Add various ruff rules (#562)

libs/colbert/ragstack_colbert/cassandra_database.py

@@ -435,4 +435,3 @@ def close(self) -> None:
         """
         Cleans up any open resources.
         """
-        pass

libs/colbert/ragstack_colbert/colbert_retriever.py

@@ -166,7 +166,6 @@ def close(self) -> None:
         """
         Closes any open resources held by the retriever.
         """
-        pass
 
     async def _query_relevant_chunks(
         self, query_embedding: Embedding, top_k: int

libs/e2e-tests/e2e_tests/langchain/test_astra.py

@@ -81,7 +81,6 @@ def test_wrong_connection_parameters(vectorstore: AstraDBVectorStore):
         pytest.fail("Should have thrown exception")
     except ConnectError as e:
         print("Error:", e)
-        pass
 
     # This is expected to be a valid endpoint,
     # because we want to test an AUTHENTICATION error

libs/e2e-tests/e2e_tests/langchain/test_unstructured.py

@@ -1,3 +1,5 @@
+from typing import TYPE_CHECKING
+
 import pytest
 from langchain.text_splitter import TokenTextSplitter
 from langchain_community.document_loaders import UnstructuredAPIFileLoader
@@ -15,9 +17,9 @@
 )
 from e2e_tests.langchain.rag_application import BASIC_QA_PROMPT
 from e2e_tests.test_utils import get_local_resource_path
-from e2e_tests.test_utils.vector_store_handler import (
-    VectorStoreTestContext,
-)
+
+if TYPE_CHECKING:
+    from e2e_tests.test_utils.vector_store_handler import VectorStoreTestContext
 
 
 @pytest.mark.parametrize("vector_store", ["cassandra", "astra_db"])

libs/e2e-tests/e2e_tests/llama_index/test_astra.py

@@ -106,7 +106,6 @@ def test_wrong_connection_parameters(environment: Environment):
         pytest.fail("Should have thrown exception")
     except ConnectError as e:
         print("Error:", e)
-        pass
 
     # This is expected to be a valid endpoint,
     # because we want to test an AUTHENTICATION error

libs/e2e-tests/e2e_tests/llama_index/test_compatibility_rag.py

@@ -1,4 +1,5 @@
 import logging
+from typing import TYPE_CHECKING
 
 import pytest
 from langchain.embeddings import HuggingFaceInferenceAPIEmbeddings
@@ -27,9 +28,9 @@
     set_current_test_info,
 )
 from e2e_tests.test_utils import get_local_resource_path
-from e2e_tests.test_utils.vector_store_handler import (
-    VectorStoreTestContext,
-)
+
+if TYPE_CHECKING:
+    from e2e_tests.test_utils.vector_store_handler import VectorStoreTestContext
 
 
 def _openai_llm(**kwargs) -> OpenAI:

libs/e2e-tests/e2e_tests/llama_index/test_llama_parse.py

@@ -6,6 +6,8 @@
     pytest.skip("llama_parse is not supported, skipping tests", allow_module_level=True)
 
 
+from typing import TYPE_CHECKING
+
 from llama_index.core import ServiceContext, StorageContext, VectorStoreIndex
 from llama_index.embeddings.openai import OpenAIEmbedding
 from llama_index.llms.openai import OpenAI
@@ -15,9 +17,9 @@
     set_current_test_info,
 )
 from e2e_tests.test_utils import get_local_resource_path
-from e2e_tests.test_utils.vector_store_handler import (
-    VectorStoreTestContext,
-)
+
+if TYPE_CHECKING:
+    from e2e_tests.test_utils.vector_store_handler import VectorStoreTestContext
 
 
 @pytest.fixture

libs/knowledge-store/ragstack_knowledge_store/graph_store.py

@@ -416,7 +416,7 @@ def mmr_traversal_search(
         # Select the best item, K times.
         depths = {id: 0 for id in helper.candidate_ids()}
         visited_tags = set()
-        for _ in range(0, k):
+        for _ in range(k):
             selected_id = helper.pop_best()
 
             if selected_id is None:

libs/langchain/ragstack_langchain/colbert/colbert_retriever.py

@@ -1,14 +1,16 @@
-from typing import Any, List, Optional, Tuple
+from typing import TYPE_CHECKING, Any, List, Optional, Tuple
 
 from langchain_core.callbacks.manager import (
     AsyncCallbackManagerForRetrieverRun,
     CallbackManagerForRetrieverRun,
 )
 from langchain_core.documents import Document
 from langchain_core.retrievers import BaseRetriever
-from ragstack_colbert import Chunk
 from ragstack_colbert.base_retriever import BaseRetriever as ColbertBaseRetriever
 
+if TYPE_CHECKING:
+    from ragstack_colbert import Chunk
+
 
 class ColbertRetriever(BaseRetriever):
     """Chain for langchain retrieve using ColBERT vector store.

libs/langchain/ragstack_langchain/graph_store/base.py

@@ -2,6 +2,7 @@
 
 from abc import abstractmethod
 from typing import (
+    TYPE_CHECKING,
     Any,
     AsyncIterable,
     ClassVar,
@@ -13,10 +14,6 @@
     Set,
 )
 
-from langchain_core.callbacks import (
-    AsyncCallbackManagerForRetrieverRun,
-    CallbackManagerForRetrieverRun,
-)
 from langchain_core.documents import Document
 from langchain_core.load import Serializable
 from langchain_core.pydantic_v1 import Field
@@ -25,6 +22,12 @@
 
 from ragstack_langchain.graph_store.links import METADATA_LINKS_KEY, Link
 
+if TYPE_CHECKING:
+    from langchain_core.callbacks import (
+        AsyncCallbackManagerForRetrieverRun,
+        CallbackManagerForRetrieverRun,
+    )
+
 
 def _has_next(iterator: Iterator) -> bool:
     """Checks if the iterator has more elements.

libs/langchain/ragstack_langchain/graph_store/extractors/link_extractor.py

@@ -1,9 +1,10 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
-from typing import Generic, Iterable, Set, TypeVar
+from typing import TYPE_CHECKING, Generic, Iterable, Set, TypeVar
 
-from ragstack_langchain.graph_store.links import Link
+if TYPE_CHECKING:
+    from ragstack_langchain.graph_store.links import Link
 
 InputT = TypeVar("InputT")
 

libs/llamaindex/ragstack_llamaindex/colbert/colbert_retriever.py

@@ -1,12 +1,14 @@
-from typing import Any, List, Optional, Tuple
+from typing import TYPE_CHECKING, Any, List, Optional, Tuple
 
 from llama_index.core.callbacks.base import CallbackManager
 from llama_index.core.constants import DEFAULT_SIMILARITY_TOP_K
 from llama_index.core.retrievers import BaseRetriever
 from llama_index.core.schema import NodeWithScore, QueryBundle, TextNode
-from ragstack_colbert import Chunk
 from ragstack_colbert.base_retriever import BaseRetriever as ColbertBaseRetriever
 
+if TYPE_CHECKING:
+    from ragstack_colbert import Chunk
+
 
 class ColbertRetriever(BaseRetriever):
     """ColBERT vector store retriever.

libs/ragulate/ragstack_ragulate/analysis.py

@@ -252,4 +252,4 @@ def compare(self, recipes: List[str], output: str):
         elif output == "histogram-grid":
             self.output_histograms_by_dataset(df=df, metrics=metrics)
         else:
-            raise ValueError()
+            raise ValueError

libs/ragulate/ragstack_ragulate/pipelines/base_pipeline.py

@@ -59,7 +59,6 @@ class BasePipeline(ABC):
     @abstractmethod
     def pipeline_type(self):
         """type of pipeline (ingest, query, cleanup)"""
-        pass
 
     @property
     @abstractmethod

pyproject.toml

@@ -59,6 +59,9 @@ extend-include = ["*.ipynb"]
 
 [tool.ruff.lint]
 ignore = [
+    "COM812", # Messes with the formatter
+    "ERA", # Do we want to activate (no commented code) ?
+    "ISC001", # Messes with the formatter
     "PERF203", # Incorrect detection
     "TRY003", # A bit too strict ?
 ]
@@ -67,20 +70,34 @@ select = [
     "ASYNC",
     "B",
     "C4",
+    "COM",
+    "DTZ",
     "E",
+    "EXE",
     "F",
     "FLY",
     "FURB",
     "I",
+    "ICN",
+    "INT",
+    "ISC",
+    "LOG",
     "N",
     "NPY",
     "PERF",
+    "PIE",
     "PGH",
+    "Q",
+    "RSE",
     "RUF",
     "SIM",
+    "SLOT",
+    "T10",
+    "TCH",
     "TRY",
     "UP",
     "W",
+    "YTT",
 ]
 
 [tool.ruff.lint.per-file-ignores]

scripts/format-example-notebooks.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 import json
 import os
 

scripts/generate-changelog.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 try:
     import requests
 except ImportError:

scripts/generate-testspace-report.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 import json
 import os.path
 import sys

scripts/parse-snyk-report.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 import json
 import sys