Correct linting issues

pyproject.toml

@@ -149,11 +149,7 @@ warn_unreachable = true
 warn_unused_ignores = true
 
 [[tool.mypy.overrides]]
-module = "haystack"
-ignore_missing_imports = true
-
-[[tool.mypy.overrides]]
-module = "haystack.dataclasses"
+module = "haystack.*"
 ignore_missing_imports = true
 
 [tool.mypy-sortedcollections]

scripts/update_version_for_prerelease.py

@@ -31,8 +31,10 @@
 
     # We can only transform a stable release version (X.Y.Z) to a prerelease version (X.Y.ZxxxN)
     if not re.match(r"^\d+\.\d+\.\d+$", current_version):
-        raise RuntimeError(f"The current version {current_version} does not match the proper semver format for "
-                           f"stable releases (X.Y.Z)")
+        raise RuntimeError(
+            f"The current version {current_version} does not match the proper semver format for "
+            f"stable releases (X.Y.Z)"
+        )
 
     # Load the version numbers of the currently published versions from PyPI
     published_versions = get_published_package_versions()

src/apify_haystack/__init__.py

@@ -2,6 +2,6 @@
 
 __version__ = metadata.version("apify-haystack")
 
-from apify_haystack.apify_dataset import ApifyDatasetLoader
+from apify_haystack.apify_dataset import ApifyDatasetFromActorCall, ApifyDatasetLoader
 
-__all__ = ["ApifyDatasetLoader"]
+__all__ = ["ApifyDatasetLoader", "ApifyDatasetFromActorCall", "ApifyDatasetFromActorCall"]

src/apify_haystack/apify_dataset.py

@@ -52,10 +52,11 @@ def __init__(
             httpx_client.headers["user-agent"] += f"; {HAYSTACK_ATTRIBUTE_USER_AGENT}"
 
     @component.output_types(documents=list[Document])
-    def run(self):  # type: ignore[no-untyped-def]
+    def run(self):  # type: ignore[no-untyped-def] # noqa: ANN201
         """Load datasets produced by the `Apify Actors`.
 
-        Type-hint note: the output is not type-hinted, otherwise linting complains that `run` method is a component
+        Type-hint note: the output is not type-hinted, otherwise linting complains
+        that `run` method is not haystack a component
         """
         dataset_items = self.client.dataset(self.dataset_id).list_items(clean=True).items
         return {"documents": list(map(self.dataset_mapping_function, dataset_items))}
@@ -84,8 +85,7 @@ def __init__(
         timeout_secs: int | None = None,
         apify_api_token: str | None = None,
     ) -> None:
-        """
-        Initialize the Apify Actor loader.
+        """Initialize the Apify Actor loader.
 
         Args:
             actor_id (str): The ID or name of the Actor on the Apify platform.
@@ -119,10 +119,11 @@ def __init__(
             httpx_client.headers["user-agent"] += f"; {HAYSTACK_ATTRIBUTE_USER_AGENT}"
 
     @component.output_types(documents=list[Document])
-    def run(self):  # type: ignore[no-untyped-def]
+    def run(self):  # type: ignore[no-untyped-def] # noqa: ANN201
         """Run an Actor on the Apify platform and wait for results to be ready.
 
-        Type-hint note: the output is not type-hinted, otherwise linting complains that `run` method is a component
+        Type-hint note: the output is not type-hinted, otherwise linting complains
+        that `run` method is not haystack a component
         """
         if not (
             actor_call := self.client.actor(self.actor_id).call(
@@ -155,19 +156,18 @@ def __init__(
         self,
         task_id: str,
         dataset_mapping_function: Callable[[dict], Document],
-        run_input: dict,
+        task_input: dict,
         *,
         build: str | None = None,
         memory_mbytes: int | None = None,
         timeout_secs: int | None = None,
         apify_api_token: str | None = None,
     ) -> None:
-        """
-        Initialize the Apify Actor loader.
+        """Initialize the Apify Actor loader.
 
         Args:
             task_id (str): The ID or name of the Actor on the Apify platform.
-            run_input (Dict): The input object of the Actor that you're trying to run.
+            task_input (Dict): The input object of the Actor that you're trying to run.
             dataset_mapping_function (Callable): A function that takes a single
                 dictionary (an Apify dataset item) and converts it to an
                 instance of the Document class.
@@ -180,7 +180,7 @@ def __init__(
         """
         self.task_id = task_id
         self.dataset_mapping_function = dataset_mapping_function
-        self.run_input = run_input
+        self.task_input = task_input
         self.build = build
         self.memory_mbytes = memory_mbytes
         self.timeout_secs = timeout_secs
@@ -197,14 +197,15 @@ def __init__(
             httpx_client.headers["user-agent"] += f"; {HAYSTACK_ATTRIBUTE_USER_AGENT}"
 
     @component.output_types(documents=list[Document])
-    def run(self):  # type: ignore[no-untyped-def]
+    def run(self):  # type: ignore[no-untyped-def] # noqa: ANN201
         """Run an Actor on the Apify platform and wait for results to be ready.
 
-        Type-hint note: the output is not type-hinted, otherwise linting complains that `run` method is a component
+        Type-hint note: the output is not type-hinted, otherwise linting complains
+        that `run` method is not haystack a component
         """
         if not (
             actor_call := self.client.task(self.task_id).call(
-                run_input=self.run_input,
+                task_input=self.task_input,
                 build=self.build,
                 memory_mbytes=self.memory_mbytes,
                 timeout_secs=self.timeout_secs,

src/apify_haystack/constants.py

@@ -1,3 +1,2 @@
-
 # A custom user-agent for attribution and monitoring purposes
 HAYSTACK_ATTRIBUTE_USER_AGENT = "Origin/haystack"

src/apify_haystack/examples/apify_actor_call.py

@@ -1,11 +1,11 @@
 """
 Call Apify Actor and load a dataset to convert it to Haystack Documents.
 
-This script demonstrates how to use Apify's Website Content Crawler to scrape text content from a specified website and convert the
-scraped data into Haystack Documents.
+This script demonstrates how to use Apify's Website Content Crawler to scrape text content from a specified website
+and convert the scraped data into Haystack Documents.
 
-For example, if you want to crawl and get text content from https://haystack.deepset.ai/, you can use this script to call the Apify actor
-and retrieve the data in a structured format.
+For example, if you want to crawl and get text content from https://haystack.deepset.ai/, you can use this script
+to call the Apify actor and retrieve the data in a structured format.
 
 The script should produce the following output (an example of a single Document):
 ......
@@ -17,7 +17,7 @@
 from dotenv import load_dotenv
 from haystack import Document
 
-from apify_dataset import ApifyDatasetFromActorCall
+from apify_haystack import ApifyDatasetFromActorCall
 
 # Sey APIFY-API-TOKEN here or load it from .env file
 apify_token = "" or load_dotenv()

src/apify_haystack/examples/crawl_and_process_data.py

@@ -21,7 +21,7 @@
 from haystack.components.writers import DocumentWriter
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 
-from apify_dataset import ApifyDatasetFromActorCall
+from apify_haystack import ApifyDatasetFromActorCall
 
 # Sey APIFY-API-TOKEN here or load it from .env file
 apify_token = "" or load_dotenv()

src/apify_haystack/examples/rag_with_crawled_website.py

@@ -29,7 +29,7 @@
 from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 
-from apify_dataset import ApifyDatasetFromActorCall
+from apify_haystack import ApifyDatasetFromActorCall
 
 # Load OPENAI_API_KEY and APIFY_API_TOKEN from .env file
 load_dotenv()