Add ruff rules for unused arguments (#574)

Author: cbornet

libs/colbert/ragstack_colbert/colbert_embedding_model.py

@@ -43,7 +43,6 @@ def __init__(
         query_maxlen: Optional[int] = None,
         verbose: Optional[int] = 3,  # 3 is the default on ColBERT checkpoint
         chunk_batch_size: Optional[int] = 640,
-        **kwargs,
     ):
         """
         Initializes a new instance of the ColbertEmbeddingModel class, setting up the

libs/colbert/ragstack_colbert/colbert_retriever.py

@@ -16,6 +16,7 @@
 from typing import Any, Dict, List, Optional, Set, Tuple
 
 import torch
+from typing_extensions import override
 
 from .base_database import BaseDatabase
 from .base_embedding_model import BaseEmbeddingModel
@@ -271,6 +272,7 @@ async def _get_chunk_data(
 
         return results
 
+    @override
     async def atext_search(
         self,
         query_text: str,
@@ -310,6 +312,7 @@ async def atext_search(
             **kwargs,
         )
 
+    @override
     async def aembedding_search(
         self,
         query_embedding: Embedding,
@@ -322,10 +325,9 @@ async def aembedding_search(
         using semantic similarity as the criteria.
 
         Parameters:
-            query_text (str): The query text to search for relevant text chunks.
-            k (Optional[int]): The number of top results to retrieve. Default 5.
-            query_maxlen (Optional[int]): The maximum length of the query to consider.
-                If None, the maxlen will be dynamically generated.
+            query_embedding (Embedding): The query embedding to search for relevant
+                text chunks.
+            k (Optional[int]): The number of top results to retrieve.
             include_embedding (Optional[bool]): Optional (default False) flag to include
                 the embedding vectors in the returned chunks
             **kwargs (Any): Additional parameters that implementations might require
@@ -373,6 +375,7 @@ async def aembedding_search(
 
         return [(chunk, chunk_scores[chunk]) for chunk in chunks]
 
+    @override
     def text_search(
         self,
         query_text: str,
@@ -407,9 +410,11 @@ def text_search(
                 k=k,
                 query_maxlen=query_maxlen,
                 include_embedding=include_embedding,
+                **kwargs,
             )
         )
 
+    @override
     def embedding_search(
         self,
         query_embedding: Embedding,

libs/colbert/tests/integration_tests/conftest.py

@@ -20,7 +20,7 @@ def get_astradb_test_store():
 
 
 @pytest.hookimpl()
-def pytest_sessionfinish(session, exitstatus):
+def pytest_sessionfinish():
     if (
         status["local_cassandra_test_store"]
         and status["local_cassandra_test_store"].docker_container

libs/e2e-tests/e2e_tests/conftest.py

@@ -161,7 +161,7 @@ def set_current_test_info(test_name: str, test_info: str):
 
 
 @pytest.hookimpl()
-def pytest_sessionfinish(session, exitstatus):
+def pytest_sessionfinish():
     logging.info("All tests report:")
     logging.info("\n".join(all_report_lines))
     logging.info("Failed tests report:")

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

@@ -1,6 +1,7 @@
 import uuid
 
 import cassio
+import pytest
 from langchain import hub
 from langchain.agents import AgentExecutor, create_openai_tools_agent
 from langchain_community.tools.cassandra_database.tool import (
@@ -12,7 +13,8 @@
 from langchain_openai import ChatOpenAI
 
 
-def test_tool_with_openai_tool(cassandra):
+@pytest.mark.usefixtures("cassandra")
+def test_tool_with_openai_tool():
     session = cassio.config.resolve_session()
     session.execute("DROP TABLE IF EXISTS default_keyspace.tool_table_users;")
 

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

@@ -20,6 +20,7 @@
     ChatOpenAI,
     OpenAIEmbeddings,
 )
+from typing_extensions import override
 from vertexai.vision_models import Image, MultiModalEmbeddingModel
 
 from e2e_tests.conftest import (
@@ -415,9 +416,11 @@ def test_multimodal(vector_store, embedding, llm, request, record_property):
     resolved_embedding, embedding_size = request.getfixturevalue(embedding)
 
     class FakeEmbeddings(Embeddings):
+        @override
         def embed_documents(self, texts: List[str]) -> List[List[float]]:
             return [[0.0] * embedding_size] * len(texts)
 
+        @override
         def embed_query(self, text: str) -> List[float]:
             return [0.0] * embedding_size
 

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

@@ -128,12 +128,10 @@ def test_wrong_connection_parameters(environment: Environment):
             )
 
 
-def verify_document(document, expected_content, expected_metadata):
+def verify_document(document, expected_content):
     if isinstance(document, NodeWithScore):
         document = document.node
         assert document.text == expected_content
-        # metadata is not returned by LlamaIndex
-        # assert document.metadata == expected_metadata
     else:
         raise TypeError(
             "document is not of type NodeWithScore but of type " + str(type(document))
@@ -185,7 +183,6 @@ def test_vector_search_with_metadata(environment: Environment):
     verify_document(
         documents[0],
         "RAGStack is a framework to run LangChain in production",
-        {"id": "http://mywebsite/intro", "source": "website", "context": "homepage"},
     )
 
     documents = index.as_retriever().retrieve("RAGStack")

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

@@ -1,6 +1,7 @@
 import uuid
 
 import cassio
+import pytest
 from llama_index.agent.openai import OpenAIAgent
 from llama_index.llms.openai import OpenAI
 from llama_index.tools.cassandra.base import CassandraDatabaseToolSpec
@@ -9,7 +10,8 @@
 )
 
 
-def test_tool_with_openai_tool(cassandra):
+@pytest.mark.usefixtures("cassandra")
+def test_tool_with_openai_tool():
     session = cassio.config.resolve_session()
     session.execute("DROP TABLE IF EXISTS default_keyspace.tool_table_users;")
 

libs/knowledge-graph/ragstack_knowledge_graph/cassandra_graph_store.py

@@ -6,6 +6,7 @@
 from langchain_community.graphs.graph_store import GraphStore
 from langchain_core.embeddings import Embeddings
 from langchain_core.runnables import Runnable, RunnableLambda
+from typing_extensions import override
 
 from .knowledge_graph import CassandraKnowledgeGraph
 from .traverse import Node, Relation
@@ -47,24 +48,29 @@ def __init__(
             keyspace=keyspace,
         )
 
+    @override
     def add_graph_documents(
         self, graph_documents: List[GraphDocument], include_source: bool = False
     ) -> None:
         # TODO: Include source.
         self.graph.insert(_elements(graph_documents))
 
     # TODO: should this include the types of each node?
+    @override
     def query(self, query: str, params: dict = {}) -> List[Dict[str, Any]]:  # noqa: B006
         raise ValueError("Querying Cassandra should use `as_runnable`.")
 
+    @override
     @property
     def get_schema(self) -> str:
         raise NotImplementedError
 
     @property
+    @override
     def get_structured_schema(self) -> Dict[str, Any]:
         raise NotImplementedError
 
+    @override
     def refresh_schema(self) -> None:
         raise NotImplementedError
 

libs/langchain/ragstack_langchain/colbert/colbert_retriever.py

@@ -7,6 +7,7 @@
 from langchain_core.documents import Document
 from langchain_core.retrievers import BaseRetriever
 from ragstack_colbert.base_retriever import BaseRetriever as ColbertBaseRetriever
+from typing_extensions import override
 
 if TYPE_CHECKING:
     from ragstack_colbert import Chunk
@@ -47,6 +48,7 @@ def __init__(
         self.k = k
         self.query_maxlen = query_maxlen
 
+    @override
     def _get_relevant_documents(
         self,
         query: str,
@@ -69,6 +71,7 @@ def _get_relevant_documents(
             for (c, _) in chunk_scores
         ]
 
+    @override
     async def _aget_relevant_documents(
         self,
         query: str,