Feat:new component list operations (#11276)

### What problem does this PR solve?
issue:
https://github.com/infiniflow/ragflow/issues/10427
change:
new component list operations

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

agent/component/list_operations.py

@@ -0,0 +1,149 @@
+from abc import ABC
+import os
+from agent.component.base import ComponentBase, ComponentParamBase
+from api.utils.api_utils import timeout
+
+class ListOperationsParam(ComponentParamBase):
+    """
+    Define the List Operations component parameters.
+    """
+    def __init__(self):
+        super().__init__()
+        self.query = ""
+        self.operations = "topN"
+        self.n=0
+        self.sort_method = "asc"
+        self.filter = {
+            "operator": "=",
+            "value": ""
+        }
+        self.outputs = {
+            "result": {
+                "value": [],
+                "type": "Array of ?"
+            },
+            "first": {
+                "value": "",
+                "type": "?"
+            },
+            "last": {
+                "value": "",
+                "type": "?"
+            }
+        }
+    
+    def check(self):
+        self.check_empty(self.query, "query")
+        self.check_valid_value(self.operations, "Support operations", ["topN","head","tail","filter","sort","drop_duplicates"])
+
+    def get_input_form(self) -> dict[str, dict]:
+        return {}
+    
+
+class ListOperations(ComponentBase,ABC):
+    component_name = "ListOperations"
+
+    @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
+    def _invoke(self, **kwargs):
+        self.input_objects=[]
+        inputs = getattr(self._param, "query", None)
+        self.inputs=self._canvas.get_variable_value(inputs)
+        self.set_input_value(inputs, self.inputs)
+        if self._param.operations == "topN":
+            self._topN()
+        elif self._param.operations == "head":
+            self._head()
+        elif self._param.operations == "tail":
+            self._tail()
+        elif self._param.operations == "filter":
+            self._filter()
+        elif self._param.operations == "sort":
+            self._sort()
+        elif self._param.operations == "drop_duplicates":
+            self._drop_duplicates()
+
+
+    def _coerce_n(self):
+        try:
+            return int(getattr(self._param, "n", 0))
+        except Exception:
+            return 0
+        
+    def _set_outputs(self, outputs):
+        self._param.outputs["result"]["value"] = outputs
+        self._param.outputs["first"]["value"] = outputs[0] if outputs else None
+        self._param.outputs["last"]["value"]  = outputs[-1] if outputs else None
+        
+    def _topN(self):
+        n = self._coerce_n()
+        if n < 1:
+            outputs = []
+        else:
+            n = min(n, len(self.inputs))
+            outputs = self.inputs[:n]
+        self._set_outputs(outputs)
+
+    def _head(self):
+        n = self._coerce_n()
+        if 1 <= n <= len(self.inputs):
+            outputs = [self.inputs[n - 1]]
+        else:
+            outputs = []
+        self._set_outputs(outputs)
+
+    def _tail(self):
+        n = self._coerce_n()
+        if 1 <= n <= len(self.inputs):
+            outputs = [self.inputs[-n]]
+        else:
+            outputs = []
+        self._set_outputs(outputs)
+
+    def _filter(self):
+        self._set_outputs([i for i in self.inputs if self._eval(self._norm(i),self._param.filter["operator"],self._param.filter["value"])])
+
+    def _norm(self,v):
+        s = "" if v is None else str(v)
+        return s
+    
+    def _eval(self, v, operator, value):
+        if operator == "=":
+            return v == value
+        elif operator == "≠":
+            return v != value
+        elif operator == "contains":
+            return value in v
+        elif operator == "start with":
+            return v.startswith(value)
+        elif operator == "end with":
+            return v.endswith(value)
+        else:
+            return False
+
+    def _sort(self):
+        if self._param.sort_method == "asc":
+            self._set_outputs(sorted(self.inputs))
+        elif self._param.sort_method == "desc":
+            self._set_outputs(sorted(self.inputs, reverse=True))
+
+    def _drop_duplicates(self):
+        seen = set()
+        outs = []
+        for item in self.inputs:
+            k = self._hashable(item)
+            if k in seen:
+                continue
+            seen.add(k)
+            outs.append(item)
+        self._set_outputs(outs)
+
+    def _hashable(self,x):
+        if isinstance(x, dict):
+            return tuple(sorted((k, self._hashable(v)) for k, v in x.items()))
+        if isinstance(x, (list, tuple)):
+            return tuple(self._hashable(v) for v in x)
+        if isinstance(x, set):
+            return tuple(sorted(self._hashable(v) for v in x))
+        return x
+    def thoughts(self) -> str:
+        return "ListOperation in progress"

web/src/constants/agent.tsx

@@ -109,6 +109,7 @@ export enum Operator {
   SearXNG = 'SearXNG',
   Placeholder = 'Placeholder',
   DataOperations = 'DataOperations',
+  ListOperations = 'ListOperations',
   VariableAssigner = 'VariableAssigner',
   VariableAggregator = 'VariableAggregator',
   File = 'File', // pipeline

web/src/locales/en.ts

@@ -1591,6 +1591,8 @@ This delimiter is used to split the input text into several text pieces echo of
       codeDescription: 'It allows developers to write custom Python logic.',
       dataOperations: 'Data operations',
       dataOperationsDescription: 'Perform various operations on a Data object.',
+      listOperations: 'List operations',
+      listOperationsDescription: 'Perform operations on a list.',
       variableAssigner: 'Variable assigner',
       variableAssignerDescription:
         'This component performs operations on Data objects, including extracting, filtering, and editing keys and values in the Data.',
@@ -1806,6 +1808,19 @@ Important structured information may include: names, dates, locations, events, k
         removeKeys: 'Remove keys',
         renameKeys: 'Rename keys',
       },
+      ListOperationsOptions: {
+        topN: 'Top N',
+        head: 'Head',
+        tail: 'Tail',
+        sort: 'Sort',
+        filter: 'Filter',
+        dropDuplicates: 'Drop duplicates',
+      },
+      sortMethod: 'Sort method',
+      SortMethodOptions: {
+        asc: 'Ascending',
+        desc: 'Descending',
+      },
     },
     llmTools: {
       bad_calculator: {

web/src/locales/zh.ts

@@ -1508,6 +1508,8 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       codeDescription: '它允许开发人员编写自定义 Python 逻辑。',
       dataOperations: '数据操作',
       dataOperationsDescription: '对数据对象执行各种操作。',
+      listOperations: '列表操作',
+      listOperationsDescription: '对列表对象执行各种操作。',
       variableAssigner: '变量赋值器',
       variableAssignerDescription:
         '此组件对数据对象执行操作，包括提取、筛选和编辑数据中的键和值。',
@@ -1679,6 +1681,19 @@ Tokenizer 会根据所选方式将内容存储为对应的数据结构。`,
         removeKeys: '删除键',
         renameKeys: '重命名键',
       },
+      ListOperationsOptions: {
+        topN: '取前N项',
+        head: '取前第N项',
+        tail: '取后第N项',
+        sort: '排序',
+        filter: '筛选',
+        dropDuplicates: '去重',
+      },
+      sortMethod: '排序方式',
+      SortMethodOptions: {
+        asc: '升序',
+        desc: '降序',
+      },
     },
     footer: {
       profile: 'All rights reserved @ React',

web/src/pages/agent/canvas/index.tsx

@@ -61,6 +61,7 @@ import { FileNode } from './node/file-node';
 import { InvokeNode } from './node/invoke-node';
 import { IterationNode, IterationStartNode } from './node/iteration-node';
 import { KeywordNode } from './node/keyword-node';
+import { ListOperationsNode } from './node/list-operations-node';
 import { MessageNode } from './node/message-node';
 import NoteNode from './node/note-node';
 import ParserNode from './node/parser-node';
@@ -101,6 +102,7 @@ export const nodeTypes: NodeTypes = {
   splitterNode: SplitterNode,
   contextNode: ExtractorNode,
   dataOperationsNode: DataOperationsNode,
+  listOperationsNode: ListOperationsNode,
   variableAssignerNode: VariableAssignerNode,
   variableAggregatorNode: VariableAggregatorNode,
 };

web/src/pages/agent/canvas/node/dropdown/accordion-operators.tsx

@@ -79,6 +79,7 @@ export function AccordionOperators({
               Operator.Code,
               Operator.StringTransform,
               Operator.DataOperations,
+              Operator.ListOperations,
               // Operator.VariableAssigner,
               Operator.VariableAggregator,
             ]}

web/src/pages/agent/canvas/node/list-operations-node.tsx

@@ -0,0 +1,22 @@
+import { BaseNode } from '@/interfaces/database/agent';
+import { NodeProps } from '@xyflow/react';
+import { camelCase } from 'lodash';
+import { useTranslation } from 'react-i18next';
+import { RagNode } from '.';
+import { ListOperationsFormSchemaType } from '../../form/list-operations-form';
+import { LabelCard } from './card';
+
+export function ListOperationsNode({
+  ...props
+}: NodeProps<BaseNode<ListOperationsFormSchemaType>>) {
+  const { data } = props;
+  const { t } = useTranslation();
+
+  return (
+    <RagNode {...props}>
+      <LabelCard>
+        {t(`flow.ListOperationsOptions.${camelCase(data.form?.operations)}`)}
+      </LabelCard>
+    </RagNode>
+  );
+}

web/src/pages/agent/constant/index.tsx

@@ -595,6 +595,35 @@ export const initialDataOperationsValues = {
     },
   },
 };
+export enum SortMethod {
+  Asc = 'asc',
+  Desc = 'desc',
+}
+
+export enum ListOperations {
+  TopN = 'topN',
+  Head = 'head',
+  Tail = 'tail',
+  Filter = 'filter',
+  Sort = 'sort',
+  DropDuplicates = 'drop_duplicates',
+}
+
+export const initialListOperationsValues = {
+  query: '',
+  operations: ListOperations.TopN,
+  outputs: {
+    result: {
+      type: 'Array<?>',
+    },
+    first: {
+      type: '?',
+    },
+    last: {
+      type: '?',
+    },
+  },
+};
 
 export const initialVariableAssignerValues = {};
 
@@ -673,6 +702,7 @@ export const RestrictedUpstreamMap = {
   [Operator.Tool]: [Operator.Begin],
   [Operator.Placeholder]: [Operator.Begin],
   [Operator.DataOperations]: [Operator.Begin],
+  [Operator.ListOperations]: [Operator.Begin],
   [Operator.Parser]: [Operator.Begin], // pipeline
   [Operator.Splitter]: [Operator.Begin],
   [Operator.HierarchicalMerger]: [Operator.Begin],
@@ -729,6 +759,7 @@ export const NodeMap = {
   [Operator.HierarchicalMerger]: 'splitterNode',
   [Operator.Extractor]: 'contextNode',
   [Operator.DataOperations]: 'dataOperationsNode',
+  [Operator.ListOperations]: 'listOperationsNode',
   [Operator.VariableAssigner]: 'variableAssignerNode',
   [Operator.VariableAggregator]: 'variableAggregatorNode',
 };

web/src/pages/agent/form-sheet/form-config-map.tsx

@@ -21,6 +21,7 @@ import IterationForm from '../form/iteration-form';
 import IterationStartForm from '../form/iteration-start-from';
 import Jin10Form from '../form/jin10-form';
 import KeywordExtractForm from '../form/keyword-extract-form';
+import ListOperationsForm from '../form/list-operations-form';
 import MessageForm from '../form/message-form';
 import ParserForm from '../form/parser-form';
 import PubMedForm from '../form/pubmed-form';
@@ -184,6 +185,9 @@ export const FormConfigMap = {
   [Operator.DataOperations]: {
     component: DataOperationsForm,
   },
+  [Operator.ListOperations]: {
+    component: ListOperationsForm,
+  },
   [Operator.VariableAssigner]: {
     component: VariableAssignerForm,
   },

web/src/pages/agent/form/list-operations-form/index.tsx

@@ -0,0 +1,140 @@
+import NumberInput from '@/components/originui/number-input';
+import { SelectWithSearch } from '@/components/originui/select-with-search';
+import { RAGFlowFormItem } from '@/components/ragflow-form';
+import {
+  Form,
+  FormControl,
+  FormField,
+  FormItem,
+  FormLabel,
+  FormMessage,
+} from '@/components/ui/form';
+import { Separator } from '@/components/ui/separator';
+import { useBuildSwitchOperatorOptions } from '@/hooks/logic-hooks/use-build-operator-options';
+import { buildOptions } from '@/utils/form';
+import { zodResolver } from '@hookform/resolvers/zod';
+import { memo } from 'react';
+import { useForm, useWatch } from 'react-hook-form';
+import { useTranslation } from 'react-i18next';
+import { z } from 'zod';
+import {
+  DataOperationsOperatorOptions,
+  JsonSchemaDataType,
+  ListOperations,
+  SortMethod,
+  initialListOperationsValues,
+} from '../../constant';
+import { useFormValues } from '../../hooks/use-form-values';
+import { useWatchFormChange } from '../../hooks/use-watch-form-change';
+import { INextOperatorForm } from '../../interface';
+import { buildOutputList } from '../../utils/build-output-list';
+import { FormWrapper } from '../components/form-wrapper';
+import { Output, OutputSchema } from '../components/output';
+import { PromptEditor } from '../components/prompt-editor';
+import { QueryVariable } from '../components/query-variable';
+
+export const RetrievalPartialSchema = {
+  query: z.string(),
+  operations: z.string(),
+  n: z.number().int().min(0).optional(),
+  sort_method: z.string().optional(),
+  filter: z
+    .object({
+      value: z.string().optional(),
+      operator: z.string().optional(),
+    })
+    .optional(),
+  ...OutputSchema,
+};
+
+export const FormSchema = z.object(RetrievalPartialSchema);
+
+export type ListOperationsFormSchemaType = z.infer<typeof FormSchema>;
+
+const outputList = buildOutputList(initialListOperationsValues.outputs);
+
+function ListOperationsForm({ node }: INextOperatorForm) {
+  const { t } = useTranslation();
+
+  const defaultValues = useFormValues(initialListOperationsValues, node);
+
+  const form = useForm<ListOperationsFormSchemaType>({
+    defaultValues: defaultValues,
+    mode: 'onChange',
+    resolver: zodResolver(FormSchema),
+    shouldUnregister: true,
+  });
+
+  const operations = useWatch({ control: form.control, name: 'operations' });
+
+  const ListOperationsOptions = buildOptions(
+    ListOperations,
+    t,
+    `flow.ListOperationsOptions`,
+    true,
+  );
+  const SortMethodOptions = buildOptions(
+    SortMethod,
+    t,
+    `flow.SortMethodOptions`,
+    true,
+  );
+  const operatorOptions = useBuildSwitchOperatorOptions(
+    DataOperationsOperatorOptions,
+  );
+  useWatchFormChange(node?.id, form, true);
+
+  return (
+    <Form {...form}>
+      <FormWrapper>
+        <QueryVariable
+          name="query"
+          className="flex-1"
+          types={[JsonSchemaDataType.Array]}
+        ></QueryVariable>
+        <Separator />
+        <RAGFlowFormItem name="operations" label={t('flow.operations')}>
+          <SelectWithSearch options={ListOperationsOptions} />
+        </RAGFlowFormItem>
+        {[
+          ListOperations.TopN,
+          ListOperations.Head,
+          ListOperations.Tail,
+        ].includes(operations as ListOperations) && (
+          <FormField
+            control={form.control}
+            name="n"
+            render={({ field }) => (
+              <FormItem>
+                <FormLabel>{t('flowNum')}</FormLabel>
+                <FormControl>
+                  <NumberInput {...field} className="w-full"></NumberInput>
+                </FormControl>
+                <FormMessage />
+              </FormItem>
+            )}
+          />
+        )}
+        {[ListOperations.Sort].includes(operations as ListOperations) && (
+          <RAGFlowFormItem name="sort_method" label={t('flow.sortMethod')}>
+            <SelectWithSearch options={SortMethodOptions} />
+          </RAGFlowFormItem>
+        )}
+        {[ListOperations.Filter].includes(operations as ListOperations) && (
+          <div className="flex items-center gap-2">
+            <RAGFlowFormItem name="filter.operator" className="flex-1">
+              <SelectWithSearch options={operatorOptions}></SelectWithSearch>
+            </RAGFlowFormItem>
+            <Separator className="w-2" />
+            <RAGFlowFormItem name="filter.value" className="flex-1">
+              <PromptEditor showToolbar={false} multiLine={false} />
+            </RAGFlowFormItem>
+          </div>
+        )}
+        <Output list={outputList} isFormRequired></Output>
+      </FormWrapper>
+    </Form>
+  );
+}
+
+export default memo(ListOperationsForm);

web/src/pages/agent/hooks/use-add-node.ts

@@ -31,6 +31,7 @@ import {
   initialIterationValues,
   initialJin10Values,
   initialKeywordExtractValues,
+  initialListOperationsValues,
   initialMessageValues,
   initialNoteValues,
   initialParserValues,
@@ -129,6 +130,7 @@ export const useInitializeOperatorParams = () => {
         prompts: t('flow.prompts.user.summary'),
       },
       [Operator.DataOperations]: initialDataOperationsValues,
+      [Operator.ListOperations]: initialListOperationsValues,
       [Operator.VariableAssigner]: initialVariableAssignerValues,
       [Operator.VariableAggregator]: initialVariableAggregatorValues,
     };

web/src/pages/agent/operator-icon.tsx

@@ -14,7 +14,7 @@ import { ReactComponent as YahooFinanceIcon } from '@/assets/svg/yahoo-finance.s
 
 import { IconFont } from '@/components/icon-font';
 import { cn } from '@/lib/utils';
-import { Equal, FileCode, HousePlus, Variable } from 'lucide-react';
+import { Columns3, Equal, FileCode, HousePlus, Variable } from 'lucide-react';
 import { Operator } from './constant';
 
 interface IProps {
@@ -57,6 +57,7 @@ export const SVGIconMap = {
 };
 export const LucideIconMap = {
   [Operator.DataOperations]: FileCode,
+  [Operator.ListOperations]: Columns3,
   [Operator.VariableAssigner]: Equal,
   [Operator.VariableAggregator]: Variable,
 };

web/src/pages/agent/utils.ts

@@ -328,7 +328,6 @@ export const buildDslComponentsByGraph = (
         case Operator.DataOperations:
           params = transformDataOperationsParams(params);
           break;
-
         default:
           break;
       }