/19/-/packages/pypi
 ARG POETRY_SOURCE_REF_RESEARCH=gitlab-research
+
 ARG PYPI_REGISTRY_RED=https://gitlab.knecon.com/api/v4/groups/12/-/packages/pypi
 ARG POETRY_SOURCE_REF_RED=gitlab-red
+
+ARG PYPI_REGISTRY_FFORESIGHT=https://gitlab.knecon.com/api/v4/groups/269/-/packages/pypi
+ARG POETRY_SOURCE_REF_FFORESIGHT=gitlab-fforesight
+
 ARG VERSION=dev
 
 LABEL maintainer="Research <research@knecon.com>"
@@ -13,27 +19,55 @@ LABEL version="${VERSION}"
 
 WORKDIR /app
 
+###########
+# ENV SETUP
+ENV PYTHONDONTWRITEBYTECODE=true
 ENV PYTHONUNBUFFERED=true
 ENV POETRY_HOME=/opt/poetry
 ENV PATH="$POETRY_HOME/bin:$PATH"
 
+RUN apt-get update && \
+    apt-get install -y curl git bash build-essential libffi-dev libssl-dev && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
 RUN curl -sSL https://install.python-poetry.org | python3 -
+RUN poetry --version
 
-COPY ./data ./data
+COPY pyproject.toml poetry.lock ./
-COPY ./config ./config
-COPY ./src ./src
-COPY pyproject.toml poetry.lock banner.txt ./
 
-RUN poetry config virtualenvs.create false && \
+RUN poetry config virtualenvs.create true && \
+    poetry config virtualenvs.in-project true && \
     poetry config installer.max-workers 10 && \
     poetry config repositories.${POETRY_SOURCE_REF_RESEARCH} ${PYPI_REGISTRY_RESEARCH} && \
-    poetry config http-basic.${POETRY_SOURCE_REF_RESEARCH} ${USERNAME} ${TOKEN} && \
+    poetry config http-basic.${POETRY_SOURCE_REF_RESEARCH} ${GITLAB_USER} ${GITLAB_ACCESS_TOKEN} && \
     poetry config repositories.${POETRY_SOURCE_REF_RED} ${PYPI_REGISTRY_RED} && \
-    poetry config http-basic.${POETRY_SOURCE_REF_RED} ${USERNAME} ${TOKEN} && \
+    poetry config http-basic.${POETRY_SOURCE_REF_RED} ${GITLAB_USER} ${GITLAB_ACCESS_TOKEN} && \
-    poetry install --without=dev -vv --no-interaction
+    poetry config repositories.${POETRY_SOURCE_REF_FFORESIGHT} ${PYPI_REGISTRY_FFORESIGHT} && \
+    poetry config http-basic.${POETRY_SOURCE_REF_FFORESIGHT} ${GITLAB_USER} ${GITLAB_ACCESS_TOKEN} && \
+    poetry install --without=dev -vv --no-interaction --no-root
+
+###############
+# WORKING IMAGE
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# COPY SOURCE CODE FROM BUILDER IMAGE
+COPY --from=builder /app /app
+# COPY BILL OF MATERIALS (BOM)
+COPY bom.json /bom.json
+
+ENV PATH="/app/.venv/bin:$PATH"
+
+###################
+# COPY SOURCE CODE
+COPY ./src ./src
+COPY ./config ./config
+COPY ./data ./data
+COPY banner.txt ./
 
 EXPOSE 5000
 EXPOSE 8080
 
-
 CMD [ "python", "src/serve.py"]

config/pyinfra.toml

@@ -1,9 +1,17 @@
+
+[dynamic_tenant_queues]
+enabled = true
+
 [metrics.prometheus]
 enabled = true
 prefix = "redactmanager_image_service"
 
-[tracing.opentelemetry]
+[tracing]
 enabled = true
+# possible values "opentelemetry" | "azure_monitor" (Excpects APPLICATIONINSIGHTS_CONNECTION_STRING environment variable.)
+type = "azure_monitor" 
+
+[tracing.opentelemetry]
 endpoint = "http://otel-collector-opentelemetry-collector.otel-collector:4318/v1/traces"
 service_name = "redactmanager_image_service"
 exporter = "otlp"
@@ -25,6 +33,16 @@ input_queue = "request_queue"
 output_queue = "response_queue"
 dead_letter_queue = "dead_letter_queue"
 
+tenant_event_queue_suffix = "_tenant_event_queue"
+tenant_event_dlq_suffix = "_tenant_events_dlq"
+tenant_exchange_name = "tenants-exchange"
+queue_expiration_time = 300000  # 5 minutes in milliseconds
+
+service_request_queue_prefix = "image_request_queue"
+service_request_exchange_name = "image_request_exchange"
+service_response_exchange_name = "image_response_exchange"
+service_dlq_name = "image_dlq"
+
 [storage]
 backend = "s3"
 
@@ -41,4 +59,7 @@ connection_string = ""
 
 [storage.tenant_server]
 public_key = ""
-endpoint =  "http://tenant-user-management:8081/internal-api/tenants"
+endpoint =  "http://tenant-user-management:8081/internal-api/tenants"
+
+[kubernetes]
+pod_name = "test_pod"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "image-classification-service"
-version = "2.4.0"
+version = "2.4.1"
 description = ""
 authors = ["Team Research <research@knecon.com>"]
 readme = "README.md"
@@ -8,7 +8,7 @@ packages = [{ include = "image_prediction", from = "src" }]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<3.11"
-pyinfra = { version = "2.1.0", source = "gitlab-research" }
+pyinfra = { version = "3.2.2", source = "gitlab-research" }
 kn-utils = { version = "0.2.7", source = "gitlab-research" }
 dvc = "^2.34.0"
 dvc-ssh = "^2.20.0"
@@ -32,11 +32,11 @@ coverage = "^6.3.2"
 Pillow = "^9.1.0"
 pdf2image = "^1.16.0"
 frozendict = "^2.3.0"
-protobuf = "^3.20.0"
 fsspec = "^2022.11.0"
 PyMonad = "^2.4.0"
 pdfnetpython3 = "9.4.2"
 loguru = "^0.7.0"
+cyclonedx-bom = "^4.5.0"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.0.1"

scripts/docker_build_run.sh

@@ -1,6 +1,6 @@
-docker build -t image-clsasification-service:$(poetry version -s)-dev \                                                               
+docker build -t --platform linux/amd64 image-clsasification-service:$(poetry version -s)-dev \                                                               
     -f Dockerfile \
-    --build-arg USERNAME=$GITLAB_USER \
+    --build-arg GITLAB_USER=$GITLAB_USER \
-    --build-arg TOKEN=$GITLAB_ACCESS_TOKEN \
+    --build-arg GITLAB_ACCESS_TOKEN=$GITLAB_ACCESS_TOKEN \
     . && \
 docker run -it --rm image-clsasification-service:$(poetry version -s)-dev

src/image_prediction/image_extractor/extractors/parsable.py

@@ -35,7 +35,7 @@ class ParsablePDFImageExtractor(ImageExtractor):
             tolerance: The tolerance in pixels for the distance between images, beyond which they will not be stitched
                 together
         """
-        self.doc: fitz.fitz.Document = None
+        self.doc: fitz.Document = None
         self.verbose = verbose
         self.tolerance = tolerance
 
@@ -48,7 +48,7 @@ class ParsablePDFImageExtractor(ImageExtractor):
 
         yield from image_metadata_pairs
 
-    def __process_images_on_page(self, page: fitz.fitz.Page):
+    def __process_images_on_page(self, page: fitz.Page):
         metadata = extract_valid_metadata(self.doc, page)
         images = get_images_on_page(self.doc, metadata)
 
@@ -130,7 +130,7 @@ def get_images_on_page(doc, metadata):
     yield from images
 
 
-def extract_valid_metadata(doc: fitz.fitz.Document, page: fitz.fitz.Page):
+def extract_valid_metadata(doc: fitz.Document, page: fitz.Page):
     metadata = get_metadata_for_images_on_page(page)
     metadata = filter_valid_metadata(metadata)
     metadata = add_alpha_channel_info(doc, metadata)
@@ -191,7 +191,7 @@ def xref_to_image(doc, xref) -> Union[Image.Image, None]:
         return
 
 
-def convert_pixmap_to_array(pixmap: fitz.fitz.Pixmap):
+def convert_pixmap_to_array(pixmap: fitz.Pixmap):
     array = np.frombuffer(pixmap.samples, dtype=np.uint8).reshape(pixmap.h, pixmap.w, pixmap.n)
     array = _normalize_channels(array)
     return array