chore: enforce kwarg logging

haystack/__init__.py

@@ -1,9 +1,9 @@
+import haystack.logging
 from haystack.core.component import component
 from haystack.core.errors import ComponentError, DeserializationError
 from haystack.core.pipeline import Pipeline, PredefinedPipeline
 from haystack.core.serialization import default_from_dict, default_to_dict
 from haystack.dataclasses import Answer, Document, ExtractedAnswer, GeneratedAnswer
-import haystack.logging
 
 # Initialize the logging configuration
 # This is a no-op unless `structlog` is installed

haystack/components/audio/whisper_local.py

@@ -1,10 +1,8 @@
-from typing import List, Optional, Dict, Any, Union, Literal, get_args
-
-import logging
 import tempfile
 from pathlib import Path
+from typing import Any, Dict, List, Literal, Optional, Union, get_args
 
-from haystack import component, Document, default_to_dict, ComponentError, default_from_dict
+from haystack import ComponentError, Document, component, default_from_dict, default_to_dict, logging
 from haystack.dataclasses import ByteStream
 from haystack.lazy_imports import LazyImport
 from haystack.utils import ComponentDevice

haystack/components/audio/whisper_remote.py

@@ -1,11 +1,10 @@
 import io
-import logging
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
 from openai import OpenAI
 
-from haystack import Document, component, default_from_dict, default_to_dict
+from haystack import Document, component, default_from_dict, default_to_dict, logging
 from haystack.dataclasses import ByteStream
 from haystack.utils import Secret, deserialize_secrets_inplace
 

haystack/components/builders/__init__.py

@@ -1,6 +1,6 @@
 from haystack.components.builders.answer_builder import AnswerBuilder
-from haystack.components.builders.prompt_builder import PromptBuilder
-from haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder
 from haystack.components.builders.dynamic_chat_prompt_builder import DynamicChatPromptBuilder
+from haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder
+from haystack.components.builders.prompt_builder import PromptBuilder
 
 __all__ = ["AnswerBuilder", "PromptBuilder", "DynamicPromptBuilder", "DynamicChatPromptBuilder"]

haystack/components/builders/answer_builder.py

@@ -1,9 +1,7 @@
-import logging
 import re
-from typing import List, Dict, Any, Optional
-
-from haystack import component, GeneratedAnswer, Document
+from typing import Any, Dict, List, Optional
 
+from haystack import Document, GeneratedAnswer, component, logging
 
 logger = logging.getLogger(__name__)
 
@@ -114,7 +112,9 @@ def run(
                     try:
                         referenced_docs.append(documents[idx])
                     except IndexError:
-                        logger.warning("Document index '%s' referenced in Generator output is out of range. ", idx + 1)
+                        logger.warning(
+                            "Document index '{index}' referenced in Generator output is out of range. ", index=idx + 1
+                        )
 
             answer_string = AnswerBuilder._extract_answer_string(reply, pattern)
             answer = GeneratedAnswer(data=answer_string, query=query, documents=referenced_docs, meta=metadata)

haystack/components/builders/dynamic_chat_prompt_builder.py

@@ -1,9 +1,8 @@
-import logging
-from typing import Dict, Any, Optional, List, Set
+from typing import Any, Dict, List, Optional, Set
 
 from jinja2 import Template, meta
 
-from haystack import component
+from haystack import component, logging
 from haystack.dataclasses.chat_message import ChatMessage, ChatRole
 
 logger = logging.getLogger(__name__)

haystack/components/builders/dynamic_prompt_builder.py

@@ -1,9 +1,8 @@
-import logging
-from typing import Dict, Any, Optional, List, Set
+from typing import Any, Dict, List, Optional, Set
 
 from jinja2 import Template, meta
 
-from haystack import component
+from haystack import component, logging
 
 logger = logging.getLogger(__name__)
 

haystack/components/caching/cache_checker.py

@@ -1,13 +1,9 @@
-from typing import List, Dict, Any
-
 import importlib
+from typing import Any, Dict, List
 
-import logging
-
-from haystack import component, Document, default_from_dict, default_to_dict, DeserializationError
+from haystack import DeserializationError, Document, component, default_from_dict, default_to_dict, logging
 from haystack.document_stores.types import DocumentStore
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -80,7 +76,7 @@ def from_dict(cls, data: Dict[str, Any]) -> "CacheChecker":
 
         try:
             module_name, type_ = init_params["document_store"]["type"].rsplit(".", 1)
-            logger.debug("Trying to import %s", module_name)
+            logger.debug("Trying to import module '{module}'", module=module_name)
             module = importlib.import_module(module_name)
         except (ImportError, DeserializationError) as e:
             raise DeserializationError(

haystack/components/classifiers/document_language_classifier.py

@@ -1,7 +1,6 @@
-import logging
-from typing import List, Dict, Optional
+from typing import Dict, List, Optional
 
-from haystack import component, Document
+from haystack import Document, component, logging
 from haystack.lazy_imports import LazyImport
 
 logger = logging.getLogger(__name__)
@@ -96,6 +95,8 @@ def _detect_language(self, document: Document) -> Optional[str]:
         try:
             language = langdetect.detect(document.content)
         except langdetect.LangDetectException:
-            logger.warning("Langdetect cannot detect the language of Document with id: %s", document.id)
+            logger.warning(
+                "Langdetect cannot detect the language of Document with id: {document_id}", document_id=document.id
+            )
             language = None
         return language

haystack/components/connectors/openapi_service.py

@@ -1,10 +1,9 @@
 import json
-import logging
 from collections import defaultdict
 from copy import copy
-from typing import List, Dict, Any, Optional, Union
+from typing import Any, Dict, List, Optional, Union
 
-from haystack import component
+from haystack import component, logging
 from haystack.dataclasses import ChatMessage, ChatRole
 from haystack.lazy_imports import LazyImport
 
@@ -179,7 +178,7 @@ def _invoke_method(self, openapi_service: OpenAPI, method_invocation_descriptor:
         :rtype: Any
         :raises RuntimeError: If the method is not found or invocation fails.
         """
-        name = method_invocation_descriptor.get("name", None)
+        name = method_invocation_descriptor.get("name")
         invocation_arguments = copy(method_invocation_descriptor.get("arguments", {}))
         if not name or not invocation_arguments:
             raise ValueError(

haystack/components/converters/__init__.py

@@ -1,11 +1,11 @@
-from haystack.components.converters.txt import TextFileToDocument
-from haystack.components.converters.tika import TikaDocumentConverter
 from haystack.components.converters.azure import AzureOCRDocumentConverter
-from haystack.components.converters.pypdf import PyPDFToDocument
 from haystack.components.converters.html import HTMLToDocument
 from haystack.components.converters.markdown import MarkdownToDocument
 from haystack.components.converters.openapi_functions import OpenAPIServiceToFunctions
 from haystack.components.converters.output_adapter import OutputAdapter
+from haystack.components.converters.pypdf import PyPDFToDocument
+from haystack.components.converters.tika import TikaDocumentConverter
+from haystack.components.converters.txt import TextFileToDocument
 
 __all__ = [
     "TextFileToDocument",

haystack/components/converters/azure.py

@@ -1,17 +1,16 @@
 from pathlib import Path
-from typing import List, Union, Dict, Any, Optional
-import logging
+from typing import Any, Dict, List, Optional, Union
 
-from haystack.lazy_imports import LazyImport
-from haystack import component, Document, default_to_dict, default_from_dict
-from haystack.dataclasses import ByteStream
+from haystack import Document, component, default_from_dict, default_to_dict, logging
 from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
+from haystack.dataclasses import ByteStream
+from haystack.lazy_imports import LazyImport
 from haystack.utils import Secret, deserialize_secrets_inplace
 
 logger = logging.getLogger(__name__)
 
 with LazyImport(message="Run 'pip install \"azure-ai-formrecognizer>=3.2.0b2\"'") as azure_import:
-    from azure.ai.formrecognizer import DocumentAnalysisClient, AnalyzeResult
+    from azure.ai.formrecognizer import AnalyzeResult, DocumentAnalysisClient
     from azure.core.credentials import AzureKeyCredential
 
 
@@ -83,7 +82,7 @@ def run(self, sources: List[Union[str, Path, ByteStream]], meta: Optional[List[D
             try:
                 bytestream = get_bytestream_from_source(source=source)
             except Exception as e:
-                logger.warning("Could not read %s. Skipping it. Error: %s", source, e)
+                logger.warning("Could not read {source}. Skipping it. Error: {error}", source=source, error=e)
                 continue
 
             poller = self.document_analysis_client.begin_analyze_document(

haystack/components/converters/html.py

@@ -1,11 +1,11 @@
-import logging
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Union, Literal
+from typing import Any, Dict, List, Literal, Optional, Union
+
 from boilerpy3 import extractors
 
-from haystack import Document, component, default_from_dict, default_to_dict
-from haystack.dataclasses import ByteStream
+from haystack import Document, component, default_from_dict, default_to_dict, logging
 from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
+from haystack.dataclasses import ByteStream
 
 logger = logging.getLogger(__name__)
 
@@ -84,13 +84,17 @@ def run(
             try:
                 bytestream = get_bytestream_from_source(source=source)
             except Exception as e:
-                logger.warning("Could not read %s. Skipping it. Error: %s", source, e)
+                logger.warning("Could not read {source}. Skipping it. Error: {error}", source=source, error=e)
                 continue
             try:
                 file_content = bytestream.data.decode("utf-8")
                 text = extractor.get_content(file_content)
             except Exception as conversion_e:
-                logger.warning("Failed to extract text from %s. Skipping it. Error: %s", source, conversion_e)
+                logger.warning(
+                    "Failed to extract text from {source}. Skipping it. Error: {error}",
+                    source=source,
+                    error=conversion_e,
+                )
                 continue
 
             merged_metadata = {**bytestream.meta, **metadata}

haystack/components/converters/markdown.py

@@ -1,13 +1,12 @@
-import logging
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
 from tqdm import tqdm
 
-from haystack import Document, component
+from haystack import Document, component, logging
+from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
 from haystack.dataclasses import ByteStream
 from haystack.lazy_imports import LazyImport
-from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
 
 with LazyImport("Run 'pip install markdown-it-py mdit_plain'") as markdown_conversion_imports:
     from markdown_it import MarkdownIt
@@ -77,13 +76,17 @@ def run(
             try:
                 bytestream = get_bytestream_from_source(source)
             except Exception as e:
-                logger.warning("Could not read %s. Skipping it. Error: %s", source, e)
+                logger.warning("Could not read {source}. Skipping it. Error: {error}", source=source, error=e)
                 continue
             try:
                 file_content = bytestream.data.decode("utf-8")
                 text = parser.render(file_content)
             except Exception as conversion_e:
-                logger.warning("Failed to extract text from %s. Skipping it. Error: %s", source, conversion_e)
+                logger.warning(
+                    "Failed to extract text from {source}. Skipping it. Error: {error}",
+                    source=source,
+                    error=conversion_e,
+                )
                 continue
 
             merged_metadata = {**bytestream.meta, **metadata}

haystack/components/converters/openapi_functions.py

@@ -1,14 +1,13 @@
 import json
-import logging
 import os
 from pathlib import Path
-from typing import List, Dict, Any, Union, Optional
+from typing import Any, Dict, List, Optional, Union
 
 import requests
 import yaml
 from requests import RequestException
 
-from haystack import component, Document
+from haystack import Document, component, logging
 from haystack.dataclasses.byte_stream import ByteStream
 from haystack.lazy_imports import LazyImport
 
@@ -80,7 +79,9 @@ def run(
             elif isinstance(source, ByteStream):
                 openapi_spec_content = source.data.decode("utf-8")
             else:
-                logger.warning("Invalid source type %s. Only str, Path, and ByteStream are supported.", type(source))
+                logger.warning(
+                    "Invalid source type {source}. Only str, Path, and ByteStream are supported.", source=type(source)
+                )
                 continue
 
             if openapi_spec_content:
@@ -94,7 +95,9 @@ def run(
                         doc = Document(content=json.dumps(function), meta=meta)
                         documents.append(doc)
                 except Exception as e:
-                    logger.error("Error processing OpenAPI specification from source %s: %s", source, e)
+                    logger.error(
+                        "Error processing OpenAPI specification from source {source}: {error}", source=source, error=e
+                    )
 
         return {"documents": documents}
 
@@ -167,7 +170,9 @@ def _parse_endpoint_spec(self, resolved_spec: Dict[str, Any]) -> Optional[Dict[s
         if function_name and description and schema["properties"]:
             return {"name": function_name, "description": description, "parameters": schema}
         else:
-            logger.warning("Invalid OpenAPI spec format provided. Could not extract function from %s", resolved_spec)
+            logger.warning(
+                "Invalid OpenAPI spec format provided. Could not extract function from {spec}", spec=resolved_spec
+            )
             return {}
 
     def _parse_property_attributes(
@@ -246,7 +251,7 @@ def _read_from_file(self, path: Union[str, Path]) -> Optional[str]:
             with open(path, "r") as f:
                 return f.read()
         except IOError as e:
-            logger.warning("IO error reading file: %s. Error: %s", path, e)
+            logger.warning("IO error reading file: {path}. Error: {error}", path=path, error=e)
             return None
 
     def _read_from_url(self, url: str) -> Optional[str]:
@@ -261,5 +266,5 @@ def _read_from_url(self, url: str) -> Optional[str]:
             response.raise_for_status()
             return response.text
         except RequestException as e:
-            logger.warning("Error fetching URL: %s. Error: %s", url, e)
+            logger.warning("Error fetching URL: {url}. Error: {error}", url=url, error=e)
             return None

haystack/components/converters/output_adapter.py

@@ -1,12 +1,12 @@
-from typing import Optional, Dict, Any, Set, Callable
+from typing import Any, Callable, Dict, Optional, Set
 
 import jinja2.runtime
 from jinja2 import TemplateSyntaxError, meta
 from jinja2.nativetypes import NativeEnvironment
 from typing_extensions import TypeAlias
 
-from haystack import component, default_to_dict, default_from_dict
-from haystack.utils import serialize_callable, deserialize_callable, serialize_type, deserialize_type
+from haystack import component, default_from_dict, default_to_dict
+from haystack.utils import deserialize_callable, deserialize_type, serialize_callable, serialize_type
 
 
 class OutputAdaptationException(Exception):

haystack/components/converters/pypdf.py

@@ -1,12 +1,11 @@
 import io
-import logging
-from typing import List, Union, Protocol, Dict, Any, Optional
 from pathlib import Path
+from typing import Any, Dict, List, Optional, Protocol, Union
 
+from haystack import Document, component, default_to_dict, logging
+from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
 from haystack.dataclasses import ByteStream
 from haystack.lazy_imports import LazyImport
-from haystack import Document, component, default_to_dict
-from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
 
 with LazyImport("Run 'pip install pypdf'") as pypdf_import:
     from pypdf import PdfReader
@@ -105,13 +104,15 @@ def run(
             try:
                 bytestream = get_bytestream_from_source(source)
             except Exception as e:
-                logger.warning("Could not read %s. Skipping it. Error: %s", source, e)
+                logger.warning("Could not read {source}. Skipping it. Error: {error}", source=source, error=e)
                 continue
             try:
                 pdf_reader = PdfReader(io.BytesIO(bytestream.data))
                 document = self._converter.convert(pdf_reader)
             except Exception as e:
-                logger.warning("Could not read %s and convert it to Document, skipping. %s", source, e)
+                logger.warning(
+                    "Could not read {source} and convert it to Document, skipping. {error}", source=source, error=e
+                )
                 continue
 
             merged_metadata = {**bytestream.meta, **metadata}