api/core/tools/provider/builtin/jina/tools/jina_reader.yaml +41 Original file line numberDiff line numberDiff line change @@ -0,0 +1,41 @@ 1 + identity: 2 + name: jina_reader 3 + author: Dify 4 + label: 5 + en_US: JinaReader 6 + zh_Hans: JinaReader 7 + pt...
feat: jina reader (langgenius#3468) bccb31e HuberyHuV1 pushed a commit to HuberyHuV1/dify that referenced this pull request Jul 22, 2024 feat: jina reader (langgenius#3468) d26235c Sign up for free to join this conversation on GitHub. Already have an account? Sign in to commen...
{"jina_reader_base":"https://r.jina.ai","open_ai_api_base":"https://api.openai.com/v1",#请填入自己的代理地址"open_ai_api_key":"sk-xxx",#请填入自己的APIkey"open_ai_model":"gpt-3.5-turbo",#填入使用的AI模型"max_words":8000,#网页链接内容的最大字数,防止超过最大输入token,使用字...
Jina AI 开源了 RAG 数据处理中的关键组件:“Reader网页数据爬取” ,目前 3300 多个 StarJina AI Reader 优点很多,比如完全开源、免费使用、能够处理arXiv的PDF、提供 stream 模式等等。说它是爬取其实有点“过”了,因为这个工具主要服务于将任何 url 转化为 llm 友好的
jinaReaderNotConfigured: 'Jina Reader 未配置', jinaReaderNotConfiguredDescription: '请配置 Jina Reader 的免费 API 密钥以访问它。', configure: '配置', run: '运行', firecrawlTitle: '使用 🔥Firecrawl 提取网页内容', firecrawlDoc: 'Firecrawl 文档', firecrawlDocLink: 'https://docs.dify.ai...
2 changes: 1 addition & 1 deletion 2 plugins/jina_sum/jina_sum.py Original file line numberDiff line numberDiff line change @@ -17,7 +17,7 @@ desire_priority=10, hidden=False, desc="Sum url link content with jina reader and llm", version="v0.0.1", version="0.0.1", author="...
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/ - jina-ai-reader/package-lock.json at main · mbrukman/jina-ai-reader
forked fromlanggenius/dify NotificationsYou must be signed in to change notification settings Fork0 Star0 Code Pull requests7 Actions Projects Security Insights Additional navigation options Browse files Yeuoly authoredApr 14, 2024 feat: jina reader (langgenius#3468) ...
jinaReaderNotConfigured: 'Jina Reader 未配置', jinaReaderNotConfiguredDescription: '请配置 Jina Reader 的免费 API 密钥以访问它。', configure: '配置', run: '运行', firecrawlTitle: '使用 🔥Firecrawl 提取网页内容', firecrawlDoc: 'Firecrawl 文档', firecrawlDocLink: 'https://docs.dify.ai...