mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-06-29 15:31:05 +08:00
Agent templates regrouped and renamed (#13873)
### What problem does this PR solve? Regrouped and renamed agent templates to increase user engagement. ### Type of change - [x] Refactoring
This commit is contained in:
writinwaters
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -2,13 +2,13 @@
|
||||
{
|
||||
"id": 11,
|
||||
"title": {
|
||||
"en": "Customer Review Analysis",
|
||||
"de": "Kundenbewertungsanalyse",
|
||||
"zh": "客户评价分析"},
|
||||
"en": "Customer feedback disptacher",
|
||||
"de": "Feedback-Lotse",
|
||||
"zh": "客户反馈协调员"},
|
||||
"description": {
|
||||
"en": "Automatically classify customer reviews using LLM (Large Language Model) and route them via email to the relevant departments.",
|
||||
"de": "Klassifiziert automatisch Kundenbewertungen mithilfe von LLM (Large Language Model) und leitet sie per E-Mail an die zuständigen Abteilungen weiter.",
|
||||
"zh": "大模型将自动分类客户评价，并通过电子邮件将结果发送到相关部门。"},
|
||||
"zh": "该模板将自动分类客户评价，并通过电子邮件将结果发送到相关部门。"},
|
||||
"canvas_type": "Customer Support",
|
||||
"dsl": {
|
||||
"components": {
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -2,13 +2,13 @@
|
||||
{
|
||||
"id": 1,
|
||||
"title": {
|
||||
"en": "Deep Research",
|
||||
"en": "Deep research",
|
||||
"de": "Tiefgehende Recherche",
|
||||
"zh": "深度研究"},
|
||||
"zh": "Deep research"},
|
||||
"description": {
|
||||
"en": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep Research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.",
|
||||
"en": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep research Agentic workflow conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.",
|
||||
"de": "Für Fachleute in Vertrieb, Marketing, Politik oder Beratung führt der Multi-Agenten-Tiefenforschungsagent strukturierte, mehrstufige Untersuchungen über verschiedene Quellen durch und liefert Berichte im Beratungsstil mit klaren Quellenangaben.",
|
||||
"zh": "专为销售、市场、政策或咨询领域的专业人士设计，多智能体的深度研究会结合多源信息进行结构化、多步骤地回答问题，并附带有清晰的引用。"},
|
||||
"zh": "专为销售、市场、政策或咨询领域的专业人士设计，多智能体的 Deep research 会结合多源信息进行结构化、多步骤地回答问题，并附带有清晰的引用。"},
|
||||
"canvas_type": "Recommended",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -431,7 +431,7 @@
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Deep Research Agent"
|
||||
"name": "Deep research Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:NewPumasLick",
|
||||
@@ -692,10 +692,10 @@
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "A Deep Research Agent built on a multi-agent architecture.\nMuch of the credit goes to Anthropic\u2019s blog post, which deeply inspired this design.\n\nhttps://www.anthropic.com/engineering/built-multi-agent-research-system"
|
||||
"text": "A Deep research Agent built on a multi-agent architecture.\nMuch of the credit goes to Anthropic\u2019s blog post, which deeply inspired this design.\n\nhttps://www.anthropic.com/engineering/built-multi-agent-research-system"
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Multi-Agent Deep Research"
|
||||
"name": "Multi-Agent Deep research"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
@@ -722,7 +722,7 @@
|
||||
"text": "Choose a SOTA model with strong reasoning capabilities."
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Deep Research Lead Agent"
|
||||
"name": "Deep research lead Agent"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
|
||||
@@ -2,13 +2,13 @@
|
||||
{
|
||||
"id": 6,
|
||||
"title": {
|
||||
"en": "Deep Research",
|
||||
"en": "Deep research",
|
||||
"de": "Tiefgehende Recherche",
|
||||
"zh": "深度研究"},
|
||||
"zh": "Deep research"},
|
||||
"description": {
|
||||
"en": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep Research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.",
|
||||
"en": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.",
|
||||
"de": "Für Fachleute in Vertrieb, Marketing, Politik oder Beratung führt der Multi-Agenten-Tiefenforschungsagent strukturierte, mehrstufige Untersuchungen über verschiedene Quellen durch und liefert Berichte im Beratungsstil mit klaren Quellenangaben.",
|
||||
"zh": "专为销售、市场、政策或咨询领域的专业人士设计，多智能体的深度研究会结合多源信息进行结构化、多步骤地回答问题，并附带有清晰的引用。"},
|
||||
"zh": "专为销售、市场、政策或咨询领域的专业人士设计，多智能体的 Deep research 会结合多源信息进行结构化、多步骤地回答问题，并附带有清晰的引用。"},
|
||||
"canvas_type": "Agent",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -431,7 +431,7 @@
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Deep Research Agent"
|
||||
"name": "Deep research Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:NewPumasLick",
|
||||
@@ -692,10 +692,10 @@
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "A Deep Research Agent built on a multi-agent architecture.\nMuch of the credit goes to Anthropic\u2019s blog post, which deeply inspired this design.\n\nhttps://www.anthropic.com/engineering/built-multi-agent-research-system"
|
||||
"text": "A Deep research Agentic workflow built on a multi-agent architecture.\nMuch of the credit goes to Anthropic\u2019s blog post, which deeply inspired this design.\n\nhttps://www.anthropic.com/engineering/built-multi-agent-research-system"
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Multi-Agent Deep Research"
|
||||
"name": "Multi-Agent Deep research"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
@@ -722,7 +722,7 @@
|
||||
"text": "Choose a SOTA model with strong reasoning capabilities."
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Deep Research Lead Agent"
|
||||
"name": "Deep research lead Agent"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
{
|
||||
"id": 12,
|
||||
"title": {
|
||||
"en": "Generate SEO Blog",
|
||||
"de": "SEO Blog generieren",
|
||||
"zh": "生成SEO博客"},
|
||||
"en": "SEO article writer",
|
||||
"de": "SEO-Blog-Magnetiseur",
|
||||
"zh": "SEO 博客写手"},
|
||||
"description": {
|
||||
"en": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don't need any writing experience. Just provide a topic or short request — the system will handle the rest.",
|
||||
"de": "Dieser Workflow generiert automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
|
||||
"zh": "此工作流根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
|
||||
"en": "This SEO article writer automatically generates a complete SEO-optimized blog article based on a simple user input. You don't need any writing experience. Just provide a topic or short request — the system will handle the rest.",
|
||||
"de": "SEO-Blog-Magnetiseur automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
|
||||
"zh": "此 SEO 博客写手根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
|
||||
"canvas_type": "Marketing",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -1,13 +1,13 @@
|
||||
{
|
||||
"id": 13,
|
||||
"title": {
|
||||
"en": "ImageLingo",
|
||||
"de": "ImageLingo",
|
||||
"zh": "图片解析"},
|
||||
"en": "Photo text translator",
|
||||
"de": "Bild-Dolmetscher",
|
||||
"zh": "图片文字快译"},
|
||||
"description": {
|
||||
"en": "ImageLingo lets you snap any photo containing text—menus, signs, or documents—and instantly recognize and translate it into your language of choice using advanced AI-powered translation technology.",
|
||||
"de": "ImageLingo ermöglicht es Ihnen, jedes Foto mit Text – Menüs, Schilder oder Dokumente – zu fotografieren und es sofort in Ihre gewünschte Sprache zu erkennen und zu übersetzen, unter Verwendung fortschrittlicher KI-gestützter Übersetzungstechnologie.",
|
||||
"zh": "多模态大模型允许您拍摄任何包含文本的照片——菜单、标志或文档——立即识别并转换成您选择的语言。"},
|
||||
"en": "Photo text translator lets you snap any photo containing text—menus, signs, or documents—and instantly recognize and translate it into your language of choice using advanced AI-powered translation technology.",
|
||||
"de": "Bild-Dolmetscher ermöglicht es Ihnen, jedes Foto mit Text – Menüs, Schilder oder Dokumente – zu fotografieren und es sofort in Ihre gewünschte Sprache zu erkennen und zu übersetzen, unter Verwendung fortschrittlicher KI-gestützter Übersetzungstechnologie.",
|
||||
"zh": "图片文字快译允许您拍摄任何包含文本的照片——菜单、标志或文档——立即识别并转换成您选择的语言。"},
|
||||
"canvas_type": "Consumer App",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -1,13 +1,13 @@
|
||||
{
|
||||
"id": 20,
|
||||
"title": {
|
||||
"en": "Report Agent Using Knowledge Base",
|
||||
"de": "Berichtsagent mit Wissensdatenbank",
|
||||
"zh": "知识库检索智能体"},
|
||||
"en": "Reflective academic paper generator",
|
||||
"de": "Schreibhilfe für Reflexionspapiere",
|
||||
"zh": "学术论文生成助手"},
|
||||
"description": {
|
||||
"en": "A report generation assistant using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
|
||||
"en": "A reflective academic paper generator using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
|
||||
"de": "Ein Berichtsgenerierungsassistent, der eine lokale Wissensdatenbank nutzt, mit erweiterten Fähigkeiten in Aufgabenplanung, Schlussfolgerung und reflektierender Analyse. Empfohlen für akademische Forschungspapier-Fragen und -Antworten.",
|
||||
"zh": "一个使用本地知识库的报告生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"},
|
||||
"zh": "一个使用本地知识库的学术论文生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"},
|
||||
"canvas_type": "Agent",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -1,13 +1,13 @@
|
||||
{
|
||||
"id": 21,
|
||||
"title": {
|
||||
"en": "Report Agent Using Knowledge Base",
|
||||
"de": "Berichtsagent mit Wissensdatenbank",
|
||||
"zh": "知识库检索智能体"},
|
||||
"en": "Reflective academic paper generator",
|
||||
"de": "Schreibhilfe für Reflexionspapiere",
|
||||
"zh": "学术论文生成助手"},
|
||||
"description": {
|
||||
"en": "A report generation assistant using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
|
||||
"en": "A reflective academic paper generator using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
|
||||
"de": "Ein Berichtsgenerierungsassistent, der eine lokale Wissensdatenbank nutzt, mit erweiterten Fähigkeiten in Aufgabenplanung, Schlussfolgerung und reflektierender Analyse. Empfohlen für akademische Forschungspapier-Fragen und -Antworten.",
|
||||
"zh": "一个使用本地知识库的报告生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"},
|
||||
"zh": "一个使用本地知识库的学术论文生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"},
|
||||
"canvas_type": "Recommended",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -1,13 +1,13 @@
|
||||
{
|
||||
"id": 8,
|
||||
"title": {
|
||||
"en": "Generate SEO Blog",
|
||||
"de": "SEO Blog generieren",
|
||||
"zh": "生成SEO博客"},
|
||||
"en": "SEO article writer",
|
||||
"de": "SEO-Blog-Magnetiseur",
|
||||
"zh": "SEO 博客写手"},
|
||||
"description": {
|
||||
"en": "This is a multi-agent version of the SEO blog generation workflow. It simulates a small team of AI “writers”, where each agent plays a specialized role — just like a real editorial team.",
|
||||
"de": "Dies ist eine Multi-Agenten-Version des Workflows zur Erstellung von SEO-Blogs. Sie simuliert ein kleines Team von KI-„Autoren“, in dem jeder Agent eine spezielle Rolle übernimmt – genau wie in einem echten Redaktionsteam.",
|
||||
"zh": "多智能体架构可根据简单的用户输入自动生成完整的SEO博客文章。模拟小型“作家”团队，其中每个智能体扮演一个专业角色——就像真正的编辑团队。"},
|
||||
"zh": "SEO 博客写手可根据简单的用户输入自动生成完整的SEO博客文章。模拟小型“作家”团队，其中每个智能体扮演一个专业角色——就像真正的编辑团队。"},
|
||||
"canvas_type": "Agent",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -1,13 +1,13 @@
|
||||
{
|
||||
"id": 4,
|
||||
"title": {
|
||||
"en": "Generate SEO Blog",
|
||||
"de": "SEO Blog generieren",
|
||||
"zh": "生成SEO博客"},
|
||||
"en": "SEO article writer",
|
||||
"de": "SEO-Blog-Magnetiseur",
|
||||
"zh": "SEO 博客写手"},
|
||||
"description": {
|
||||
"en": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don't need any writing experience. Just provide a topic or short request — the system will handle the rest.",
|
||||
"de": "Dieser Workflow generiert automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
|
||||
"zh": "此工作流根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
|
||||
"en": "This SEO article writer automatically generates a complete SEO-optimized blog article based on a simple user input. You don't need any writing experience. Just provide a topic or short request — the system will handle the rest.",
|
||||
"de": "SEO-Blog-Magnetiseur automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
|
||||
"zh": "此 SEO 博客写手根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
|
||||
"canvas_type": "Recommended",
|
||||
"dsl": {
|
||||
"components": {
|
||||
@@ -1,14 +1,14 @@
|
||||
{
|
||||
"id": 22,
|
||||
"title": {
|
||||
"en": "Ecommerce Customer Service Workflow",
|
||||
"en": "Smart customer service specialist",
|
||||
"de": "Ecommerce Kundenservice Workflow",
|
||||
"zh": "电子商务客户服务工作流程"
|
||||
"zh": "智能客户服务专员"
|
||||
},
|
||||
"description": {
|
||||
"en": "This template helps e-commerce platforms address complex customer needs, such as comparing product features, providing usage support, and coordinating home installation services.",
|
||||
"de": "Diese Vorlage hilft E-Commerce-Plattformen, komplexe Kundenbedürfnisse zu erfüllen, wie z.B. den Vergleich von Produktmerkmalen, die Bereitstellung von Nutzungsunterstützung und die Koordination von Hausinstallationsdiensten.",
|
||||
"zh": "该模板可帮助电子商务平台解决复杂的客户需求，例如比较产品功能、提供使用支持和协调家庭安装服务。"
|
||||
"en": "This template helps address complex customer needs, such as comparing product features, providing usage support, and coordinating home installation services.",
|
||||
"de": "Diese Vorlage hilft komplexe Kundenbedürfnisse zu erfüllen, wie z.B. den Vergleich von Produktmerkmalen, die Bereitstellung von Nutzungsunterstützung und die Koordination von Hausinstallationsdiensten.",
|
||||
"zh": "该模板可帮助解决复杂的客户需求，例如比较产品功能、提供使用支持和协调家庭安装服务。"
|
||||
},
|
||||
"canvas_type": "Customer Support",
|
||||
"dsl": {
|
||||
File diff suppressed because one or more lines are too long
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"id": 17,
|
||||
"title": {
|
||||
"en": "SQL Assistant",
|
||||
"de": "SQL Assistent",
|
||||
"zh": "SQL助理"},
|
||||
"en": "Text-to-SQL data expert",
|
||||
"de": "Text-to-SQL-Datenexperte",
|
||||
"zh": "Text-to-SQL 问数专家"},
|
||||
"description": {
|
||||
"en": "SQL Assistant is an AI-powered tool that lets business users turn plain-English questions into fully formed SQL queries. Simply type your question (e.g., 'Show me last quarter's top 10 products by revenue') and SQL Assistant generates the exact SQL, runs it against your database, and returns the results in seconds. ",
|
||||
"de": "SQL-Assistent ist ein KI-gestütztes Tool, mit dem Geschäftsanwender einfache englische Fragen in vollständige SQL-Abfragen umwandeln können. Geben Sie einfach Ihre Frage ein (z.B. 'Zeige mir die Top 10 Produkte des letzten Quartals nach Umsatz') und der SQL-Assistent generiert das exakte SQL, führt es gegen Ihre Datenbank aus und liefert die Ergebnisse in Sekunden.",
|
||||
"en": "Text-to-SQL data expert lets business users turn plain-English questions into fully formed SQL queries. Simply type your question (e.g., 'Show me last quarter's top 10 products by revenue') and Text-to-SQL data expert generates the exact SQL, runs it against your database, and returns the results in seconds. ",
|
||||
"de": "Text-to-SQL-Datenexperte ist ein KI-gestütztes Tool, mit dem Geschäftsanwender einfache englische Fragen in vollständige SQL-Abfragen umwandeln können. Geben Sie einfach Ihre Frage ein (z.B. 'Zeige mir die Top 10 Produkte des letzten Quartals nach Umsatz') und der SQL-Assistent generiert das exakte SQL, führt es gegen Ihre Datenbank aus und liefert die Ergebnisse in Sekunden.",
|
||||
"zh": "用户能够将简单文本问题转化为完整的SQL查询并输出结果。只需输入您的问题（例如，展示上个季度前十名按收入排序的产品），SQL助理就会生成精确的SQL语句，对其运行您的数据库，并几秒钟内返回结果。"},
|
||||
"canvas_type": "Marketing",
|
||||
"dsl": {
|
||||
@@ -2,13 +2,13 @@
|
||||
{
|
||||
"id": 14,
|
||||
"title": {
|
||||
"en": "Trip Planner",
|
||||
"en": "Trip planner",
|
||||
"de": "Reiseplaner",
|
||||
"zh": "旅行规划"},
|
||||
"zh": "旅行规划师"},
|
||||
"description": {
|
||||
"en": "This smart trip planner utilizes LLM technology to automatically generate customized travel itineraries, with optional tool integration for enhanced reliability.",
|
||||
"de": "Dieser intelligente Reiseplaner nutzt LLM-Technologie zur automatischen Generierung maßgeschneiderter Reiserouten mit optionaler Tool-Integration für erhöhte Zuverlässigkeit.",
|
||||
"zh": "智能旅行规划将利用大模型自动生成定制化的旅行行程，附带可选工具集成，以增强可靠性。"},
|
||||
"zh": "智能旅行规划师将利用大模型自动生成定制化的旅行行程，附带可选工具集成，以增强可靠性。"},
|
||||
"canvas_type": "Consumer App",
|
||||
"dsl": {
|
||||
"components": {
|
||||
|
||||
@@ -2,14 +2,14 @@
|
||||
{
|
||||
"id": 9,
|
||||
"title": {
|
||||
"en": "Technical Docs QA",
|
||||
"de": "Technische Dokumentation Fragen & Antworten",
|
||||
"zh": "技术文档问答"},
|
||||
"en": "Your starter dataset chatbot",
|
||||
"de": "Dein Starter-Datensatz-Chatbot",
|
||||
"zh": "入门级知识库聊天助手"},
|
||||
"description": {
|
||||
"en": "This is a document question-and-answer system based on a knowledge base. When a user asks a question, it retrieves relevant document content to provide accurate answers.",
|
||||
"de": "Dies ist ein dokumentenbasiertes Frage-und-Antwort-System auf Basis einer Wissensdatenbank. Wenn ein Benutzer eine Frage stellt, werden relevante Dokumenteninhalte abgerufen, um genaue Antworten zu liefern.",
|
||||
"zh": "基于知识库的文档问答系统，当用户提出问题时，会检索相关本地文档并提供准确回答。"},
|
||||
"canvas_type": "Customer Support",
|
||||
"zh": "基于知识库的入门级知识库聊天助手，当用户提出问题时，会检索相关本地文档并提供准确回答。"},
|
||||
"canvas_type": "Recommended",
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Agent:StalePandasDream": {
|
||||
@@ -24,7 +24,7 @@ The **Execute SQL** tool enables you to connect to a relational database and run
|
||||
|
||||
## Examples
|
||||
|
||||
You can pair an **Agent** component with the **Execute SQL** tool, with the **Agent** generating SQL statements and the **Execute SQL** tool handling database connection and query execution. An example of this setup can be found in the **SQL Assistant** Agent template shown below:
|
||||
You can pair an **Agent** component with the **Execute SQL** tool, with the **Agent** generating SQL statements and the **Execute SQL** tool handling database connection and query execution. An example of this setup can be found in the **Text-to-SQL data expert** Agent template shown below:
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -43,7 +43,7 @@ We also provide templates catered to different business scenarios. You can eithe
|
||||
|
||||
|
||||
|
||||
2. To create an agent from scratch, click **Create Agent**. Alternatively, to create an agent from one of our templates, click the desired card, such as **Deep Research**, name your agent in the pop-up dialogue, and click **OK** to confirm.
|
||||
2. To create an agent from scratch, click **Create Agent**. Alternatively, to create an agent from one of our templates, click the desired card, such as **Deep research**, name your agent in the pop-up dialogue, and click **OK** to confirm.
|
||||
|
||||
*You are now taken to the **no-code workflow editor** page.*
|
||||
|
||||
|
||||
@@ -25,6 +25,6 @@ To activate this feature:
|
||||
|
||||
|
||||
|
||||
*The following is a screenshot of a conversation that integrates Deep Research:*
|
||||
*The following is a screenshot of a conversation that integrates Deep research:*
|
||||
|
||||
|
||||
@@ -40,7 +40,7 @@ You start an AI conversation by creating an assistant.
|
||||
- **Top N** determines the *maximum* number of chunks to feed to the LLM. In other words, even if more chunks are retrieved, only the top N chunks are provided as input.
|
||||
- **Multi-turn optimization** enhances user queries using existing context in a multi-round conversation. It is enabled by default. When enabled, it will consume additional LLM tokens and significantly increase the time to generate answers.
|
||||
- **Use knowledge graph** indicates whether to use knowledge graph(s) in the specified dataset(s) during retrieval for multi-hop question answering. When enabled, this would involve iterative searches across entity, relationship, and community report chunks, greatly increasing retrieval time.
|
||||
- **Reasoning** indicates whether to generate answers through reasoning processes like Deepseek-R1/OpenAI o1. Once enabled, the chat model autonomously integrates Deep Research during question answering when encountering an unknown topic. This involves the chat model dynamically searching external knowledge and generating final answers through reasoning.
|
||||
- **Reasoning** indicates whether to generate answers through reasoning processes like Deepseek-R1/OpenAI o1. Once enabled, the chat model autonomously integrates Deep research during question answering when encountering an unknown topic. This involves the chat model dynamically searching external knowledge and generating final answers through reasoning.
|
||||
- **Rerank model** sets the reranker model to use. It is left empty by default.
|
||||
- If **Rerank model** is left empty, the hybrid score system uses keyword similarity and vector similarity, and the default weight assigned to the vector similarity component is 1-0.7=0.3.
|
||||
- If **Rerank model** is selected, the hybrid score system uses keyword similarity and reranker score, and the default weight assigned to the reranker score is 1-0.7=0.3.
|
||||
|
||||
@@ -364,7 +364,7 @@ Released on August 8, 2025.
|
||||
|
||||
### New agent templates (both workflow and agentic)
|
||||
|
||||
- SQL Assistant Workflow: Empowers non-technical teams (e.g., operations, product) to independently query business data.
|
||||
- Text-to-SQL data expert Workflow: Empowers non-technical teams (e.g., operations, product) to independently query business data.
|
||||
- Choose Your Knowledge Base Workflow: Lets users select a dataset to query during conversations. [#9325](https://github.com/infiniflow/ragflow/pull/9325)
|
||||
- Choose Your Knowledge Base Agent: Delivers higher-quality responses with extended reasoning time, suited for complex queries. [#9325](https://github.com/infiniflow/ragflow/pull/9325)
|
||||
|
||||
@@ -397,14 +397,14 @@ From v0.20.0 onwards, Agents are no longer compatible with earlier versions, and
|
||||
|
||||
### New agent templates introduced
|
||||
|
||||
- Multi-Agent based Deep Research: Collaborative Agent teamwork led by a Lead Agent with multiple Subagents, distinct from traditional workflow orchestration.
|
||||
- Multi-Agent based Deep research: Collaborative Agent teamwork led by a Lead Agent with multiple Subagents, distinct from traditional workflow orchestration.
|
||||
- An intelligent Q&A chatbot leveraging internal datasets, designed for customer service and training scenarios.
|
||||
- A resume analysis template used by the RAGFlow team to screen, analyze, and record candidate information.
|
||||
- A blog generation workflow that transforms raw ideas into SEO-friendly blog content.
|
||||
- An intelligent customer service workflow.
|
||||
- A user feedback analysis template that directs user feedback to appropriate teams through semantic analysis.
|
||||
- Trip Planner: Uses web search and map MCP servers to assist with travel planning.
|
||||
- Image Lingo: Translates content from uploaded photos.
|
||||
- Trip planner: Uses web search and map MCP servers to assist with travel planning.
|
||||
- Photo text translator: Translates content from uploaded photos.
|
||||
- An information search assistant that retrieves answers from both internal datasets and the web.
|
||||
|
||||
## v0.19.1
|
||||
@@ -551,7 +551,7 @@ Released on March 3, 2025.
|
||||
|
||||
### New features
|
||||
|
||||
- AI chat: Implements Deep Research for agentic reasoning. To activate this, enable the **Reasoning** toggle under the **Prompt engine** tab of your chat assistant dialogue.
|
||||
- AI chat: Implements Deep research for agentic reasoning. To activate this, enable the **Reasoning** toggle under the **Prompt engine** tab of your chat assistant dialogue.
|
||||
- AI chat: Leverages Tavily-based web search to enhance contexts in agentic reasoning. To activate this, enter the correct Tavily API key under the **Assistant settings** tab of your chat assistant dialogue.
|
||||
- AI chat: Supports starting a chat without specifying datasets.
|
||||
- AI chat: HTML files can also be previewed and referenced, in addition to PDF files.
|
||||
@@ -561,11 +561,11 @@ Released on March 3, 2025.
|
||||
- Models: Updates the supported model list for Tongyi-Qianwen (Qwen), adding DeepSeek-specific models; adds ModelScope as a model provider.
|
||||
- APIs: Document metadata can be updated through an API.
|
||||
|
||||
The following diagram illustrates the workflow of RAGFlow's Deep Research:
|
||||
The following diagram illustrates the workflow of RAGFlow's Deep research:
|
||||
|
||||
|
||||
|
||||
The following is a screenshot of a conversation that integrates Deep Research:
|
||||
The following is a screenshot of a conversation that integrates Deep research:
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user