Add ruff-specific rules (RUF) (#558)

cbornet · web-flow · commit bdd1be27cc55 · 2024-07-03T02:55:29.000+02:00
diff --git a/examples/evaluation/langchain_trulens_full.ipynb b/examples/evaluation/langchain_trulens_full.ipynb
@@ -455,7 +455,8 @@
     "\n",
     "# note that token & cost data collection is currently broken with AzureOpenAI\n",
     "\n",
-    "columns_to_keep = feedback_columns + [\n",
+    "columns_to_keep = [\n",
+    "    *feedback_columns,\n",
     "    \"record_id\",\n",
     "    \"input\",\n",
     "    \"output\",\n",
@@ -490,7 +491,7 @@
     "import numpy as np\n",
     "import pandas as pd\n",
     "\n",
-    "tests = feedback_columns + [\"latency\", \"total_tokens\", \"total_cost\"]\n",
+    "tests = [*feedback_columns, \"latency\", \"total_tokens\", \"total_cost\"]\n",
     "\n",
     "results = pd.DataFrame(\n",
     "    columns=[\"records\", \"mean\", \"median\", \"95th_percentile\", \"99th_percentile\"]\n",
diff --git a/examples/evaluation/tru_download.py b/examples/evaluation/tru_download.py
@@ -10,7 +10,8 @@
     print(f"Downloading data for {app_id}...")
     df_records, feedback_columns = tru.get_records_and_feedback([app_id])
 
-    columns_to_keep = feedback_columns + [
+    columns_to_keep = [
+        *feedback_columns,
         "record_id",
         "input",
         "output",
diff --git a/examples/notebooks/advancedRAG.ipynb b/examples/notebooks/advancedRAG.ipynb
@@ -222,7 +222,7 @@
     "Context: {context}\n",
     "Question: {question}\n",
     "Your answer:\n",
-    "\"\"\"  # noqa: E501\n",
+    "\"\"\"\n",
     "prompt = ChatPromptTemplate.from_template(prompt_template)\n",
     "\n",
     "questions = [\n",
diff --git a/examples/notebooks/astradb.ipynb b/examples/notebooks/astradb.ipynb
@@ -521,7 +521,7 @@
     "\n",
     "QUESTION: {question}\n",
     "\n",
-    "YOUR ANSWER:\"\"\"  # noqa: E501\n",
+    "YOUR ANSWER:\"\"\"\n",
     "\n",
     "philo_prompt = ChatPromptTemplate.from_template(philo_template)\n",
     "\n",
diff --git a/examples/notebooks/conftest.py b/examples/notebooks/conftest.py
@@ -30,7 +30,7 @@ def try_delete_with_backoff(collection: str, sleep=1, max_tries=2):
     try:
         logging.info(f"deleting collection {collection}")
         response = client.delete_collection(collection)
-        logging.info(f"delete collection {collection} response: {str(response)}")
+        logging.info(f"delete collection {collection} response: {response!s}")
     except Exception as e:
         max_tries -= 1
         if max_tries < 0:
diff --git a/examples/notebooks/langchain_evaluation.ipynb b/examples/notebooks/langchain_evaluation.ipynb
@@ -318,7 +318,7 @@
     "Context: {context}\n",
     "Question: {question}\n",
     "Your answer:\n",
-    "\"\"\"  # noqa: E501\n",
+    "\"\"\"\n",
     "prompt = ChatPromptTemplate.from_template(prompt_template)\n",
     "model = ChatOpenAI()\n",
     "\n",
@@ -408,13 +408,13 @@
     "    \"What motivates the narrator, Montresor, to seek revenge against Fortunato?\",\n",
     "    \"What are the major themes in this story?\",\n",
     "    \"What is the significance of the story taking place during the carnival season?\",\n",
-    "    \"What literary techniques does Poe use to create suspense and tension in the story?\",  # noqa: E501\n",
+    "    \"What literary techniques does Poe use to create suspense and tension in the story?\",\n",
     "]\n",
     "\n",
     "eval_answers = [\n",
     "    \"Montresor is insulted by Lenora and seeks revenge.\",  # Incorrect Answer\n",
     "    \"The major themes are happiness and trustworthiness.\",  # Incorrect Answer\n",
-    "    \"The carnival season is a time of celebration and merriment, which contrasts with the sinister events of the story.\",  # noqa: E501\n",
+    "    \"The carnival season is a time of celebration and merriment, which contrasts with the sinister events of the story.\",\n",
     "    \"Poe uses foreshadowing, irony, and symbolism to create suspense and tension.\",\n",
     "]\n",
     "\n",
diff --git a/libs/e2e-tests/e2e_tests/langchain/test_astra.py b/libs/e2e-tests/e2e_tests/langchain/test_astra.py
@@ -193,7 +193,7 @@ def test_basic_metadata_filtering_no_vector(vectorstore: AstraDBVectorStore):
         else:
             pytest.fail(
                 f"Should have thrown ValueError with UNSUPPORTED_FILTER_OPERATION "
-                f"but it was {e}"  # noqa: E501
+                f"but it was {e}"
             )
 
 
diff --git a/libs/e2e-tests/e2e_tests/langchain/test_compatibility_rag.py b/libs/e2e-tests/e2e_tests/langchain/test_compatibility_rag.py
@@ -499,4 +499,4 @@ def test_chat(chat, request, record_property):
         record_langsmith_sharelink(run_id, record_property)
         assert "Syracuse" in str(
             response.content
-        ), f"Expected Syracuse in the answer but got: {str(response.content)}"
+        ), f"Expected Syracuse in the answer but got: {response.content!s}"
diff --git a/libs/e2e-tests/e2e_tests/test_utils/astradb_vector_store_handler.py b/libs/e2e-tests/e2e_tests/test_utils/astradb_vector_store_handler.py
@@ -229,7 +229,7 @@ def try_delete_with_backoff(collection: str, sleep=1, max_tries=5):
         response = AstraDBVectorStoreHandler.default_astra_client.delete_collection(
             collection
         )
-        logging.info(f"delete collection {collection} response: {str(response)}")
+        logging.info(f"delete collection {collection} response: {response!s}")
     except Exception as e:
         max_tries -= 1
         if max_tries < 0:
diff --git a/libs/knowledge-graph/ragstack_knowledge_graph/traverse.py b/libs/knowledge-graph/ragstack_knowledge_graph/traverse.py
@@ -6,10 +6,19 @@
 from cassio.config import check_resolve_keyspace, check_resolve_session
 
 
-class Node(NamedTuple):
+class _Node(NamedTuple):
     name: str
     type: str
-    properties: Dict[str, Any] = {}
+    properties: Dict[str, Any]
+
+
+class Node(_Node):
+    __slots__ = ()
+
+    def __new__(cls, name, type, properties=None):
+        if properties is None:
+            properties = {}
+        return super().__new__(cls, name, type, properties)
 
     def __repr__(self):
         return f"{self.name} ({self.type})"
@@ -64,7 +73,7 @@ def _prepare_edge_query(
         WHERE {edge_source_name} = ?
         AND {edge_source_type} = ?"""
     if edge_filters:
-        query = "\n        AND ".join([query] + edge_filters)
+        query = "\n        AND ".join([query, *edge_filters])
     return session.prepare(query)
 
 
diff --git a/libs/knowledge-store/ragstack_knowledge_store/graph_store.py b/libs/knowledge-store/ragstack_knowledge_store/graph_store.py
@@ -276,7 +276,7 @@ def _apply_schema(self):
             CREATE CUSTOM INDEX IF NOT EXISTS {self._node_table}_text_embedding_index
             ON {self._keyspace}.{self._node_table}(text_embedding)
             USING 'StorageAttachedIndex';
-        """)  # noqa: E501
+        """)
 
         # Index on target_text_embedding (for similarity search)
         self._session.execute(f"""
@@ -291,7 +291,7 @@ def _concurrent_queries(self) -> ConcurrentQueries:
     # TODO: Async (aadd_nodes)
     def add_nodes(
         self,
-        nodes: Iterable[Node] = None,
+        nodes: Iterable[Node],
     ) -> Iterable[str]:
         node_ids = []
         texts = []
diff --git a/libs/langchain/ragstack_langchain/colbert/colbert_retriever.py b/libs/langchain/ragstack_langchain/colbert/colbert_retriever.py
@@ -49,7 +49,7 @@ def _get_relevant_documents(
         self,
         query: str,
         *,
-        run_manager: CallbackManagerForRetrieverRun,  # noqa
+        run_manager: CallbackManagerForRetrieverRun,
     ) -> List[Document]:
         """Get documents relevant to a query.
         Args:
@@ -71,7 +71,7 @@ async def _aget_relevant_documents(
         self,
         query: str,
         *,
-        run_manager: AsyncCallbackManagerForRetrieverRun,  # noqa
+        run_manager: AsyncCallbackManagerForRetrieverRun,
     ) -> List[Document]:
         """Asynchronously get documents relevant to a query.
         Args:
diff --git a/libs/langchain/tests/unit_tests/test_gliner_link_extractor.py b/libs/langchain/tests/unit_tests/test_gliner_link_extractor.py
@@ -2,8 +2,8 @@
 from ragstack_langchain.graph_store.links import Link
 
 PAGE_1 = """
-Cristiano Ronaldo dos Santos Aveiro (Portuguese pronunciation: [kɾiʃˈtjɐnu
-ʁɔˈnaldu]; born 5 February 1985) is a Portuguese professional footballer who
+Cristiano Ronaldo dos Santos Aveiro (Portuguese pronunciation: [kɾiʃ'tjɐnu
+ʁɔ'naldu]; born 5 February 1985) is a Portuguese professional footballer who
 plays as a forward for and captains both Saudi Pro League club Al Nassr and the
 Portugal national team. Widely regarded as one of the greatest players of all
 time, Ronaldo has won five Ballon d'Or awards,[note 3] a record three UEFA Men's
diff --git a/libs/ragulate/ragstack_ragulate/analysis.py b/libs/ragulate/ragstack_ragulate/analysis.py
@@ -25,7 +25,8 @@ def get_all_data(self, recipes: List[str]) -> DataFrame:
                 df, metrics = tru.get_records_and_feedback([dataset])
                 all_metrics.extend(metrics)
 
-                columns_to_keep = metrics + [
+                columns_to_keep = [
+                    *metrics,
                     "record_id",
                     "latency",
                     "total_tokens",
diff --git a/libs/ragulate/ragstack_ragulate/pipelines/query_pipeline.py b/libs/ragulate/ragstack_ragulate/pipelines/query_pipeline.py
@@ -30,8 +30,8 @@ class QueryPipeline(BasePipeline):
     _tru: Tru
     _name: str
     _progress: tqdm
-    _queries: Dict[str, List[str]] = {}
-    _golden_sets: Dict[str, List[Dict[str, str]]] = {}
+    _queries: Dict[str, List[str]]
+    _golden_sets: Dict[str, List[Dict[str, str]]]
     _total_queries: int = 0
     _total_feedbacks: int = 0
     _finished_feedbacks: int = 0
@@ -60,6 +60,8 @@ def __init__(
         model_name: Optional[str] = None,
         **kwargs,
     ):
+        self._queries = {}
+        self._golden_sets = {}
         super().__init__(
             recipe_name=recipe_name,
             script_path=script_path,
diff --git a/libs/tests-utils/ragstack_tests_utils/test_data.py b/libs/tests-utils/ragstack_tests_utils/test_data.py
@@ -71,7 +71,7 @@ def nebula_voyager_text() -> str:
             - What challenges does the Quantum Opacity phenomenon present to the crew of
               the Nebula Voyager?
             - How does the Bioquantum Array aid Dr. Nyx Moreau in studying the
-              Nebuloforms within Orion’s Whisper?
+              Nebuloforms within Orion's Whisper?
             - What are Xenospheric Particulates?
             - What is the significance of the Cryptolingual Synthesizer used by Jiro
               Takashi, and how does it function?
diff --git a/pyproject.toml b/pyproject.toml
@@ -73,6 +73,7 @@ select = [
     "N",
     "NPY",
     "PERF",
+    "RUF",
     "SIM",
     "UP",
     "W",
diff --git a/scripts/generate-changelog.py b/scripts/generate-changelog.py
@@ -58,7 +58,7 @@ def main():
                 break
         if package_name in IMPORTANT_DEPENDENCIES:
             if package_name == "langchain":
-                version_range = f"https://datastax.github.io/ragstack-ai/api_reference/{package_version}/langchain[{version_range}]{{external-link-icon}}"  # noqa
+                version_range = f"https://datastax.github.io/ragstack-ai/api_reference/{package_version}/langchain[{version_range}]{{external-link-icon}}"
             extra_str = f" (via extra `{extra}`)" if extra else ""
             deps_str += f"\n| {package_name}{extra_str}\n| {version_range}\n"
 

Original file line number	Diff line number	Diff line change
`@@ -193,7 +193,7 @@ def test_basic_metadata_filtering_no_vector(vectorstore: AstraDBVectorStore):`
`193`	`193`	`else:`
`194`	`194`	`pytest.fail(`
`195`	`195`	`f"Should have thrown ValueError with UNSUPPORTED_FILTER_OPERATION "`
`196`		`- f"but it was {e}" # noqa: E501`
	`196`	`+ f"but it was {e}"`
`197`	`197`	`)`
`198`	`198`
`199`	`199`
Original file line number	Diff line number	Diff line change
`@@ -229,7 +229,7 @@ def try_delete_with_backoff(collection: str, sleep=1, max_tries=5):`
`229`	`229`	`response = AstraDBVectorStoreHandler.default_astra_client.delete_collection(`
`230`	`230`	`collection`
`231`	`231`	`)`
`232`		`- logging.info(f"delete collection {collection} response: {str(response)}")`
	`232`	`+ logging.info(f"delete collection {collection} response: {response!s}")`
`233`	`233`	`except Exception as e:`
`234`	`234`	`max_tries -= 1`
`235`	`235`	`if max_tries < 0:`