解析网页内容存到知识库

YAML 源码

app:
  description: ''
  icon: 🤖
  icon_background: '#FFEAD5'
  mode: workflow
  name: 解析网页内容存到知识库
  use_icon_as_answer_icon: false
kind: app
version: 0.1.2
workflow:
  conversation_variables: []
  environment_variables: []
  features:
    file_upload:
      allowed_file_extensions:
      - .JPG
      - .JPEG
      - .PNG
      - .GIF
      - .WEBP
      - .SVG
      allowed_file_types:
      - image
      allowed_file_upload_methods:
      - local_file
      - remote_url
      enabled: false
      image:
        enabled: false
        number_limits: 3
        transfer_methods:
        - local_file
        - remote_url
      number_limits: 3
    opening_statement: ''
    retriever_resource:
      enabled: true
    sensitive_word_avoidance:
      enabled: false
    speech_to_text:
      enabled: false
    suggested_questions: []
    suggested_questions_after_answer:
      enabled: false
    text_to_speech:
      enabled: false
      language: ''
      voice: ''
  graph:
    edges:
    - data:
        isInIteration: false
        sourceType: start
        targetType: tool
      id: 1726648972903-source-1726648991458-target
      source: '1726648972903'
      sourceHandle: source
      target: '1726648991458'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: tool
        targetType: llm
      id: 1726648991458-source-1726649065049-target
      selected: false
      source: '1726648991458'
      sourceHandle: source
      target: '1726649065049'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: llm
        targetType: code
      id: 1726649065049-source-1726649425625-target
      source: '1726649065049'
      sourceHandle: source
      target: '1726649425625'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: code
        targetType: http-request
      id: 1726649425625-source-1726649528184-target
      source: '1726649425625'
      sourceHandle: source
      target: '1726649528184'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: http-request
        targetType: end
      id: 1726649528184-source-1726650097797-target
      source: '1726649528184'
      sourceHandle: source
      target: '1726650097797'
      targetHandle: target
      type: custom
      zIndex: 0
    nodes:
    - data:
        desc: ''
        selected: false
        title: 开始
        type: start
        variables:
        - label: url
          max_length: 256
          options: []
          required: true
          type: text-input
          variable: url
      height: 109
      id: '1726648972903'
      position:
        x: 77.84557970061047
        y: 282
      positionAbsolute:
        x: 77.84557970061047
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 243
    - data:
        desc: ''
        provider_id: jina
        provider_name: jina
        provider_type: builtin
        selected: false
        title: JinaReader
        tool_configurations:
          gather_all_images_at_the_end: 0
          gather_all_links_at_the_end: 0
          image_caption: 0
          max_retries: 3
          no_cache: 0
          proxy_server: null
          summary: 0
          target_selector: null
          wait_for_selector: null
        tool_label: JinaReader
        tool_name: jina_reader
        tool_parameters:
          url:
            type: mixed
            value: '{{#1726648972903.url#}}'
        type: tool
      height: 369
      id: '1726648991458'
      position:
        x: 381.69115940122094
        y: 282
      positionAbsolute:
        x: 381.69115940122094
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 243
    - data:
        context:
          enabled: true
          variable_selector:
          - '1726648991458'
          - text
        desc: ''
        model:
          completion_params:
            temperature: 0.7
          mode: chat
          name: qwen2.5:latest
          provider: ollama
        prompt_template:
        - id: b74b533b-9c88-494a-a5ad-9136734eb2bb
          role: system
          text: 'Use {{#context#}} as learned knowledge.

            任务要求：

            - 从给定的JSON数据中提取所有的纯文本内容。

            - 清除其中的推广信息、图片描述、链接以及换行符（包括\n和\r\n）。

            - 最终输出结果应完全用中文表述。

            - 仅关注并输出清理后的纯文本部分。

            '
        selected: false
        title: LLM
        type: llm
        variables: []
        vision:
          enabled: false
      height: 119
      id: '1726649065049'
      position:
        x: 691.4615295204807
        y: 282
      positionAbsolute:
        x: 691.4615295204807
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 243
    - data:
        code: "function main({ arg1 }) {\n    const cleaned = arg1.replace(/\\r?\\\
          n/g, '');\n    return { result: cleaned };\n}"
        code_language: javascript
        desc: ''
        outputs:
          result:
            children: null
            type: string
        selected: false
        title: 代码执行
        type: code
        variables:
        - value_selector:
          - '1726649065049'
          - text
          variable: arg1
      height: 64
      id: '1726649425625'
      position:
        x: 986.415630992888
        y: 282
      positionAbsolute:
        x: 986.415630992888
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 243
    - data:
        authorization:
          config:
            api_key: dataset-0ns4yKcVofUPJHGhp75MYvop
            type: bearer
          type: api-key
        body:
          data: '{"name": "content","text": "{{#1726649425625.result#}}","indexing_technique":
            "high_quality","process_rule": {"mode": "automatic"}}'
          type: json
        desc: ''
        headers: ''
        method: post
        params: ''
        selected: false
        timeout:
          max_connect_timeout: 0
          max_read_timeout: 0
          max_write_timeout: 0
        title: HTTP 请求
        type: http-request
        url: http://host.docker.internal/v1/datasets/2aae0d12-1b58-495f-834f-1b3dfd0c9bf8/document/create_by_text
        variables: []
      height: 214
      id: '1726649528184'
      position:
        x: 1291.7171189006258
        y: 282
      positionAbsolute:
        x: 1291.7171189006258
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 243
    - data:
        desc: ''
        outputs:
        - value_selector:
          - '1726649528184'
          - body
          variable: knowledge
        - value_selector:
          - '1726649425625'
          - result
          variable: cleaned_content
        - value_selector:
          - '1726649065049'
          - text
          variable: content
        selected: true
        title: 结束
        type: end
      height: 174
      id: '1726650097797'
      position:
        x: 1599
        y: 282
      positionAbsolute:
        x: 1599
        y: 282
      selected: true
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 243
    viewport:
      x: -172.91311585043468
      y: -61.259857828891654
      zoom: 0.9609278489568617