ops: separate format check into a different workflow (#687)

Author: georgeh0

.github/workflows/CI.yml

@@ -26,33 +26,6 @@ permissions:
   contents: read
 
 jobs:
-  rust-format-check:
-    name: Check Rust formatting
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@stable
-        with:
-          components: rustfmt
-      - name: Check Rust formatting
-        run: |
-          cargo fmt --check
-
-  python-format-check:
-    name: Check Python formatting
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: 3.11
-      - name: Install Ruff
-        run: |
-          pip install ruff
-      - name: Check Python formatting
-        run: |
-          ruff format --check .
-
   test:
     name: Run test
     uses: ./.github/workflows/_test.yml

.github/workflows/format.yml

@@ -0,0 +1,52 @@
+# This file is autogenerated by maturin v1.8.1
+# To update, run
+#
+#    maturin generate-ci github
+#
+name: format check
+
+on:
+  pull_request:
+    branches: [main]
+    paths:
+      - src/**
+      - python/**
+      - examples/**
+  push:
+    branches: [main]
+    paths:
+      - src/**
+      - python/**
+      - examples/**
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  rust-format-check:
+    name: Check Rust formatting
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          components: rustfmt
+      - name: Check Rust formatting
+        run: |
+          cargo fmt --check
+
+  python-format-check:
+    name: Check Python formatting
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.11
+      - name: Install Ruff
+        run: |
+          pip install ruff
+      - name: Check Python formatting
+        run: |
+          ruff format --check .

examples/patient_intake_extraction/.env.example

@@ -1,4 +1,4 @@
 # Postgres database address for cocoindex
 COCOINDEX_DATABASE_URL=postgres://cocoindex:cocoindex@localhost/cocoindex
 
-OPENAI_API_KEY=
+OPENAI_API_KEY=

examples/patient_intake_extraction/README.md

@@ -2,7 +2,7 @@
 [![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex)
 
 
-This repo shows how to use OpenAI API to extract structured data from patient intake forms with different formats, like PDF, Docx, etc. from Google Drive. 
+This repo shows how to use OpenAI API to extract structured data from patient intake forms with different formats, like PDF, Docx, etc. from Google Drive.
 
 We appreciate a star ⭐ at [CocoIndex Github](https://github.com/cocoindex-io/cocoindex) if this is helpful.
 

examples/patient_intake_extraction/main.py

@@ -8,25 +8,29 @@
 
 import cocoindex
 
+
 @dataclasses.dataclass
 class Contact:
     name: str
     phone: str
     relationship: str
 
+
 @dataclasses.dataclass
 class Address:
     street: str
     city: str
     state: str
     zip_code: str
 
+
 @dataclasses.dataclass
 class Pharmacy:
     name: str
     phone: str
     address: Address
 
+
 @dataclasses.dataclass
 class Insurance:
     provider: str
@@ -35,25 +39,30 @@ class Insurance:
     policyholder_name: str
     relationship_to_patient: str
 
+
 @dataclasses.dataclass
 class Condition:
     name: str
     diagnosed: bool
 
+
 @dataclasses.dataclass
 class Medication:
     name: str
     dosage: str
 
+
 @dataclasses.dataclass
 class Allergy:
     name: str
 
+
 @dataclasses.dataclass
 class Surgery:
     name: str
     date: str
 
+
 @dataclasses.dataclass
 class Patient:
     name: str
@@ -80,6 +89,7 @@ class Patient:
 class ToMarkdown(cocoindex.op.FunctionSpec):
     """Convert a document to markdown."""
 
+
 @cocoindex.op.executor_class(gpu=True, cache=True, behavior_version=1)
 class ToMarkdownExecutor:
     """Executor for ToMarkdown."""
@@ -99,25 +109,33 @@ def __call__(self, content: bytes, filename: str) -> str:
             text = self._converter.convert(temp_file.name).text_content
             return text
 
+
 @cocoindex.flow_def(name="PatientIntakeExtraction")
-def patient_intake_extraction_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.DataScope):
+def patient_intake_extraction_flow(
+    flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.DataScope
+):
     """
     Define a flow that extracts patient information from intake forms.
     """
     data_scope["documents"] = flow_builder.add_source(
-        cocoindex.sources.LocalFile(path="data/patient_forms", binary=True))
+        cocoindex.sources.LocalFile(path="data/patient_forms", binary=True)
+    )
 
     patients_index = data_scope.add_collector()
 
     with data_scope["documents"].row() as doc:
-
-        doc["markdown"] = doc["content"].transform(ToMarkdown(), filename = doc["filename"])
+        doc["markdown"] = doc["content"].transform(
+            ToMarkdown(), filename=doc["filename"]
+        )
         doc["patient_info"] = doc["markdown"].transform(
             cocoindex.functions.ExtractByLlm(
                 llm_spec=cocoindex.LlmSpec(
-                    api_type=cocoindex.LlmApiType.OPENAI, model="gpt-4o"),
+                    api_type=cocoindex.LlmApiType.OPENAI, model="gpt-4o"
+                ),
                 output_type=Patient,
-                instruction="Please extract patient information from the intake form."))
+                instruction="Please extract patient information from the intake form.",
+            )
+        )
         patients_index.collect(
             filename=doc["filename"],
             patient_info=doc["patient_info"],