Submit assignment 1

.devcontainer/Dockerfile

@@ -1,6 +1,6 @@
-FROM ubuntu:noble
-
-RUN apt-get update \
-	&& apt-get install -y curl python3 python3-pip git
-
+FROM ubuntu:noble
+
+RUN apt-get update \
+	&& apt-get install -y curl python3 python3-pip git
+
 RUN pip3 install git+https://github.com/tira-io/tira.git@pyterrier-artifacts#egg=tira&subdirectory=python-client

.devcontainer/devcontainer.json

@@ -1,20 +1,20 @@
-{
-	"build": {"dockerfile": "Dockerfile", "context": ".."},
-	"customizations": {
-	  "vscode": {
-		"extensions": [
-		  "ms-python.python",
-		  "ms-python.vscode-pylance",
-		  "ms-toolsai.jupyter",
-		  "ms-toolsai.datawrangler",
-		  "ms-azuretools.vscode-docker"
-		]
-	  },
-	  "codespaces": {
-		"openFiles":[
-		  "README.md"
-		]
-	  }
-	},
-	"runArgs": ["--network=host"]
+{
+	"build": {"dockerfile": "Dockerfile", "context": ".."},
+	"customizations": {
+	  "vscode": {
+		"extensions": [
+		  "ms-python.python",
+		  "ms-python.vscode-pylance",
+		  "ms-toolsai.jupyter",
+		  "ms-toolsai.datawrangler",
+		  "ms-azuretools.vscode-docker"
+		]
+	  },
+	  "codespaces": {
+		"openFiles":[
+		  "README.md"
+		]
+	  }
+	},
+	"runArgs": ["--network=host"]
 }

.gitignore

@@ -1,2 +1,2 @@
-__pycache__
-wows_eval.egg-info
+__pycache__
+wows_eval.egg-info

README.md

@@ -1,2 +1,2 @@
-# wows-code
-Code used for evaluation and baselines of the shared tasks and data challenges hosted as part of the Workshops on Open Web Search (WOWS).
+# wows-code
+Code used for evaluation and baselines of the shared tasks and data challenges hosted as part of the Workshops on Open Web Search (WOWS).

ecir24/README.md

@@ -1,42 +1,42 @@
-# Code and Tutorials for the [1st International Workshop on Open Web Search](https://opensearchfoundation.org/en/events-osf/wows2024) #wows2024
-
-This repository contains all code, tutorials, and baselines for the [1st International Workshop on Open Web Search](https://opensearchfoundation.org/en/events-osf/wows2024) hosted at the [46th European Conference on Information Retrieval](https://www.ecir2024.org/) in Glasgow (24th-28th March, 2024).
-
-
-## Tutorials
-
-We included all components into a [dashboard of resources](https://tira-io.github.io/teaching-ir-with-shared-tasks/) that can be easily re-used within teaching.
-
-- [Re-using pre-built indices](https://github.com/tira-io/teaching-ir-with-shared-tasks/blob/main/tutorials/tutorial-reuse-pyterrier-indices.ipynb)
-
-## Resources
-
-- [PyTerrier indices of public datasets](https://zenodo.org/records/10743990)
-
-|Team              | Component | Link to Tutorial Notebok|
-|------------------|-----------|-------------------------|
-|sean              |           |                         |
-|naverlabseurope   |           |                         |
-|fschlatt          |           |                         |
-|tu-dresden-01     |           |                         |
-|tu-dresden-02     |           |                         |
-|tu-dresden-03     |           | https://github.com/tira-io/teaching-ir-with-shared-tasks/blob/main/tutorials/tutorial-query-expansion-with-llms.ipynb                        |
-|tu-dresden-04     |           |                         |
-|qspell            |           |                         |
-|marcelgohsen      |           |                         |
-
-## Links
-
-
-## Resources
-
-Important links/resources:
-- [The workshop page](https://opensearchfoundation.org/en/events-osf/wows2024)
-- [Software submissions](https://www.tira.io/task-overview/workshop-on-open-web-search/)
-- [Pre-registration](https://www.tira.io/t/pre-registration) to promote new collaborations and brainstorming for the [ECIR Collab-a-thon](https://www.ecir2024.org/collab-a-thon/)
-- [Tutorial on how to submit](https://github.com/OpenWebSearch/wows-code/tree/main/ecir24/tutorials)
-- [Baselines for software submissions](https://github.com/OpenWebSearch/wows-code/tree/main/ecir24/baselines)
-- [Jupyter notebooks showcasing already submitted components in declarative PyTerrier pipelines](https://github.com/OpenWebSearch/wows-code/tree/main/ecir24/post-hoc-notebooks)
-
-If you have any questions or problems, please do not hesitate to contact us via [the forum](https://www.tira.io/t/the-forum-for-the-1st-international-workshop-on-open-web-search-wows2024) or via mail.
-
+# Code and Tutorials for the [1st International Workshop on Open Web Search](https://opensearchfoundation.org/en/events-osf/wows2024) #wows2024
+
+This repository contains all code, tutorials, and baselines for the [1st International Workshop on Open Web Search](https://opensearchfoundation.org/en/events-osf/wows2024) hosted at the [46th European Conference on Information Retrieval](https://www.ecir2024.org/) in Glasgow (24th-28th March, 2024).
+
+
+## Tutorials
+
+We included all components into a [dashboard of resources](https://tira-io.github.io/teaching-ir-with-shared-tasks/) that can be easily re-used within teaching.
+
+- [Re-using pre-built indices](https://github.com/tira-io/teaching-ir-with-shared-tasks/blob/main/tutorials/tutorial-reuse-pyterrier-indices.ipynb)
+
+## Resources
+
+- [PyTerrier indices of public datasets](https://zenodo.org/records/10743990)
+
+|Team              | Component | Link to Tutorial Notebok|
+|------------------|-----------|-------------------------|
+|sean              |           |                         |
+|naverlabseurope   |           |                         |
+|fschlatt          |           |                         |
+|tu-dresden-01     |           |                         |
+|tu-dresden-02     |           |                         |
+|tu-dresden-03     |           | https://github.com/tira-io/teaching-ir-with-shared-tasks/blob/main/tutorials/tutorial-query-expansion-with-llms.ipynb                        |
+|tu-dresden-04     |           |                         |
+|qspell            |           |                         |
+|marcelgohsen      |           |                         |
+
+## Links
+
+
+## Resources
+
+Important links/resources:
+- [The workshop page](https://opensearchfoundation.org/en/events-osf/wows2024)
+- [Software submissions](https://www.tira.io/task-overview/workshop-on-open-web-search/)
+- [Pre-registration](https://www.tira.io/t/pre-registration) to promote new collaborations and brainstorming for the [ECIR Collab-a-thon](https://www.ecir2024.org/collab-a-thon/)
+- [Tutorial on how to submit](https://github.com/OpenWebSearch/wows-code/tree/main/ecir24/tutorials)
+- [Baselines for software submissions](https://github.com/OpenWebSearch/wows-code/tree/main/ecir24/baselines)
+- [Jupyter notebooks showcasing already submitted components in declarative PyTerrier pipelines](https://github.com/OpenWebSearch/wows-code/tree/main/ecir24/post-hoc-notebooks)
+
+If you have any questions or problems, please do not hesitate to contact us via [the forum](https://www.tira.io/t/the-forum-for-the-1st-international-workshop-on-open-web-search-wows2024) or via mail.
+

ecir24/baselines/.devcontainer.json

@@ -1,8 +1,8 @@
-{
-  "image": "mam10eks/tira-for-school:0.0.1",
-  "customizations": {
-    "vscode": {
-      "extensions": ["ms-python.python", "ms-python.vscode-pylance", "ms-toolsai.jupyter"]
-    }
-  }
-}
+{
+  "image": "mam10eks/tira-for-school:0.0.1",
+  "customizations": {
+    "vscode": {
+      "extensions": ["ms-python.python", "ms-python.vscode-pylance", "ms-toolsai.jupyter"]
+    }
+  }
+}

ecir24/baselines/.github/workflows/upload-docker-submission.yml

@@ -1,62 +1,62 @@
-name: Upload Docker Software to TIRA
-on: 
-  workflow_dispatch:
-    inputs:
-      dockerpath:
-        description: The path to the directory where the Docker image should be build. Should contain a Dockerfile that specifies everything.
-        required: true
-        default: query-processing
-
-jobs:
-  docker-build:
-    runs-on: ubuntu-latest
-    timeout-minutes: 45
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v3
-      -
-        name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
-      -
-        name: Login to Docker Hub
-        uses: docker/login-action@v2
-        with:
-          registry: registry.webis.de
-          username: ${{ secrets.TIRA_DOCKER_REGISTRY_USER }}
-          password: ${{ secrets.TIRA_DOCKER_REGISTRY_TOKEN }}
-      -
-        name: Set up Dependencies
-        uses: actions/setup-python@v4
-        with:
-          python-version: 3.8
-      -
-        name: Install required python packages
-        run: |
-          python -m pip install --upgrade pip
-          pip install tira==0.0.100
-      -
-        name: Set environment variables
-        env:
-          TIRA_TASK_ID: TIRA_TASK_ID_FOR_AUTOMATIC_REPLACEMENT
-          TIRA_VM_ID: TIRA_USER_FOR_AUTOMATIC_REPLACEMENT
-        run: |
-          tira-run --export-submission-environment \
-          	GITHUB_SHA=${{ github.sha }} \
-          	TIRA_VM_ID=${{ env.TIRA_VM_ID }} \
-          	TIRA_TASK_ID=${{ env.TIRA_TASK_ID }} \
-          	TIRA_DOCKER_REGISTRY_TOKEN=${{ secrets.TIRA_DOCKER_REGISTRY_TOKEN }} \
-          	TIRA_DOCKER_REGISTRY_USER=${{ secrets.TIRA_DOCKER_REGISTRY_USER }} \
-          	TIRA_CLIENT_TOKEN=${{ secrets.TIRA_CLIENT_TOKEN }} \
-          	TIRA_CLIENT_USER=${{ secrets.TIRA_CLIENT_USER }} \
-          	TIRA_CODE_REPOSITORY_ID=${{ secrets.TIRA_CODE_REPOSITORY_ID }} \
-          	TIRA_DOCKER_FILE=${{ inputs.dockerfile }}/Dockerfile \
-          	TIRA_DOCKER_PATH=${{ inputs.dockerpath }}
-          	>> $GITHUB_ENV 
-      - name: Build, test, and upload image
-        run: |
-          docker build -t ${{ env.IMAGE_TAG }} -f ${{ github.workspace }}/${{ inputs.dockerpath }}
-          tira-run --input-dataset workshop-on-open-web-search/document-processing-20231027-training --image ${{ env.IMAGE_TAG }} --push true
+name: Upload Docker Software to TIRA
+on: 
+  workflow_dispatch:
+    inputs:
+      dockerpath:
+        description: The path to the directory where the Docker image should be build. Should contain a Dockerfile that specifies everything.
+        required: true
+        default: query-processing
+
+jobs:
+  docker-build:
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          registry: registry.webis.de
+          username: ${{ secrets.TIRA_DOCKER_REGISTRY_USER }}
+          password: ${{ secrets.TIRA_DOCKER_REGISTRY_TOKEN }}
+      -
+        name: Set up Dependencies
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.8
+      -
+        name: Install required python packages
+        run: |
+          python -m pip install --upgrade pip
+          pip install tira==0.0.100
+      -
+        name: Set environment variables
+        env:
+          TIRA_TASK_ID: TIRA_TASK_ID_FOR_AUTOMATIC_REPLACEMENT
+          TIRA_VM_ID: TIRA_USER_FOR_AUTOMATIC_REPLACEMENT
+        run: |
+          tira-run --export-submission-environment \
+          	GITHUB_SHA=${{ github.sha }} \
+          	TIRA_VM_ID=${{ env.TIRA_VM_ID }} \
+          	TIRA_TASK_ID=${{ env.TIRA_TASK_ID }} \
+          	TIRA_DOCKER_REGISTRY_TOKEN=${{ secrets.TIRA_DOCKER_REGISTRY_TOKEN }} \
+          	TIRA_DOCKER_REGISTRY_USER=${{ secrets.TIRA_DOCKER_REGISTRY_USER }} \
+          	TIRA_CLIENT_TOKEN=${{ secrets.TIRA_CLIENT_TOKEN }} \
+          	TIRA_CLIENT_USER=${{ secrets.TIRA_CLIENT_USER }} \
+          	TIRA_CODE_REPOSITORY_ID=${{ secrets.TIRA_CODE_REPOSITORY_ID }} \
+          	TIRA_DOCKER_FILE=${{ inputs.dockerfile }}/Dockerfile \
+          	TIRA_DOCKER_PATH=${{ inputs.dockerpath }}
+          	>> $GITHUB_ENV 
+      - name: Build, test, and upload image
+        run: |
+          docker build -t ${{ env.IMAGE_TAG }} -f ${{ github.workspace }}/${{ inputs.dockerpath }}
+          tira-run --input-dataset workshop-on-open-web-search/document-processing-20231027-training --image ${{ env.IMAGE_TAG }} --push true

ecir24/baselines/README.md

@@ -1,33 +1,33 @@
-# Submissions of TIRA_USER_FOR_AUTOMATIC_REPLACEMENT
-
-This repository contains baseline submissions (document-processing, query-processing, re-ranking, and retrieval) together with a Github action and a development container configuration as starting point for submissions for the [](). 
-
-We recommend that you work either in Github Codespaces or using [dev containers with Docker](https://code.visualstudio.com/docs/devcontainers/containers). Github Codespaces are an easy option to start in a few minutes (free tier of 130 compute hours per month), whereas dev container with Docker might be interesting if you want to put a bit more focus on technical/deployment details.
-
-
-## Developing in Github Codespaces
-
-- Open this repository in Github Codespaces (i.e., click on "Code" -> "Codespaces" -> "Create ...").
-- Please do not forget to commit often
-
-
-## Developing in Dev Containers
-
-A dev container (please find a suitable installation instruction [here](https://code.visualstudio.com/docs/devcontainers/containers)) allows you to directly work in the prepared Docker container so that you do not have to install the dependencies (which can sometimes be a bit tricky).
-
-To develop with dev containers, please:
-
-- Install [VS Code](https://code.visualstudio.com/download) and [Docker](https://docs.docker.com/engine/install/) on your machine
-- Clone this repository: `git clone ...`
-- Open the directory `jupyter-notebook-submissions` with VS Code (it should ask you to open the repository in a dev container)
-
-If you do not want to use VS Code, you can start and develop in a jupyter notebook via (please execute the command within the `jupyter-notebook-submissions` directory):
-
-```
-docker run --rm  -it -p 8888:8888 --entrypoint jupyter -w /workspace -v ${PWD}:/workspace webis/ir-lab-wise-2023:0.0.1 notebook --allow-root --ip 0.0.0.0
-```
-
-## Submitting Your Software
-
-Run the github action to submit your software.
-
+# Submissions of TIRA_USER_FOR_AUTOMATIC_REPLACEMENT
+
+This repository contains baseline submissions (document-processing, query-processing, re-ranking, and retrieval) together with a Github action and a development container configuration as starting point for submissions for the [](). 
+
+We recommend that you work either in Github Codespaces or using [dev containers with Docker](https://code.visualstudio.com/docs/devcontainers/containers). Github Codespaces are an easy option to start in a few minutes (free tier of 130 compute hours per month), whereas dev container with Docker might be interesting if you want to put a bit more focus on technical/deployment details.
+
+
+## Developing in Github Codespaces
+
+- Open this repository in Github Codespaces (i.e., click on "Code" -> "Codespaces" -> "Create ...").
+- Please do not forget to commit often
+
+
+## Developing in Dev Containers
+
+A dev container (please find a suitable installation instruction [here](https://code.visualstudio.com/docs/devcontainers/containers)) allows you to directly work in the prepared Docker container so that you do not have to install the dependencies (which can sometimes be a bit tricky).
+
+To develop with dev containers, please:
+
+- Install [VS Code](https://code.visualstudio.com/download) and [Docker](https://docs.docker.com/engine/install/) on your machine
+- Clone this repository: `git clone ...`
+- Open the directory `jupyter-notebook-submissions` with VS Code (it should ask you to open the repository in a dev container)
+
+If you do not want to use VS Code, you can start and develop in a jupyter notebook via (please execute the command within the `jupyter-notebook-submissions` directory):
+
+```
+docker run --rm  -it -p 8888:8888 --entrypoint jupyter -w /workspace -v ${PWD}:/workspace webis/ir-lab-wise-2023:0.0.1 notebook --allow-root --ip 0.0.0.0
+```
+
+## Submitting Your Software
+
+Run the github action to submit your software.
+

ecir24/baselines/dev-container/Dockerfile

@@ -1,14 +1,14 @@
-#docker build -t webis/wows-2024-baseline:0.0.6 .
-FROM pytorch/pytorch:latest
-
-ENV PYTERRIER_VERSION='5.8'
-ENV PYTERRIER_HELPER_VERSION='0.0.8'
-
-RUN apt-get update \
-	&& DEBIAN_FRONTEND=noninteractive TZ=Etc/UTC apt-get install -y git openjdk-11-jdk wget \
-	&& rm -rf /root/.cache
-
-RUN apt-get install -y gcc \
-	&& pip3 install tira ir_datasets python-terrier \
-	&& rm -rf /root/.cache
-
+#docker build -t webis/wows-2024-baseline:0.0.6 .
+FROM pytorch/pytorch:latest
+
+ENV PYTERRIER_VERSION='5.8'
+ENV PYTERRIER_HELPER_VERSION='0.0.8'
+
+RUN apt-get update \
+	&& DEBIAN_FRONTEND=noninteractive TZ=Etc/UTC apt-get install -y git openjdk-11-jdk wget \
+	&& rm -rf /root/.cache
+
+RUN apt-get install -y gcc \
+	&& pip3 install tira ir_datasets python-terrier \
+	&& rm -rf /root/.cache
+