infra: setup lint in CI (#272)

.github/actions/poetry_setup/action.yml

@@ -0,0 +1,88 @@
+# An action for setting up poetry install with caching.
+# Using a custom action since the default action does not
+# take poetry install groups into account.
+# Action code from:
+# https://github.com/actions/setup-python/issues/505#issuecomment-1273013236
+name: poetry-install-with-caching
+description: Poetry install with support for caching of dependency groups.
+
+inputs:
+  python-version:
+    description: Python version, supporting MAJOR.MINOR only
+    required: true
+
+  poetry-version:
+    description: Poetry version
+    required: true
+
+  cache-key:
+    description: Cache key to use for manual handling of caching
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - uses: actions/setup-python@v5
+      name: Setup python ${{ inputs.python-version }}
+      id: setup-python
+      with:
+        python-version: ${{ inputs.python-version }}
+
+    - uses: actions/cache@v3
+      id: cache-bin-poetry
+      name: Cache Poetry binary - Python ${{ inputs.python-version }}
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
+      with:
+        path: |
+          /opt/pipx/venvs/poetry
+        # This step caches the poetry installation, so make sure it's keyed on the poetry version as well.
+        key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }}
+
+    - name: Refresh shell hashtable and fixup softlinks
+      if: steps.cache-bin-poetry.outputs.cache-hit == 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      run: |
+        set -eux
+
+        # Refresh the shell hashtable, to ensure correct `which` output.
+        hash -r
+
+        # `actions/cache@v3` doesn't always seem able to correctly unpack softlinks.
+        # Delete and recreate the softlinks pipx expects to have.
+        rm /opt/pipx/venvs/poetry/bin/python
+        cd /opt/pipx/venvs/poetry/bin
+        ln -s "$(which "python$PYTHON_VERSION")" python
+        chmod +x python
+        cd /opt/pipx_bin/
+        ln -s /opt/pipx/venvs/poetry/bin/poetry poetry
+        chmod +x poetry
+
+        # Ensure everything got set up correctly.
+        /opt/pipx/venvs/poetry/bin/python --version
+        /opt/pipx_bin/poetry --version
+
+    - name: Install poetry
+      if: steps.cache-bin-poetry.outputs.cache-hit != 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      # Install poetry using the python version installed by setup-python step.
+      run: pipx install "poetry==$POETRY_VERSION" --python '${{ steps.setup-python.outputs.python-path }}' --verbose
+
+    - name: Restore pip and poetry cached dependencies
+      uses: actions/cache@v3
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4"
+      with:
+        path: |
+          ~/.cache/pip
+          ~/.cache/pypoetry/virtualenvs
+          ~/.cache/pypoetry/cache
+          ~/.cache/pypoetry/artifacts
+          ./.venv
+        key: py-deps-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles('./poetry.lock') }}

.github/workflows/lint.yml

@@ -0,0 +1,61 @@
+name: lint
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+  # This env var allows us to get inline annotations when ruff has complaints.
+  RUFF_OUTPUT_FORMAT: github
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # Only lint on the min and max supported Python versions.
+        # It's extremely unlikely that there's a lint issue on any version in between
+        # that doesn't show up on the min or max versions.
+        #
+        # GitHub rate-limits how many jobs can be running at any one time.
+        # Starting new jobs is also relatively slow,
+        # so linting on fewer versions makes CI faster.
+        python-version:
+          - "3.8"
+          - "3.11"
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: lint
+
+      - name: Check Poetry File
+        shell: bash
+        run: poetry check
+
+      - name: Check lock file
+        shell: bash
+        run: poetry lock --check
+
+      - name: Install dependencies
+        run: poetry install --with lint
+
+      - name: Get .mypy_cache to speed up mypy
+        uses: actions/cache@v3
+        env:
+          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
+        with:
+          path: |
+            ./.mypy_cache
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ hashFiles('./poetry.lock') }}
+
+      - name: Analysing the code with our lint
+        run: |
+          make lint

Makefile

@@ -4,5 +4,12 @@ start:
 
 .PHONY: format
 format:
-	black .
-	isort .
+	poetry run ruff format .
+	poetry run ruff --select I --fix .
+
+.PHONY: lint
+lint:
+	poetry run ruff .
+	poetry run ruff format . --diff
+	poetry run ruff --select I .
+

_scripts/evaluate_chains_agent.py

@@ -25,29 +25,6 @@
 WEAVIATE_DOCS_INDEX_NAME = "LangChain_Combined_Docs_OpenAI_text_embedding_3_small"
 
 
-def search(inp: str, index_name: str, callbacks=None) -> str:
-    client = weaviate.Client(
-        url=WEAVIATE_URL,
-        auth_client_secret=weaviate.AuthApiKey(api_key=WEAVIATE_API_KEY),
-    )
-
-    weaviate_client = Weaviate(
-        client=client,
-        index_name=index_name,
-        text_key="text",
-        embedding=OpenAIEmbeddings(chunk_size=200),
-        by_text=False,
-        attributes=["source"] if not index_name == "LangChain_agent_sources" else None,
-    )
-    retriever = (
-        weaviate_client.as_retriever(search_kwargs=dict(k=3), callbacks=callbacks)
-        if index_name == "LangChain_agent_sources"
-        else weaviate_client.as_retriever(search_kwargs=dict(k=6), callbacks=callbacks)
-    )
-
-    return retriever.get_relevant_documents(inp, callbacks=callbacks)
-
-
 def search(inp: str, callbacks=None) -> list:
     client = weaviate.Client(
         url=WEAVIATE_URL,