|
|
@@ -2,14 +2,14 @@ identity:
|
|
|
name: jina_reader
|
|
|
author: Dify
|
|
|
label:
|
|
|
- en_US: JinaReader
|
|
|
- zh_Hans: JinaReader
|
|
|
- pt_BR: JinaReader
|
|
|
+ en_US: Fetch Single Page
|
|
|
+ zh_Hans: 获取单页面
|
|
|
+ pt_BR: Fetch Single Page
|
|
|
description:
|
|
|
human:
|
|
|
- en_US: Convert any URL to an LLM-friendly input. Experience improved output for your agent and RAG systems at no cost.
|
|
|
- zh_Hans: 将任何 URL 转换为 LLM 友好的输入。无需付费即可体验为您的 Agent 和 RAG 系统提供的改进输出。
|
|
|
- pt_BR: Converta qualquer URL em uma entrada amigável ao LLM. Experimente uma saída aprimorada para seus sistemas de agente e RAG sem custo.
|
|
|
+ en_US: Fetch the target URL (can be a PDF) and convert it into a LLM-friendly markdown.
|
|
|
+ zh_Hans: 获取目标网址（可以是 PDF），并将其转换为适合大模型处理的 Markdown 格式。
|
|
|
+ pt_BR: Busque a URL de destino (que pode ser um PDF) e converta em um Markdown LLM-friendly.
|
|
|
llm: A tool for scraping webpages. Input should be a URL.
|
|
|
parameters:
|
|
|
- name: url
|
|
|
@@ -17,13 +17,13 @@ parameters:
|
|
|
required: true
|
|
|
label:
|
|
|
en_US: URL
|
|
|
- zh_Hans: 网页链接
|
|
|
+ zh_Hans: 网址
|
|
|
pt_BR: URL
|
|
|
human_description:
|
|
|
- en_US: used for linking to webpages
|
|
|
- zh_Hans: 用于链接到网页
|
|
|
- pt_BR: used for linking to webpages
|
|
|
- llm_description: url for scraping
|
|
|
+ en_US: Web link
|
|
|
+ zh_Hans: 网页链接
|
|
|
+ pt_BR: URL da web
|
|
|
+ llm_description: url para scraping
|
|
|
form: llm
|
|
|
- name: request_params
|
|
|
type: string
|
|
|
@@ -31,14 +31,14 @@ parameters:
|
|
|
label:
|
|
|
en_US: Request params
|
|
|
zh_Hans: 请求参数
|
|
|
- pt_BR: Request params
|
|
|
+ pt_BR: Parâmetros de solicitação
|
|
|
human_description:
|
|
|
en_US: |
|
|
|
request parameters, format: {"key1": "value1", "key2": "value2"}
|
|
|
zh_Hans: |
|
|
|
请求参数，格式：{"key1": "value1", "key2": "value2"}
|
|
|
pt_BR: |
|
|
|
- request parameters, format: {"key1": "value1", "key2": "value2"}
|
|
|
+ parâmetros de solicitação, formato: {"key1": "value1", "key2": "value2"}
|
|
|
llm_description: request parameters
|
|
|
form: llm
|
|
|
- name: target_selector
|
|
|
@@ -51,7 +51,7 @@ parameters:
|
|
|
human_description:
|
|
|
en_US: css selector for scraping specific elements
|
|
|
zh_Hans: css 选择器用于抓取特定元素
|
|
|
- pt_BR: css selector for scraping specific elements
|
|
|
+ pt_BR: css selector para scraping de elementos específicos
|
|
|
llm_description: css selector of the target element to scrape
|
|
|
form: form
|
|
|
- name: wait_for_selector
|
|
|
@@ -64,7 +64,7 @@ parameters:
|
|
|
human_description:
|
|
|
en_US: css selector for waiting for specific elements
|
|
|
zh_Hans: css 选择器用于等待特定元素
|
|
|
- pt_BR: css selector for waiting for specific elements
|
|
|
+ pt_BR: css selector para aguardar elementos específicos
|
|
|
llm_description: css selector of the target element to wait for
|
|
|
form: form
|
|
|
- name: image_caption
|
|
|
@@ -77,8 +77,8 @@ parameters:
|
|
|
pt_BR: Legenda da imagem
|
|
|
human_description:
|
|
|
en_US: "Captions all images at the specified URL, adding 'Image [idx]: [caption]' as an alt tag for those without one. This allows downstream LLMs to interact with the images in activities such as reasoning and summarizing."
|
|
|
- zh_Hans: "为指定 URL 上的所有图像添加标题，为没有标题的图像添加“Image [idx]: [caption]”作为 alt 标签。这允许下游 LLM 在推理和总结等活动中与图像进行交互。"
|
|
|
- pt_BR: "Captions all images at the specified URL, adding 'Image [idx]: [caption]' as an alt tag for those without one. This allows downstream LLMs to interact with the images in activities such as reasoning and summarizing."
|
|
|
+ zh_Hans: "为指定 URL 上的所有图像添加标题，为没有标题的图像添加“Image [idx]: [caption]”作为 alt 标签，以支持下游模型的图像交互。"
|
|
|
+ pt_BR: "Adiciona legendas a todas as imagens na URL especificada, adicionando 'Imagem [idx]: [legenda]' como uma tag alt para aquelas que não têm uma. Isso permite que os modelos LLM inferiores interajam com as imagens em atividades como raciocínio e resumo."
|
|
|
llm_description: Captions all images at the specified URL
|
|
|
form: form
|
|
|
- name: gather_all_links_at_the_end
|
|
|
@@ -91,8 +91,8 @@ parameters:
|
|
|
pt_BR: Coletar todos os links ao final
|
|
|
human_description:
|
|
|
en_US: A "Buttons & Links" section will be created at the end. This helps the downstream LLMs or web agents navigating the page or take further actions.
|
|
|
- zh_Hans: 最后会创建一个“按钮和链接”部分。这可以帮助下游 LLM 或 Web 代理浏览页面或采取进一步的行动。
|
|
|
- pt_BR: A "Buttons & Links" section will be created at the end. This helps the downstream LLMs or web agents navigating the page or take further actions.
|
|
|
+ zh_Hans: 末尾将添加“按钮和链接”部分，方便下游模型或网络代理做页面导航或执行进一步操作。
|
|
|
+ pt_BR: Um "Botões & Links" section will be created at the end. This helps the downstream LLMs or web agents navigating the page or take further actions.
|
|
|
llm_description: Gather all links at the end
|
|
|
form: form
|
|
|
- name: gather_all_images_at_the_end
|
|
|
@@ -105,8 +105,8 @@ parameters:
|
|
|
pt_BR: Coletar todas as imagens ao final
|
|
|
human_description:
|
|
|
en_US: An "Images" section will be created at the end. This gives the downstream LLMs an overview of all visuals on the page, which may improve reasoning.
|
|
|
- zh_Hans: 最后会创建一个“图像”部分。这可以让下游的 LLM 概览页面上的所有视觉效果，从而提高推理能力。
|
|
|
- pt_BR: An "Images" section will be created at the end. This gives the downstream LLMs an overview of all visuals on the page, which may improve reasoning.
|
|
|
+ zh_Hans: 末尾会新增“图片”部分，方便下游模型全面了解页面的视觉内容，提升推理效果。
|
|
|
+ pt_BR: Um "Imagens" section will be created at the end. This gives the downstream LLMs an overview of all visuals on the page, which may improve reasoning.
|
|
|
llm_description: Gather all images at the end
|
|
|
form: form
|
|
|
- name: proxy_server
|
Sa Zhang