Merge pull request #17 from argilla-io/feat/code_rewriting

[RELEASE] ArgillaLlamaIndex 1.0: Update to Llama Index >= 0.10.0

.github/workflows/integration-tests.yml

@@ -0,0 +1,83 @@
+name: 🧪 Integration Tests
+
+on:
+  push:
+    branches:
+      - '*'
+
+jobs:
+  integration_tests:
+    name: Running integration tests, which require an Argilla instance running
+    runs-on: ubuntu-latest
+    services:
+      search-engine:
+        image:
+          searchEngineDockerImage:
+            description: "The name of the Docker image of the search engine to use."
+            default: docker.elastic.co/elasticsearch/elasticsearch:8.8.2
+            required: false
+            type: string
+        ports:
+          - 6900:6900
+        env:
+          searchEngineDockerEnv:
+            description: "The name of the Docker image of the search engine to use."
+            default: '{"discovery.type": "single-node", "xpack.security.enabled": "false"}'
+            required: false
+            type: string
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout Code 🛎
+        uses: actions/checkout@v3
+      - name: Setup Conda Env 🐍
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          miniforge-variant: Mambaforge
+          miniforge-version: latest
+          use-mamba: true
+          activate-environment: argilla
+      - name: Get date for conda cache
+        id: get-date
+        run: echo "::set-output name=today::$(/bin/date -u '+%Y%m%d')"
+        shell: bash
+      - name: Cache Conda env
+        uses: actions/cache@v3
+        id: cache
+        with:
+          path: ${{ env.CONDA }}/envs
+          key: conda-${{ runner.os }}--${{ runner.arch }}--${{ steps.get-date.outputs.today }}-${{ hashFiles('environment_dev.yml') }}-${{ env.CACHE_NUMBER }}
+      - name: Update environment
+        if: steps.cache.outputs.cache-hit != 'true'
+        run: mamba env update -n argilla -f environment_dev.yml
+      - name: Cache pip 👜
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ env.CACHE_NUMBER }}-${{ hashFiles('pyproject.toml') }}
+      - name: Set Argilla search engine env variable
+        if: startsWith(inputs.searchEngineDockerImage, 'docker.elastic.co')
+        run: |
+          echo "ARGILLA_SEARCH_ENGINE=elasticsearch" >> "$GITHUB_ENV"
+          echo "Configure elasticsearch engine"
+      - name: Set Argilla search engine env variable
+        if: startsWith(inputs.searchEngineDockerImage, 'opensearchproject')
+        run: |
+          echo "ARGILLA_SEARCH_ENGINE=opensearch" >> "$GITHUB_ENV"
+          echo "Configure opensearch engine"
+      - name: Launch Argilla Server
+        env:
+          ARGILLA_ENABLE_TELEMETRY: 0
+        run: |
+          pip install -e ".[server]"
+          python -m argilla server database migrate
+          python -m argilla server database users create_default
+          python -m argilla server start &
+      - name: Run end2end examples 📈
+        env:
+          ARGILLA_ENABLE_TELEMETRY: 0
+        run: |
+          pip install pytest
+          pytest tests
+

.github/workflows/release.yml

@@ -0,0 +1,39 @@
+name: 🎉 Release
+
+on:
+  release:
+    types:
+      - published
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+          # Looks like it's not working very well for other people:
+          # https://github.com/actions/setup-python/issues/436
+          # cache: "pip"
+          # cache-dependency-path: pyproject.toml
+
+      - uses: actions/cache@v3
+        id: cache
+        with:
+          path: ${{ env.pythonLocation }}
+          key: ${{ runner.os }}-python-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml') }}-release-v00
+
+      - name: Install dependencies
+        if: steps.cache.outputs.cache-hit != 'true'
+        run: pip install build
+
+      - name: Build distribution
+        run: python -m build
+
+      - name: Publish
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -3,6 +3,8 @@ __pycache__/
 *.py[cod]
 *$py.class
 
+.DS_Store
+
 # C extensions
 *.so
 

pyproject.toml

@@ -18,8 +18,8 @@ classifiers = [
     "Programming Language :: Python :: 3.11",
 ]
 dependencies = [
-    "argilla >= 1.18.0",
-    "llama-index >= 0.9.32",
+    "argilla >= 1.22.0",
+    "llama-index >= 0.10.0",
     "packaging >= 23.2",
     "typing-extensions >= 4.3.0"
 ]

src/argilla_llama_index/__init__.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.0.1-alpha"
+__version__ = "1.0.0"
 
 from argilla_llama_index.llama_index_handler import ArgillaCallbackHandler
 

src/argilla_llama_index/helpers.py

@@ -0,0 +1,43 @@
+"""
+Auxiliary methods for the Argilla Llama Index integration.
+"""
+
+from datetime import datetime
+from typing import Dict, List
+
+from llama_index.core.callbacks.schema import CBEvent
+
+def _get_time_diff(event_1_time_str: str, event_2_time_str: str) -> float:
+    """
+    Get the time difference between two events Follows the American format (month, day, year).
+
+    Args:
+        event_1_time_str (str): The first event time.
+        event_2_time_str (str): The second event time.
+
+    Returns:
+        float: The time difference between the two events.
+    """
+    time_format = "%m/%d/%Y, %H:%M:%S.%f"
+
+    event_1_time = datetime.strptime(event_1_time_str, time_format)
+    event_2_time = datetime.strptime(event_2_time_str, time_format)
+
+    return round((event_2_time - event_1_time).total_seconds(), 4)
+
+
+def _calc_time(events_data: Dict[str, List[CBEvent]], id: str) -> float:
+    """
+    Calculate the time difference between the start and end of an event using the events_data.
+
+    Args:
+        events_data (Dict[str, List[CBEvent]]): The events data, stored in a dictionary.
+        id (str): The event id to calculate the time difference between start and finish timestamps.
+
+    Returns:
+        float: The time difference between the start and end of the event.
+    """
+
+    start_time = events_data[id][0].time
+    end_time = events_data[id][1].time
+    return _get_time_diff(start_time, end_time)