Add black step when testing examples (#6425)

.github/workflows/snippets_tests.yml

@@ -19,8 +19,80 @@ env:
   PYTHON_VERSION: "3.8"
 
 jobs:
+  black:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Install Black
+        run: |
+          pip install --upgrade pip
+          pip install .[dev]
+
+      - name: Check status
+        run: |
+          if ! black . --check; then
+            git status
+            echo "###################################################################################################"
+            echo "# "
+            echo "# CHECK FAILED! Black found issues with your code formatting."
+            echo "# "
+            echo "# Either:"
+            echo "# 1. Run Black locally before committing:"
+            echo "# "
+            echo "#     pip install .[formatting]"
+            echo "#     black ."
+            echo "# "
+            echo "# 2. Install the pre-commit hook:"
+            echo "# "
+            echo "#     pre-commit install"
+            echo "# "
+            echo "# 3. See https://github.com/deepset-ai/haystack/blob/main/CONTRIBUTING.md for help."
+            echo "# "
+            echo "# If you have further problems, please open an issue: https://github.com/deepset-ai/haystack/issues"
+            echo "# "
+            echo "##################################################################################################"
+            exit 1
+          fi
+
+      - name: Calculate alert data
+        id: calculator
+        shell: bash
+        if: (success() || failure()) && github.ref_name == 'main'
+        run: |
+          if [ "${{ job.status }}" = "success" ]; then
+            echo "alert_type=success" >> "$GITHUB_OUTPUT";
+          else
+            echo "alert_type=error" >> "$GITHUB_OUTPUT";
+          fi
+
+      - name: Send event to Datadog
+        if: (success() || failure()) && github.ref_name == 'main'
+        uses: masci/datadog@v1
+        with:
+          api-key: ${{ secrets.CORE_DATADOG_API_KEY }}
+          api-url: https://api.datadoghq.eu
+          events: |
+            - title: "${{ github.workflow }} workflow"
+              text: "Job ${{ github.job }} in branch ${{ github.ref_name }}"
+              alert_type: "${{ steps.calculator.outputs.alert_type }}"
+              source_type_name: "Github"
+              host: ${{ github.repository_owner }}
+              tags:
+                - "project:${{ github.repository }}"
+                - "job:${{ github.job }}"
+                - "run_id:${{ github.run_id }}"
+                - "workflow:${{ github.workflow }}"
+                - "branch:${{ github.ref_name }}"
+                - "url:https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
+
   tests:
     name: Snippets
+    needs: black
     runs-on: ubuntu-latest
 
     steps:

.github/workflows/tests.yml

@@ -44,25 +44,6 @@ jobs:
         run: |
           if ! black . --check; then
             git status
-            echo "###################################################################################################"
-            echo "# "
-            echo "# CHECK FAILED! Black found issues with your code formatting."
-            echo "# "
-            echo "# Either:"
-            echo "# 1. Run Black locally before committing:"
-            echo "# "
-            echo "#     pip install .[formatting]"
-            echo "#     black ."
-            echo "# "
-            echo "# 2. Install the pre-commit hook:"
-            echo "# "
-            echo "#     pre-commit install"
-            echo "# "
-            echo "# 3. See https://github.com/deepset-ai/haystack/blob/main/CONTRIBUTING.md for help."
-            echo "# "
-            echo "# If you have further problems, please open an issue: https://github.com/deepset-ai/haystack/issues"
-            echo "# "
-            echo "##################################################################################################"
             exit 1
           fi
 

examples/pipeline_loop_to_autocorrect_json.py

@@ -24,9 +24,11 @@ class City(BaseModel):
     country: str
     population: int
 
+
 class CitiesData(BaseModel):
     cities: List[City]
 
+
 schema = CitiesData.schema_json(indent=2)
 
 
@@ -34,18 +36,13 @@ schema = CitiesData.schema_json(indent=2)
 # and validates if this is compliant with our schema.
 # If not, it returns also the error message so that we have a better chance of correcting it in the next loop
 @component
-class OutputParser():
+class OutputParser:
-    def __init__(self, pydantic_model:pydantic.BaseModel):
+    def __init__(self, pydantic_model: pydantic.BaseModel):
         self.pydantic_model = pydantic_model
         self.iteration_counter = 0
 
-    @component.output_types(valid=List[str],
+    @component.output_types(valid=List[str], invalid=Optional[List[str]], error_message=Optional[str])
-                            invalid=Optional[List[str]],
+    def run(self, replies: List[str]):
-                            error_message=Optional[str])
-    def run(
-            self,
-            replies: List[str]):
-
         self.iteration_counter += 1
 
         # let's simulate a corrupt JSON with 30% probability by adding extra brackets (for demo purposes)
@@ -55,13 +52,17 @@ class OutputParser():
         try:
             output_dict = json.loads(replies[0])
             self.pydantic_model.parse_obj(output_dict)
-            print(f"OutputParser at Iteration {self.iteration_counter}: Valid JSON from LLM - No need for looping: {replies[0]}")
+            print(
+                f"OutputParser at Iteration {self.iteration_counter}: Valid JSON from LLM - No need for looping: {replies[0]}"
+            )
             return {"valid": replies}
 
         except (ValueError, ValidationError) as e:
-            print(f"OutputParser at Iteration {self.iteration_counter}: Invalid JSON from LLM - Let's try again.\n"
+            print(
-                         f"Output from LLM:\n {replies[0]} \n"
+                f"OutputParser at Iteration {self.iteration_counter}: Invalid JSON from LLM - Let's try again.\n"
-                         f"Error from OutputParser: {e}")
+                f"Output from LLM:\n {replies[0]} \n"
+                f"Error from OutputParser: {e}"
+            )
             return {"invalid": replies, "error_message": str(e)}
 
 
@@ -92,9 +93,6 @@ pipeline.connect("output_parser.error_message", "prompt_builder.error_message")
 
 # Now, let's run our pipeline with an example passage that we want to convert into our JSON format
 passage = "Berlin is the capital of Germany. It has a population of 3,850,809"
-result = pipeline.run({
+result = pipeline.run({"prompt_builder": {"passage": passage, "schema": schema}})
-    "prompt_builder": {"passage": passage,
-                       "schema": schema}
-})
 
 print(result)