Chore: AutoFix formatting and update slash commands (#13)

Author: aaronsteers

.github/workflows/fix-pr-command.yml .github/workflows/autofix-command.yml.github/workflows/fix-pr-command.yml renamed to .github/workflows/autofix-command.yml

@@ -1,4 +1,4 @@
-name: On-Demand PR Auto-Fix
+name: On-Demand AutoFix
 
 on:
   workflow_dispatch:

.github/workflows/python_lint.yml

@@ -82,4 +82,4 @@ jobs:
         files: "airbyte_cdk/**/*.py"
     - name: Run mypy on changed files
       if: steps.changed-py-files.outputs.any_changed == 'true'
-      run: mypy ${{ steps.changed-py-files.outputs.all_changed_files }} --config-file mypy.ini --install-types --non-interactive
+      run: poetry run mypy ${{ steps.changed-py-files.outputs.all_changed_files }} --config-file mypy.ini --install-types --non-interactive

.github/workflows/slash_command_dispatch.yml

@@ -20,8 +20,8 @@ jobs:
           dispatch-type: workflow
           issue-type: pull-request
           commands: |
-            fix-pr
-            test-pr
+            autofix
+            test
             poetry-lock
           static-args: |
             pr=${{ github.event.issue.number }}

.github/workflows/test-pr-command.yml .github/workflows/test-command.yml.github/workflows/test-pr-command.yml renamed to .github/workflows/test-command.yml

@@ -1,4 +1,4 @@
-name: On-Demand PR Test
+name: On-Demand Test
 
 on:
   workflow_dispatch:

airbyte_cdk/connector.py

@@ -96,8 +96,7 @@ def check(self, logger: logging.Logger, config: TConfig) -> AirbyteConnectionSta
 
 class _WriteConfigProtocol(Protocol):
     @staticmethod
-    def write_config(config: Mapping[str, Any], config_path: str) -> None:
-        ...
+    def write_config(config: Mapping[str, Any], config_path: str) -> None: ...
 
 
 class DefaultConnectorMixin:
@@ -108,5 +107,4 @@ def configure(self: _WriteConfigProtocol, config: Mapping[str, Any], temp_dir: s
         return config
 
 
-class Connector(DefaultConnectorMixin, BaseConnector[Mapping[str, Any]], ABC):
-    ...
+class Connector(DefaultConnectorMixin, BaseConnector[Mapping[str, Any]], ABC): ...

airbyte_cdk/connector_builder/main.py

@@ -74,7 +74,9 @@ def handle_request(args: List[str]) -> str:
     command, config, catalog, state = get_config_and_catalog_from_args(args)
     limits = get_limits(config)
     source = create_source(config, limits)
-    return orjson.dumps(AirbyteMessageSerializer.dump(handle_connector_builder_request(source, command, config, catalog, state, limits))).decode()  # type: ignore[no-any-return] # Serializer.dump() always returns AirbyteMessage
+    return orjson.dumps(
+        AirbyteMessageSerializer.dump(handle_connector_builder_request(source, command, config, catalog, state, limits))
+    ).decode()  # type: ignore[no-any-return] # Serializer.dump() always returns AirbyteMessage
 
 
 if __name__ == "__main__":

airbyte_cdk/destinations/destination.py

@@ -85,7 +85,6 @@ def parse_args(self, args: List[str]) -> argparse.Namespace:
         return parsed_args
 
     def run_cmd(self, parsed_args: argparse.Namespace) -> Iterable[AirbyteMessage]:
-
         cmd = parsed_args.command
         if cmd not in self.VALID_CMDS:
             raise Exception(f"Unrecognized command: {cmd}")

airbyte_cdk/destinations/vector_db_based/embedder.py

@@ -109,7 +109,19 @@ def __init__(self, config: OpenAIEmbeddingConfigModel, chunk_size: int):
 class AzureOpenAIEmbedder(BaseOpenAIEmbedder):
     def __init__(self, config: AzureOpenAIEmbeddingConfigModel, chunk_size: int):
         # Azure OpenAI API has — as of 20230927 — a limit of 16 documents per request
-        super().__init__(OpenAIEmbeddings(openai_api_key=config.openai_key, chunk_size=16, max_retries=15, openai_api_type="azure", openai_api_version="2023-05-15", openai_api_base=config.api_base, deployment=config.deployment, disallowed_special=()), chunk_size)  # type: ignore
+        super().__init__(
+            OpenAIEmbeddings(
+                openai_api_key=config.openai_key,
+                chunk_size=16,
+                max_retries=15,
+                openai_api_type="azure",
+                openai_api_version="2023-05-15",
+                openai_api_base=config.api_base,
+                deployment=config.deployment,
+                disallowed_special=(),
+            ),
+            chunk_size,
+        )  # type: ignore
 
 
 COHERE_VECTOR_SIZE = 1024
@@ -167,7 +179,13 @@ def __init__(self, config: OpenAICompatibleEmbeddingConfigModel):
         self.config = config
         # Client is set internally
         # Always set an API key even if there is none defined in the config because the validator will fail otherwise. Embedding APIs that don't require an API key don't fail if one is provided, so this is not breaking usage.
-        self.embeddings = LocalAIEmbeddings(model=config.model_name, openai_api_key=config.api_key or "dummy-api-key", openai_api_base=config.base_url, max_retries=15, disallowed_special=())  # type: ignore
+        self.embeddings = LocalAIEmbeddings(
+            model=config.model_name,
+            openai_api_key=config.api_key or "dummy-api-key",
+            openai_api_base=config.base_url,
+            max_retries=15,
+            disallowed_special=(),
+        )  # type: ignore
 
     def check(self) -> Optional[str]:
         deployment_mode = os.environ.get("DEPLOYMENT_MODE", "")
@@ -254,7 +272,6 @@ def create_from_config(
     ],
     processing_config: ProcessingConfigModel,
 ) -> Embedder:
-
     if embedding_config.mode == "azure_openai" or embedding_config.mode == "openai":
         return cast(Embedder, embedder_map[embedding_config.mode](embedding_config, processing_config.chunk_size))
     else:

airbyte_cdk/models/airbyte_protocol.py

@@ -62,9 +62,9 @@ class AirbyteGlobalState:
 class AirbyteStateMessage:
     type: Optional[AirbyteStateType] = None  # type: ignore [name-defined]
     stream: Optional[AirbyteStreamState] = None
-    global_: Annotated[
-        AirbyteGlobalState | None, Alias("global")
-    ] = None  # "global" is a reserved keyword in python ⇒ Alias is used for (de-)serialization
+    global_: Annotated[AirbyteGlobalState | None, Alias("global")] = (
+        None  # "global" is a reserved keyword in python ⇒ Alias is used for (de-)serialization
+    )
     data: Optional[Dict[str, Any]] = None
     sourceStats: Optional[AirbyteStateStats] = None  # type: ignore [name-defined]
     destinationStats: Optional[AirbyteStateStats] = None  # type: ignore [name-defined]

airbyte_cdk/sources/connector_state_manager.py

@@ -113,7 +113,8 @@ def _extract_from_state_message(
         else:
             streams = {
                 HashableStreamDescriptor(
-                    name=per_stream_state.stream.stream_descriptor.name, namespace=per_stream_state.stream.stream_descriptor.namespace  # type: ignore[union-attr] # stream has stream_descriptor
+                    name=per_stream_state.stream.stream_descriptor.name,
+                    namespace=per_stream_state.stream.stream_descriptor.namespace,  # type: ignore[union-attr] # stream has stream_descriptor
                 ): per_stream_state.stream.stream_state  # type: ignore[union-attr] # stream has stream_state
                 for per_stream_state in state
                 if per_stream_state.type == AirbyteStateType.STREAM and hasattr(per_stream_state, "stream")  # type: ignore # state is always a list of AirbyteStateMessage if is_per_stream is True