Skip to content

feat: support single run doc extractor node #11318

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jan 8, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 19 additions & 1 deletion api/core/workflow/nodes/document_extractor/node.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,8 @@
import operator
import os
import tempfile
from typing import cast
from collections.abc import Mapping, Sequence
from typing import Any, cast

import docx
import pandas as pd
Expand Down Expand Up @@ -81,6 +82,23 @@ def _run(self):
process_data=process_data,
)

@classmethod
def _extract_variable_selector_to_variable_mapping(
cls,
*,
graph_config: Mapping[str, Any],
node_id: str,
node_data: DocumentExtractorNodeData,
) -> Mapping[str, Sequence[str]]:
"""
Extract variable selector to variable mapping
:param graph_config: graph config
:param node_id: node id
:param node_data: node data
:return:
"""
return {node_id + ".files": node_data.variable_selector}


def _extract_text_by_mime_type(*, file_content: bytes, mime_type: str) -> str:
"""Extract text from a file based on its MIME type."""
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ import VariableAssigner from '@/app/components/workflow/nodes/variable-assigner/
import Assigner from '@/app/components/workflow/nodes/assigner/default'
import ParameterExtractorDefault from '@/app/components/workflow/nodes/parameter-extractor/default'
import IterationDefault from '@/app/components/workflow/nodes/iteration/default'
import DocumentExtractorDefault from '@/app/components/workflow/nodes/document-extractor/default'
import { ssePost } from '@/service/base'

import { getInputVars as doGetInputVars } from '@/app/components/base/prompt-editor/constants'
Expand All @@ -43,6 +44,7 @@ const { checkValid: checkVariableAssignerValid } = VariableAssigner
const { checkValid: checkAssignerValid } = Assigner
const { checkValid: checkParameterExtractorValid } = ParameterExtractorDefault
const { checkValid: checkIterationValid } = IterationDefault
const { checkValid: checkDocumentExtractorValid } = DocumentExtractorDefault

const checkValidFns: Record<BlockEnum, Function> = {
[BlockEnum.LLM]: checkLLMValid,
Expand All @@ -57,6 +59,7 @@ const checkValidFns: Record<BlockEnum, Function> = {
[BlockEnum.VariableAggregator]: checkVariableAssignerValid,
[BlockEnum.ParameterExtractor]: checkParameterExtractorValid,
[BlockEnum.Iteration]: checkIterationValid,
[BlockEnum.DocExtractor]: checkDocumentExtractorValid,
} as any

type Params<T> = {
Expand Down
37 changes: 36 additions & 1 deletion web/app/components/workflow/nodes/document-extractor/panel.tsx
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,11 @@ import useConfig from './use-config'
import type { DocExtractorNodeType } from './types'
import { fetchSupportFileTypes } from '@/service/datasets'
import Field from '@/app/components/workflow/nodes/_base/components/field'
import { BlockEnum, type NodePanelProps } from '@/app/components/workflow/types'
import { BlockEnum, InputVarType, type NodePanelProps } from '@/app/components/workflow/types'
import I18n from '@/context/i18n'
import { LanguagesSupported } from '@/i18n/language'
import BeforeRunForm from '@/app/components/workflow/nodes/_base/components/before-run-form'
import ResultPanel from '@/app/components/workflow/run/result-panel'

const i18nPrefix = 'workflow.nodes.docExtractor'

Expand Down Expand Up @@ -46,6 +48,15 @@ const Panel: FC<NodePanelProps<DocExtractorNodeType>> = ({
inputs,
handleVarChanges,
filterVar,
// single run
isShowSingleRun,
hideSingleRun,
runningStatus,
handleRun,
handleStop,
runResult,
files,
setFiles,
} = useConfig(id, data)

return (
Expand Down Expand Up @@ -81,6 +92,30 @@ const Panel: FC<NodePanelProps<DocExtractorNodeType>> = ({
/>
</OutputVars>
</div>
{
isShowSingleRun && (
<BeforeRunForm
nodeName={inputs.title}
onHide={hideSingleRun}
forms={[
{
inputs: [{
label: t(`${i18nPrefix}.inputVar`)!,
variable: 'files',
type: InputVarType.multiFiles,
required: true,
}],
values: { files },
onChange: keyValue => setFiles((keyValue as any).files),
},
]}
runningStatus={runningStatus}
onRun={handleRun}
onStop={handleStop}
result={<ResultPanel {...runResult} showSteps={false} />}
/>
)
}
</div>
)
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,10 @@ import produce from 'immer'
import { useStoreApi } from 'reactflow'

import type { ValueSelector, Var } from '../../types'
import { VarType } from '../../types'
import { InputVarType, VarType } from '../../types'
import { type DocExtractorNodeType } from './types'
import useNodeCrud from '@/app/components/workflow/nodes/_base/hooks/use-node-crud'
import useOneStepRun from '@/app/components/workflow/nodes/_base/hooks/use-one-step-run'
import {
useIsChatMode,
useNodesReadOnly,
Expand Down Expand Up @@ -55,11 +56,53 @@ const useConfig = (id: string, payload: DocExtractorNodeType) => {
setInputs(newInputs)
}, [getType, inputs, setInputs])

// single run
const {
isShowSingleRun,
hideSingleRun,
runningStatus,
isCompleted,
handleRun,
handleStop,
runInputData,
setRunInputData,
runResult,
} = useOneStepRun<DocExtractorNodeType>({
id,
data: inputs,
defaultRunInputData: { files: [] },
})
const varInputs = [{
label: inputs.title,
variable: 'files',
type: InputVarType.multiFiles,
required: true,
}]

const files = runInputData.files
const setFiles = useCallback((newFiles: []) => {
setRunInputData({
...runInputData,
files: newFiles,
})
}, [runInputData, setRunInputData])

return {
readOnly,
inputs,
filterVar,
handleVarChanges,
// single run
isShowSingleRun,
hideSingleRun,
runningStatus,
isCompleted,
handleRun,
handleStop,
varInputs,
files,
setFiles,
runResult,
}
}

Expand Down
1 change: 1 addition & 0 deletions web/app/components/workflow/utils.ts
Original file line number Diff line number Diff line change
Expand Up @@ -382,6 +382,7 @@ export const canRunBySingle = (nodeType: BlockEnum) => {
|| nodeType === BlockEnum.Tool
|| nodeType === BlockEnum.ParameterExtractor
|| nodeType === BlockEnum.Iteration
|| nodeType === BlockEnum.DocExtractor
}

type ConnectedSourceOrTargetNodesChange = {
Expand Down
Loading