fix: Linting issues

pyproject.toml

@@ -157,17 +157,15 @@ select = [
 fixable = ["ALL"]
 ignore = [
     "D100",   # Missing docstring in public module
+    "D101",   # Missing docstring in public class
+    "D102",   # Missing docstring in public method
     "D104",   # Missing docstring in public package
+    "D103",   # Missing docstring in public function
+    "D106",   # Missing docstring in public nested class
     "ANN101", # Missing type annotation for self
     "ANN102", # Missing type annotation for cls
 ]
 
-[tool.ruff.lint.per-file-ignores]
-"test_*.py" = [
-    "ANN201", # Missing return type annotation for public function
-    "D103",   # Missing docstring in public function
-]
-
 [tool.ruff.format]
 quote-style = "double"
 indent-style = "space"

src/unstract/sdk/adapter.py

@@ -1,9 +1,8 @@
 import json
-from typing import Any, Optional
+from typing import Any
 
 import requests
 from requests.exceptions import ConnectionError, HTTPError
-
 from unstract.sdk.adapters.utils import AdapterUtils
 from unstract.sdk.constants import AdapterKeys, LogLevel, ToolEnv
 from unstract.sdk.exceptions import SdkError
@@ -25,8 +24,7 @@ def __init__(
         platform_host: str,
         platform_port: str,
     ) -> None:
-        """
-        Args:
+        """Args:
             tool (AbstractTool): Instance of AbstractTool
             platform_host (str): Host of platform service
             platform_port (str): Port of platform service
@@ -89,7 +87,7 @@ def _get_adapter_configuration(
     @staticmethod
     def get_adapter_config(
         tool: BaseTool, adapter_instance_id: str
-    ) -> Optional[dict[str, Any]]:
+    ) -> dict[str, Any] | None:
         """Get adapter spec by the help of unstract DB tool.
 
         This method first checks if the adapter_instance_id matches

src/unstract/sdk/adapters/adapterkit.py

@@ -2,7 +2,6 @@
 from typing import Any
 
 from singleton_decorator import singleton
-
 from unstract.sdk.adapters import AdapterDict
 from unstract.sdk.adapters.base import Adapter
 from unstract.sdk.adapters.constants import Common
@@ -34,16 +33,14 @@ def adapters(self) -> AdapterDict:
 
     def get_adapter_class_by_adapter_id(self, adapter_id: str) -> Adapter:
         if adapter_id in self._adapters:
-            adapter_class: Adapter = self._adapters[adapter_id][
-                Common.METADATA
-            ][Common.ADAPTER]
+            adapter_class: Adapter = self._adapters[adapter_id][Common.METADATA][
+                Common.ADAPTER
+            ]
             return adapter_class
         else:
             raise RuntimeError(f"Couldn't obtain adapter for {adapter_id}")
 
-    def get_adapter_by_id(
-        self, adapter_id: str, *args: Any, **kwargs: Any
-    ) -> Adapter:
+    def get_adapter_by_id(self, adapter_id: str, *args: Any, **kwargs: Any) -> Adapter:
         """Instantiates and returns a adapter.
 
         Args:
@@ -55,17 +52,13 @@ def get_adapter_by_id(
         Returns:
             Adapter: Concrete impl of the `Adapter` base
         """
-        adapter_class: Adapter = self.get_adapter_class_by_adapter_id(
-            adapter_id
-        )
+        adapter_class: Adapter = self.get_adapter_class_by_adapter_id(adapter_id)
         return adapter_class(*args, **kwargs)
 
     def get_adapters_list(self) -> list[dict[str, Any]]:
         adapters = []
         for adapter_id, adapter_registry_metadata in self._adapters.items():
-            m: Adapter = adapter_registry_metadata[Common.METADATA][
-                Common.ADAPTER
-            ]
+            m: Adapter = adapter_registry_metadata[Common.METADATA][Common.ADAPTER]
             _id = m.get_id()
             name = m.get_name()
             adapter_type = m.get_adapter_type().name

src/unstract/sdk/adapters/embedding/azure_open_ai/src/azure_open_ai.py

@@ -4,7 +4,6 @@
 import httpx
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 from unstract.sdk.adapters.exceptions import AdapterError
@@ -71,5 +70,3 @@ def get_embedding_instance(self) -> BaseEmbedding:
             return embedding
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/embedding/bedrock/src/bedrock.py

@@ -3,11 +3,11 @@
 
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.bedrock import BedrockEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 from unstract.sdk.adapters.exceptions import AdapterError
 
+
 class Constants:
     MODEL = "model"
     TIMEOUT = "timeout"
@@ -18,6 +18,7 @@ class Constants:
     DEFAULT_TIMEOUT = 240
     DEFAULT_MAX_RETRIES = 3
 
+
 class Bedrock(EmbeddingAdapter):
     def __init__(self, settings: dict[str, Any]):
         super().__init__("Bedrock")
@@ -66,5 +67,3 @@ def get_embedding_instance(self) -> BaseEmbedding:
             return embedding
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/embedding/embedding_adapter.py

@@ -3,11 +3,10 @@
 
 from llama_index.core import MockEmbedding
 from llama_index.core.embeddings import BaseEmbedding
-
 from unstract.sdk.adapters.base import Adapter
+from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 from unstract.sdk.adapters.enums import AdapterTypes
 
-from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 
 class EmbeddingAdapter(Adapter, ABC):
     def __init__(self, name: str):
@@ -47,8 +46,8 @@ def get_embedding_instance(self, embed_config: dict[str, Any]) -> BaseEmbedding:
             Raises exceptions for any error
         """
         return MockEmbedding(embed_dim=1)
-    
+
     def test_connection(self) -> bool:
         embedding = self.get_embedding_instance()
         test_result: bool = EmbeddingHelper.test_embedding_instance(embedding)
-        return test_result
+        return test_result

src/unstract/sdk/adapters/embedding/helper.py

@@ -1,8 +1,7 @@
 import logging
-from typing import Any, Optional
+from typing import Any
 
 from llama_index.core.embeddings import BaseEmbedding
-
 from unstract.sdk.adapters.exceptions import AdapterError
 
 logger = logging.getLogger(__name__)
@@ -28,7 +27,7 @@ def get_embedding_batch_size(config: dict[str, Any]) -> int:
         return embedding_batch_size
 
     @staticmethod
-    def test_embedding_instance(embedding: Optional[BaseEmbedding]) -> bool:
+    def test_embedding_instance(embedding: BaseEmbedding | None) -> bool:
         try:
             if embedding is None:
                 return False

src/unstract/sdk/adapters/embedding/hugging_face/src/hugging_face.py

@@ -1,9 +1,8 @@
 import os
-from typing import Any, Optional
+from typing import Any
 
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 from unstract.sdk.adapters.exceptions import AdapterError
@@ -45,7 +44,7 @@ def get_embedding_instance(self) -> BaseEmbedding:
             embedding_batch_size = EmbeddingHelper.get_embedding_batch_size(
                 config=self.config
             )
-            max_length: Optional[int] = (
+            max_length: int | None = (
                 int(self.config.get(Constants.MAX_LENGTH, 0))
                 if self.config.get(Constants.MAX_LENGTH)
                 else None
@@ -61,5 +60,3 @@ def get_embedding_instance(self) -> BaseEmbedding:
             return embedding
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/embedding/ollama/src/ollama.py

@@ -3,7 +3,6 @@
 
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.ollama import OllamaEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 from unstract.sdk.adapters.exceptions import AdapterError
@@ -55,5 +54,3 @@ def get_embedding_instance(self) -> BaseEmbedding:
             return embedding
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/embedding/open_ai/src/open_ai.py

@@ -4,7 +4,6 @@
 import httpx
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.openai import OpenAIEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.exceptions import AdapterError
 
@@ -66,5 +65,3 @@ def get_embedding_instance(self) -> BaseEmbedding:
             return embedding
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/embedding/palm/src/palm.py

@@ -3,7 +3,6 @@
 
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.google import GooglePaLMEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 from unstract.sdk.adapters.exceptions import AdapterError
@@ -55,5 +54,3 @@ def get_embedding_instance(self) -> BaseEmbedding:
             return embedding
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/embedding/qdrant_fast_embed/src/qdrant_fast_embed.py

@@ -3,7 +3,6 @@
 
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.fastembed import FastEmbedEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.exceptions import AdapterError
 
@@ -44,5 +43,3 @@ def get_embedding_instance(self) -> BaseEmbedding:
             return embedding
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/embedding/vertex_ai/src/vertex_ai.py

@@ -4,21 +4,21 @@
 
 from google.auth.transport import requests as google_requests
 from google.oauth2.service_account import Credentials
-
 from llama_index.core.embeddings import BaseEmbedding
 from llama_index.embeddings.vertex import VertexTextEmbedding
-
 from unstract.sdk.adapters.embedding.embedding_adapter import EmbeddingAdapter
 from unstract.sdk.adapters.embedding.helper import EmbeddingHelper
 from unstract.sdk.adapters.exceptions import AdapterError
 from unstract.sdk.exceptions import EmbeddingError
 
+
 class Constants:
     MODEL = "model"
     PROJECT = "project"
     JSON_CREDENTIALS = "json_credentials"
     EMBED_MODE = "embed_mode"
 
+
 class VertexAIEmbedding(EmbeddingAdapter):
     def __init__(self, settings: dict[str, Any]):
         super().__init__("Bedrock")
@@ -45,7 +45,7 @@ def get_provider() -> str:
     @staticmethod
     def get_icon() -> str:
         return "/icons/adapter-icons/VertexAI.png"
-    
+
     def get_embedding_instance(self) -> BaseEmbedding:
         try:
             embedding_batch_size = EmbeddingHelper.get_embedding_batch_size(
@@ -69,11 +69,9 @@ def get_embedding_instance(self) -> BaseEmbedding:
             )
             return embedding
         except json.JSONDecodeError:
-                raise EmbeddingError(
-                    "Credentials is not a valid service account JSON, "
-                    "please provide a valid JSON."
-                )
+            raise EmbeddingError(
+                "Credentials is not a valid service account JSON, "
+                "please provide a valid JSON."
+            )
         except Exception as e:
             raise AdapterError(str(e))
-
-

src/unstract/sdk/adapters/llm/anthropic/src/anthropic.py

@@ -5,7 +5,6 @@
 from llama_index.core.llms import LLM
 from llama_index.llms.anthropic import Anthropic
 from llama_index.llms.anthropic.base import DEFAULT_ANTHROPIC_MAX_TOKENS
-
 from unstract.sdk.adapters.exceptions import AdapterError
 from unstract.sdk.adapters.llm.constants import LLMKeys
 from unstract.sdk.adapters.llm.llm_adapter import LLMAdapter
@@ -23,6 +22,7 @@ class Constants:
     ENABLE_THINKING = "enable_thinking"
     BUDGET_TOKENS = "budget_tokens"
 
+
 class AnthropicLLM(LLMAdapter):
     def __init__(self, settings: dict[str, Any]):
         super().__init__("Anthropic")
@@ -63,7 +63,7 @@ def get_llm_instance(self) -> LLM:
             budget_tokens = self.config.get(Constants.BUDGET_TOKENS)
             thinking_dict = {"type": "enabled", "budget_tokens": budget_tokens}
             temperature = 1
-            
+
         try:
             llm: LLM = Anthropic(
                 model=str(self.config.get(Constants.MODEL)),
@@ -76,7 +76,7 @@ def get_llm_instance(self) -> LLM:
                 ),
                 temperature=temperature,
                 max_tokens=max_tokens,
-                thinking_dict=thinking_dict
+                thinking_dict=thinking_dict,
             )
             return llm
         except Exception as e:

src/unstract/sdk/adapters/llm/bedrock/src/bedrock.py

@@ -1,9 +1,8 @@
 import os
-from typing import Any, Optional
+from typing import Any
 
 from llama_index.core.llms import LLM
 from llama_index.llms.bedrock import Bedrock
-
 from unstract.sdk.adapters.exceptions import AdapterError
 from unstract.sdk.adapters.llm.constants import LLMKeys
 from unstract.sdk.adapters.llm.llm_adapter import LLMAdapter
@@ -47,11 +46,11 @@ def get_provider() -> str:
 
     @staticmethod
     def get_icon() -> str:
-        return "/icons/adapter-icons/Bedrock.png"  
+        return "/icons/adapter-icons/Bedrock.png"
 
     def get_llm_instance(self) -> LLM:
         try:
-            context_size: Optional[int] = (
+            context_size: int | None = (
                 int(self.config.get(Constants.CONTEXT_SIZE, 0))
                 if self.config.get(Constants.CONTEXT_SIZE)
                 else None
@@ -76,4 +75,4 @@ def get_llm_instance(self) -> LLM:
             )
             return llm
         except Exception as e:
-            raise AdapterError(str(e))
+            raise AdapterError(str(e))