ref: Add ruff rules for perf (PERF) (#4047)

Add ruff rules for perf (PERF)

src/backend/base/langflow/base/vectorstores/utils.py

@@ -18,7 +18,6 @@ def chroma_collection_to_data(collection_dict: dict):
             "text": doc,
         }
         if ("metadatas" in collection_dict) and collection_dict["metadatas"][i]:
-            for key, value in collection_dict["metadatas"][i].items():
-                data_dict[key] = value
+            data_dict.update(collection_dict["metadatas"][i].items())
         data.append(Data(**data_dict))
     return data

src/backend/base/langflow/components/deactivated/SplitText.py

@@ -45,18 +45,12 @@ class SplitTextComponent(Component):
     ]
 
     def _docs_to_data(self, docs):
-        data = []
-        for doc in docs:
-            data.append(Data(text=doc.page_content, data=doc.metadata))
-        return data
+        return [Data(text=doc.page_content, data=doc.metadata) for doc in docs]
 
     def split_text(self) -> list[Data]:
         separator = unescape_string(self.separator)
 
-        documents = []
-        for _input in self.data_inputs:
-            if isinstance(_input, Data):
-                documents.append(_input.to_lc_document())
+        documents = [_input.to_lc_document() for _input in self.data_inputs if isinstance(_input, Data)]
 
         splitter = CharacterTextSplitter(
             chunk_overlap=self.chunk_overlap,

src/backend/base/langflow/components/helpers/CSVtoData.py

@@ -69,10 +69,8 @@ class CSVToDataComponent(Component):
                 msg = "No CSV data provided."
                 raise ValueError(msg)
 
-            result = []
             csv_reader = csv.DictReader(io.StringIO(csv_data))
-            for row in csv_reader:
-                result.append(Data(data=row))
+            result = [Data(data=row) for row in csv_reader]
 
             if not result:
                 self.status = "The CSV data is empty."

src/backend/base/langflow/components/helpers/SplitText.py

@@ -45,18 +45,12 @@ class SplitTextComponent(Component):
     ]
 
     def _docs_to_data(self, docs):
-        data = []
-        for doc in docs:
-            data.append(Data(text=doc.page_content, data=doc.metadata))
-        return data
+        return [Data(text=doc.page_content, data=doc.metadata) for doc in docs]
 
     def split_text(self) -> list[Data]:
         separator = unescape_string(self.separator)
 
-        documents = []
-        for _input in self.data_inputs:
-            if isinstance(_input, Data):
-                documents.append(_input.to_lc_document())
+        documents = [_input.to_lc_document() for _input in self.data_inputs if isinstance(_input, Data)]
 
         splitter = CharacterTextSplitter(
             chunk_overlap=self.chunk_overlap,

src/backend/base/langflow/components/prompts/LangChainHubPrompt.py

@@ -51,9 +51,7 @@ class LangChainHubPromptComponent(Component):
             template_messages = [HumanMessagePromptTemplate(prompt=template)]
 
         # Extract the messages from the prompt data
-        prompt_template = []
-        for message_data in template_messages:
-            prompt_template.append(message_data.prompt)
+        prompt_template = [message_data.prompt for message_data in template_messages]
 
         # Regular expression to find all instances of {<string>}
         pattern = r"\{(.*?)\}"
@@ -77,7 +75,7 @@ class LangChainHubPromptComponent(Component):
         build_config["langchain_hub_prompt"]["info"] = full_template
 
         # Remove old parameter inputs if any
-        for key, _ in build_config.copy().items():
+        for key in build_config.copy():
             if key.startswith("param_"):
                 del build_config[key]
 

src/backend/base/langflow/components/tools/GleanSearchAPI.py

@@ -138,10 +138,7 @@ class GleanSearchAPIComponent(LCToolComponent):
         )
 
         # Build the data
-        data = []
-        for result in results:
-            data.append(Data(data=result, text=result["snippets"][0]["text"]))
-
+        data = [Data(data=result, text=result["snippets"][0]["text"]) for result in results]
         self.status = data
 
         return data

src/backend/base/langflow/components/tools/PythonCodeStructuredTool.py

@@ -292,13 +292,12 @@ class PythonCodeStructuredTool(LCToolComponent):
         return classes, functions
 
     def _find_imports(self, code: str) -> dotdict:
-        imports = []
+        imports: list[str] = []
         from_imports = []
         parsed_code = ast.parse(code)
         for node in parsed_code.body:
             if isinstance(node, ast.Import):
-                for alias in node.names:
-                    imports.append(alias.name)
+                imports.extend(alias.name for alias in node.names)
             elif isinstance(node, ast.ImportFrom):
                 from_imports.append(node)
         return dotdict({"imports": imports, "from_imports": from_imports})

src/backend/base/langflow/components/tools/SearXNGTool.py

@@ -70,9 +70,7 @@ class SearXNGToolComponent(LCToolComponent):
             for selected_category in build_config["categories"]["value"]:
                 if selected_category not in build_config["categories"]["options"]:
                     build_config["categories"]["value"].remove(selected_category)
-            languages = []
-            for language in data["locales"]:
-                languages.append(language)
+            languages = list(data["locales"])
             build_config["language"]["options"] = languages.copy()
         except Exception as e:
             self.status = f"Failed to extract names: {e}"
@@ -107,11 +105,8 @@ class SearXNGToolComponent(LCToolComponent):
                         },
                     ).json()
 
-                    results = []
                     num_results = min(SearxSearch._max_results, len(response["results"]))
-                    for i in range(num_results):
-                        results.append(response["results"][i])
-                    return results
+                    return [response["results"][i] for i in range(num_results)]
                 except Exception as e:
                     return [f"Failed to search: {e}"]
 

src/backend/base/langflow/custom/code_parser/code_parser.py

@@ -389,8 +389,7 @@ class CodeParser:
         bases = []
         for base in dunder_class.__bases__:
             bases.append(base)
-            for bases_base in base.__bases__:
-                bases.append(bases_base)
+            bases.extend(base.__bases__)
         return bases
 
     def parse_code(self) -> dict[str, Any]:

src/backend/base/langflow/custom/custom_component/component.py

@@ -404,11 +404,13 @@ class Component(CustomComponent):
         # Get the input object from the current component
         input_ = self._inputs[input_name]
         # Iterate over outputs to find matches based on types
-        for output in outputs:
-            for output_type in output.types:
-                # Check if the output type matches the input's accepted types
-                if input_.input_types and output_type in input_.input_types:
-                    matching_pairs.append((output, input_))
+        matching_pairs = [
+            (output, input_)
+            for output in outputs
+            for output_type in output.types
+            # Check if the output type matches the input's accepted types
+            if input_.input_types and output_type in input_.input_types
+        ]
         # If multiple matches are found, raise an error indicating ambiguity
         if len(matching_pairs) > 1:
             matching_pairs_str = self._build_error_string_from_matching_pairs(matching_pairs)
@@ -593,7 +595,7 @@ class Component(CustomComponent):
         #! works and then update this later
         field_config = self.get_template_config(self)
         frontend_node = ComponentFrontendNode.from_inputs(**field_config)
-        for key, _value in self._inputs.items():
+        for key in self._inputs:
             frontend_node.set_field_load_from_db_in_template(key, False)
         self._map_parameters_on_frontend_node(frontend_node)
 

src/backend/base/langflow/custom/utils.py

@@ -64,9 +64,7 @@ def reorder_fields(frontend_node: CustomComponentFrontendNode, field_order: list
     field_dict = {field.name: field for field in frontend_node.template.fields}
     reordered_fields = [field_dict[name] for name in field_order if name in field_dict]
     # Add any fields that are not in the field_order list
-    for field in frontend_node.template.fields:
-        if field.name not in field_order:
-            reordered_fields.append(field)
+    reordered_fields.extend(field for field in frontend_node.template.fields if field.name not in field_order)
     frontend_node.template.fields = reordered_fields
     frontend_node.field_order = field_order
 

src/backend/base/langflow/graph/graph/utils.py

@@ -118,7 +118,7 @@ def update_template(template, g_nodes):
     Returns:
         None
     """
-    for _, value in template.items():
+    for value in template.values():
         if not value.get("proxy"):
             continue
         proxy_dict = value["proxy"]

src/backend/base/langflow/helpers/flow.py

@@ -228,11 +228,7 @@ def get_flow_inputs(graph: Graph) -> list[Vertex]:
     Returns:
         List[Data]: A list of input data, where each record contains the ID, name, and description of the input vertex.
     """
-    inputs = []
-    for vertex in graph.vertices:
-        if vertex.is_input:
-            inputs.append(vertex)
-    return inputs
+    return [vertex for vertex in graph.vertices if vertex.is_input]
 
 
 def build_schema_from_inputs(name: str, inputs: list[Vertex]) -> type[BaseModel]:

src/backend/base/langflow/logging/logger.py

@@ -98,10 +98,7 @@ class SizedLogBuffer:
         try:
             with self._wlock:
                 as_list = list(self.buffer)
-            rc = {}
-            for ts, msg in as_list[-last_idx:]:
-                rc[ts] = msg
-            return rc
+            return dict(as_list[-last_idx:])
         finally:
             self._rsemaphore.release()
 

src/backend/base/langflow/memory.py

@@ -66,9 +66,7 @@ def add_messages(messages: Message | list[Message], flow_id: str | None = None):
             msg = f"The messages must be instances of Message. Found: {types}"
             raise ValueError(msg)
 
-        messages_models: list[MessageTable] = []
-        for msg in messages:
-            messages_models.append(MessageTable.from_message(msg, flow_id=flow_id))
+        messages_models = [MessageTable.from_message(msg, flow_id=flow_id) for msg in messages]
         with session_scope() as session:
             messages_models = add_messagetables(messages_models, session)
         return [Message(**message.model_dump()) for message in messages_models]

src/backend/base/langflow/services/factory.py

@@ -74,10 +74,13 @@ def import_all_services_into_a_dict():
             service_name = ServiceType(service_type).value.replace("_service", "")
             module_name = f"langflow.services.{service_name}.service"
             module = importlib.import_module(module_name)
-            for name, obj in inspect.getmembers(module, inspect.isclass):
-                if issubclass(obj, Service) and obj is not Service:
-                    services[name] = obj
-                    # break
+            services.update(
+                {
+                    name: obj
+                    for name, obj in inspect.getmembers(module, inspect.isclass)
+                    if issubclass(obj, Service) and obj is not Service
+                }
+            )
         except Exception as exc:
             logger.exception(exc)
             msg = "Could not initialize services. Please check your settings."

src/backend/base/pyproject.toml

@@ -62,6 +62,7 @@ select = [
     "LOG",
     "NPY",
     "PD",
+    "PERF",
     "PIE",
     "PT",
     "PTH",
@@ -82,6 +83,7 @@ select = [
 ignore = [
     "COM812", # Messes with the formatter
     "ISC001", # Messes with the formatter
+    "PERF203", # Rarely useful
     "RUF006", # TODO (Store a reference to the return value of `asyncio.create_task`)
     "RUF012", # TODO (Mutable class attributes should be annotated with `typing.ClassVar`)
 ]